Agricultural product whole-course traceability system and method based on Internet of Things and RFID technology

Abstract

The invention provides an agricultural product whole-course traceability system and method based on the Internet of Things and the RFID technology. The system comprises a data collecting and uploading assembly, a real-time tracking and monitoring assembly and an information interaction feedback assembly. The method comprises the following steps: automatically acquiring key data by using an RFID technology; the key data is uploaded to the cloud platform in real time through the Internet of Things equipment; the transportation and storage process of the agricultural products is monitored in real time through the Internet of Things technology, and the circulation path of the agricultural products is tracked in combination with the RFID tags; modeling the flow path of the agricultural product into a graph structure by adopting a graph neural network, analyzing the relationship between path nodes, and optimizing the flow path planning of the agricultural product; a convenient query entrance is provided, the RFID tags are read through the RFID reader, and the quality safety information of the agricultural products is obtained in real time. According to the invention, full-flow transparent management of agricultural products from production to consumption is realized; the quality safety level of agricultural products is improved, the logistics efficiency is optimized, and the loss rate is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural product traceability, and particularly relates to a whole-process traceability system and method for agricultural products based on the Internet of Things and RFID technology. Background Art

[0002] The whole-process traceability of agricultural products refers to recording and tracking the whole process of agricultural products from production, processing, transportation to sales through technical means to ensure that the information of each link is transparent and traceable. The core of the whole-process traceability of agricultural products lies in "whole process" and "traceability", that is, every step from the field to the table can be traced, and consumers can understand information such as the origin, production environment and processing process of the product by scanning a QR code or other means. The implementation of the whole-process traceability technology of agricultural products is conducive to ensuring food safety, enhancing consumer trust, promoting agricultural modernization and facilitating brand building, etc.; the technologies commonly used in the existing technologies include blockchain, QR codes or barcodes, and big data analysis technologies. Although these technologies are advanced, they pose relatively high requirements on the operating device software and hardware, objectively increasing the cost of traceability.

[0003] Prior Art One. Application No.: CN202311280083.X discloses a whole-process traceability system for agricultural products based on blockchain. The system includes a memory and a processor. The processor executes the computer program stored in the memory to implement the following steps: obtaining the relevant information of each node in the traceability chain of the current batch of agricultural products, and determining the degree of danger according to the received quantity, shipped quantity, bad fruit rate, chemical test results of each node to be evaluated and the relative distance between it and the previous adjacent node; obtaining the updated credit score according to the number of participation in consensus, the number of effective consensus and the degree of danger of each node to be evaluated; screening the target nodes based on the updated credit score, and linking the relevant information of the target nodes into the traceability chain. Although it improves the accuracy and reliability of agricultural product traceability, the deployment cost is relatively high and the technical complexity is also greater.

[0004] Prior art 2, application number: CN202311476543.6 discloses a method and system for full-process traceability of agricultural products, including the steps of: the farmer logs in to the traceability platform, selects a regional block, and records the agricultural action information, farm information and agricultural materials information of the agricultural products planted at the front end, and sends the regional block selection information, agricultural action information, farm information and agricultural materials information to the traceability platform. The traceability platform writes the received information into the scan link corresponding to the QR code label on the agricultural product packaging. Although the consumer obtains the agricultural products, scans the QR code label on the agricultural product packaging to open the traceability link corresponding to the QR code label, and then obtains the agricultural product traceability information corresponding to the QR code, realizes the traceability of agricultural products, animal husbandry, aquatic products, etc., so that the source can be checked, the process can be seen, the destination can be traced, and the responsibility can be corrected, so that the elderly and low-educated farmers can operate simply and conveniently, and consumers can also rest assured; however, the uploading and storage of data depends on manual operation, there is a possibility of data tampering or forgery, and the anti-counterfeiting ability is weak.

[0005] Prior art three, application number: CN201910291045.1 discloses a system and system for the whole process quality control of agricultural products, including an agricultural product origin registration database system: a third-party regulatory agency intervenes, defines the production area of ​​the specific product pointed to by the brand in the database system, and registers the origin of the brand authorized merchants within the production area; agricultural product whole process traceability control system: based on the origin measured by GPS in the agricultural product origin registration database system, the whole process is traced, and the corresponding number of anti-counterfeiting buckles are issued according to the estimated output; agricultural product quality control personnel management system: agricultural product quality control personnel mainly standardize the production process and output specifications and grades of agricultural products. Although this system and system have changed the shortcomings of the general traceability system that cannot control the over-sale of agricultural products and eliminate counterfeit and shoddy products, and at the same time introduce third-party supervision and consumer supervision at key nodes, the system has a wide range of application prospects in cooperating with the creation of regional public brands; however, obtaining information through third-party regulatory agencies or anti-counterfeiting buckles is relatively simple, and real-time monitoring and dynamic data display cannot be achieved.

[0006] At present, the existing technologies 1, 2 and 3 have the problems of being unable to realize real-time monitoring and dynamic data display, the possibility of data tampering or forgery, and weak anti-counterfeiting ability. Therefore, the present invention provides a system and method for tracing the source of agricultural products based on the Internet of Things and RFID technology. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a system for tracing agricultural products based on the Internet of Things and RFID technology, comprising:

[0008] The data collection and upload component is responsible for automatically collecting key data in each link of agricultural products by using RFID technology; the key data is uploaded to the cloud platform in real time through Internet of Things devices;

[0009] The real-time tracking and monitoring component is responsible for real-time monitoring of the transportation and storage processes of agricultural products through Internet of Things technology, and combining with RFID tags to track the transfer path of agricultural products; using graph neural network to model the transfer path of agricultural products as a graph structure, analyzing the relationships between path nodes, and optimizing the transfer path planning of agricultural products;

[0010] The information interaction and feedback component is responsible for providing a convenient query entrance for consumers, reading RFID tags through RFID readers, and obtaining the quality and safety information of agricultural products in real time.

[0011] Optionally, the data collection and upload component includes:

[0012] The dynamic capture module is responsible for realizing the dynamic capture of key data in multiple dimensions such as environmental temperature and humidity, soil nutrients, pesticide use records, and transportation trajectories by deploying an adaptive sensing network; realizing the correlation analysis between key data in multiple dimensions by introducing the quantum entanglement effect;

[0013] The tag binding module is responsible for converting key data into a standardized format, generating a dynamic code for key data by using an encoding mapping mechanism, and binding it to the RFID tag;

[0014] The cloud synchronization module is responsible for uploading the key data bound to the RFID tag to the cloud platform in real time; during transportation, the RFID tag communicates with the vehicle-mounted Internet of Things device in real time, and encrypts and uploads the transportation trajectory data to the cloud platform.

[0015] Optionally, the dynamic capture module includes:

[0016] The network formation sub-module is responsible for constructing a quantum state preparation system at the central node of the adaptive sensing network, preparing a multi-particle entangled state with high coherence, and distributing the multi-particle entangled state to each sensing node through a quantum channel to form a quantum state distribution network;

[0017] The data correlation sub-module is responsible for naturally correlating key data in multiple dimensions in the quantum superposition state after the quantum state carrying environmental information is converged to the central node through the quantum channel, so that non-classical correlations are generated between key data in different dimensions, and extracting the correlation network between key data in multiple dimensions;

[0018] The quantum measurement sub-module is responsible for the central node to measure the quantum superposition state through quantum measurement, and the result is presented in the form of a probability distribution, including the correlation information between key data in multiple dimensions.

[0019] Optionally, the tag binding module includes:

[0020] A data conversion sub-module responsible for extracting time series features from multi-dimensional key data, including the change trend of key data in a single dimension and the co-variation pattern between multi-dimensional key data; converting the correlation and time series features of multi-dimensional key data into dynamic codes;

[0021] An encoding conversion sub-module responsible for converting the time series features in the dynamic code into a signal sequence of neuron pulses, while the correlation of multi-dimensional key data is converted into a co-variation pattern between signals;

[0022] A feature embedding sub-module responsible for converting the time series features in the dynamic code into timestamp information in the RFID tag after signal modulation, while the correlation of multi-dimensional key data is converted into associated fields in the tag.

[0023] Optionally, the real-time tracking and monitoring component includes:

[0024] A path confirmation module responsible for scanning agricultural products entering the transfer location using an RFID reading device to obtain the attribute data of the agricultural products, calling the transfer locations passed by the agricultural products from the transfer path database to obtain a set of transfer locations; determining the transfer path of the agricultural products by combining the starting transfer location and the ending transfer location of the agricultural products;

[0025] A model construction module responsible for abstracting the transfer path of agricultural products into a graph structure, so that the transfer network of agricultural products is converted into a dynamic graph structure;

[0026] A recommendation generation module responsible for inputting the graph structure data of the transfer path into the graph structure model; selecting the transfer path according to the scoring result and generating a transfer path recommendation.

[0027] Optionally, the path confirmation module includes:

[0028] A record acquisition sub-module responsible for calling the historical transfer records of agricultural products from the transfer path database according to the RFID tag number of the agricultural products, with each transfer location attached with a timestamp, an operation type, and environmental data;

[0029] A set formation sub-module responsible for sorting the transfer locations in chronological order after obtaining the historical transfer records to form a set of transfer locations, which records the transfer trajectory of the agricultural products and also includes multi-dimensional feature information of each location;

[0030] An information supplement sub-module responsible for verifying and supplementing the set of transfer locations. If the environmental data of a certain transfer location is missing, it is supplemented through correlation analysis.

[0031] Optionally, it is recommended that the generation module generate a graph structure model, including node features, edge features, and historical transfer data.

[0032] Optionally, the recommended generation module includes:

[0033] A node feature extraction sub-module responsible for mapping the initial features of the geographical location, capacity, and historical transportation volume of each node to a higher-dimensional space; transforming the initial features of the transportation time, cost, and environmental conditions of each edge into a higher-order representation; capturing the patterns and relationships of node and edge features through the non-linear transformation of a multi-layer neural network;

[0034] A message passing mechanism sub-module responsible for each node generating a message based on its own features and the features of its neighbor nodes, and the node aggregating the received messages; updating the feature representation of the node according to the aggregated messages, and the updated features include the information of the node itself and the information of its neighbor nodes; through multiple rounds of message passing, the features of the node gradually capture the global information of the entire graph;

[0035] A transportation path scoring sub-module responsible for calculating the total time of the path through the edge features and node features; calculating the total cost of the path through the edge features and node features; evaluating the environmental impact of the path through the edge features and node features, inputting the feature vector of the path, and outputting a score value.

[0036] Optionally, the information interaction feedback component includes:

[0037] An RFID reading module responsible for when consumers need to query the quality and safety information of agricultural products, reading the RFID tag on the agricultural product through an RFID reader, the RFID reader emitting a radio frequency signal to activate the tag, and the RFID tag transmitting the stored information back to the RFID reader;

[0038] An information query module responsible for displaying the read information, including the transfer path of the agricultural product, environmental temperature and humidity records, and pesticide use records, to consumers;

[0039] A feedback interaction module responsible for consumers uploading feedback information to the cloud platform through information interaction feedback.

[0040] A method for the whole-process traceability of agricultural products based on the Internet of Things and RFID technology provided by the present invention includes the following steps:

[0041] Using RFID technology to automatically collect key data at each link of agricultural products; the key data is uploaded to the cloud platform in real time through Internet of Things devices;

[0042] Real-time monitor the transportation and storage processes of agricultural products through Internet of Things technology, combine with RFID tags to track the circulation path of agricultural products; use graph neural network to model the circulation path of agricultural products as a graph structure, analyze the relationships between path nodes, and optimize the circulation path planning of agricultural products;

[0043] Provide a convenient query entrance, read the RFID tag through an RFID reader, and obtain the quality and safety information of agricultural products in real time.

[0044] The RFID tag of the data acquisition and upload component of the present invention serves as a data carrier, which can quickly and accurately record and transmit information, ensuring the integrity and timeliness of the data. The real-time tracking and monitoring component can dynamically adjust the transportation plan, reduce transportation time and costs, and at the same time avoid the loss of agricultural products caused by environmental changes. The information interaction and feedback component's transparent information display method allows consumers to comprehensively understand the overall process of agricultural products.

[0045] Other features and advantages of the present invention will be described in the subsequent specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained by the structure specifically pointed out in the written specification and the drawings.

[0046] The technical solution of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0047] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0048] Figure 1 It is the block diagram of the whole-process traceability system for agricultural products based on Internet of Things and RFID technology in Embodiment 1 of the present invention;

[0049] Figure 2 It is the block diagram of the data acquisition and upload component in Embodiment 2 of the present invention;

[0050] Figure 3 It is the block diagram of the dynamic capture module in Embodiment 3 of the present invention;

[0051] Figure 4 It is the block diagram of the tag binding module in Embodiment 4 of the present invention;

[0052] Figure 5 It is the block diagram of the real-time tracking and monitoring component in Embodiment 5 of the present invention;

[0053] Figure 6 It is the block diagram of the path confirmation module in Embodiment 6 of the present invention;

[0054] Figure 7 Block diagram of the model construction module in Embodiment 7 of the present invention

[0055] Figure 8 Block diagram of the suggestion generation module in Embodiment 8 of the present invention

[0056] Figure 9 Block diagram of the information interaction feedback component in Embodiment 9 of the present invention

[0057] Figure 10 Flowchart of the whole-process traceability method for agricultural products based on the Internet of Things and RFID technology in Embodiment 10 of the present invention Detailed implementation manners

[0058] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0059] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. In the embodiments of the present application, the singular forms of "a", "the" and "said" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0060] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are only examples of devices and methods consistent with some aspects of the present application. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0061] Embodiment 1: As Figure 1 shown, the embodiment of the present invention provides a whole-process traceability system for agricultural products based on the Internet of Things and RFID technology, including:

[0062] A data collection and upload component, which is responsible for using RFID technology to automatically collect key data such as environmental temperature and humidity, soil nutrients, pesticide usage records, and transportation trajectories in various links of agricultural product production, processing, transportation, warehousing, and sales; the key data is uploaded to the cloud platform in real time through Internet of Things devices;

[0063] The real-time tracking and monitoring component is responsible for real-time monitoring of the transportation and storage processes of agricultural products through Internet of Things technology. Combining with RFID tags, it tracks the transfer paths of agricultural products. It uses graph neural networks to model the transfer paths of agricultural products as graph structures, analyzes the relationships between path nodes, and optimizes the transfer path planning of agricultural products.

[0064] The information interaction and feedback component is responsible for providing consumers with a convenient query entrance. It reads RFID tags through RFID readers to obtain the quality and safety information of agricultural products in real time.

[0065] The working principles and beneficial effects of the above technical solutions are as follows: The data collection and upload component in this embodiment uses RFID technology to automatically collect key data including environmental temperature and humidity, soil nutrients, pesticide usage records, and transportation trajectories in various links such as the production, processing, transportation, storage, and sales of agricultural products. The key data is uploaded to the cloud platform in real time through Internet of Things devices. The real-time tracking and monitoring component monitors the transportation and storage processes of agricultural products in real time through Internet of Things technology. Combining with RFID tags, it tracks the transfer paths of agricultural products. It uses graph neural networks to model the transfer paths of agricultural products as graph structures, analyzes the relationships between path nodes, and optimizes the transfer path planning of agricultural products. The information interaction and feedback component provides consumers with a convenient query entrance. It reads RFID tags through RFID readers to obtain the quality and safety information of agricultural products in real time. The RFID tags of the data collection and upload component in the above solution are used as data carriers, which can record and transmit information quickly and accurately, ensuring the integrity and timeliness of the data. Significance: Through real-time data collection and upload, producers and managers can timely grasp the growth environment, processing process, and logistics status of agricultural products, ensuring standardized operations in each link. At the same time, the transparency of the data also provides a reliable basis for regulatory authorities, helping to improve the quality and safety level of agricultural products and enhancing consumers' trust. The real-time tracking and monitoring component can dynamically adjust the transportation plan, reducing transportation time and costs, and at the same time avoiding losses of agricultural products caused by environmental changes. Significance: Real-time tracking and path optimization not only improve logistics efficiency but also reduce the loss rate of agricultural products, ensuring the quality of agricultural products during transportation and storage. In addition, through path optimization, carbon emissions can be reduced, promoting the development of green logistics, which is in line with the concept of sustainable development. The transparent information display method of the information interaction and feedback component allows consumers to comprehensively understand the overall process of agricultural products. Significance: The information interaction and feedback component shortens the distance between consumers and producers, enhancing consumers' trust in agricultural products. At the same time, the transparent information display also helps to improve the brand image and promote the market competitiveness of high-quality agricultural products. Consumers can choose safer and healthier agricultural products by querying information, thus promoting the healthy development of the entire industry.

[0066] In summary, through the collaborative work of three components: data collection and upload, real-time tracking and monitoring, and information interaction and feedback, the present embodiment realizes the transparent management of the entire process of agricultural products from production to consumption. It not only improves the quality and safety level of agricultural products, but also optimizes the logistics efficiency, reduces the loss rate, and enhances consumers' trust. More importantly, the system provides strong support for the digital transformation of agriculture, promotes the intelligent upgrading of the agricultural industrial chain, and injects new impetus into rural revitalization and sustainable development.

[0067] Embodiment 2: As Figure 2 shown, on the basis of Embodiment 1, the data collection and upload component provided by the embodiment of the present invention includes:

[0068] The dynamic capture module is responsible for dynamically capturing key data in multiple dimensions such as environmental temperature and humidity, soil nutrients, pesticide usage records, and transportation trajectories by deploying an adaptive sensing network; and realizing the correlation analysis between key data in multiple dimensions by introducing the quantum entanglement effect;

[0069] The tag binding module is responsible for converting the key data into a standardized format, generating a dynamic code for the key data using a coding mapping mechanism, and binding it to an RFID tag;

[0070] The cloud synchronization module is responsible for uploading the key data bound to the RFID tag to the cloud platform in real time; during transportation, the RFID tag communicates with the vehicle-mounted Internet of Things device in real time, and encrypts and uploads the transportation trajectory data to the cloud platform.

[0071] The working principle and beneficial effects of the above technical solution are as follows: The dynamic capture module of this embodiment realizes the dynamic capture of key data in multiple dimensions such as environmental temperature and humidity, soil nutrients, pesticide usage records, and transportation trajectories by deploying an adaptive sensing network; realizes the correlation analysis between key data in multiple dimensions by introducing the quantum entanglement effect; the tag binding module converts the key data into a standardized format, generates a dynamic code for the key data using an encoding mapping mechanism, and binds it to the RFID tag; the cloud synchronization module uploads the key data bound to the RFID tag to the cloud platform in real time; during transportation, the RFID tag communicates with the vehicle-mounted Internet of Things device in real time, encrypts the transportation trajectory data, and uploads it to the cloud platform. The adaptive sensing network of the dynamic capture module in the above solution can be flexibly deployed to adapt to various complex environments; the quantum entanglement effect realizes the correlation analysis of multi-dimensional data, improving the data value; real-time capture of multi-dimensional data such as the environment, soil, and pesticides ensures the comprehensiveness of the data. Significance: Provide a reliable data basis for precision agriculture; realize the whole-process monitoring of agricultural production; improve the depth and breadth of data analysis for agricultural product traceability. The data standardization process of the tag binding module ensures data compatibility, the dynamic coding mechanism improves data security, and the RFID tag binding realizes the physical carrier of data. Significance: Establish a unified data standard system, realize the traceability of data, and provide a basis for the circulation of agricultural product traceability data. The cloud synchronization module uploads in real time to ensure data timeliness, and the encrypted transmission ensures data security. The vehicle-mounted Internet of Things device realizes the whole-process monitoring during transportation. Significance: Build a complete data closed-loop, realize the transparent management of the whole process, and provide real-time data support for big data analysis.

[0072] In summary, this embodiment realizes the full-process management from data collection to upload, providing strong technical support for the digital transformation of modern agriculture. It not only improves agricultural production efficiency but also provides a reliable data basis for food safety traceability and precision agriculture management.

[0073] Embodiment 3: As Figure 3 shown, based on Embodiment 2, the dynamic capture module provided by the embodiment of the present invention includes:

[0074] The network formation sub-module is responsible for constructing a quantum state preparation system at the central node of the adaptive sensing network, preparing a multi-particle entangled state with high coherence, and distributing the multi-particle entangled state to each sensing node through a quantum channel to form a quantum state distribution network;

[0075] Among them, for the environmental temperature and humidity data, the quantum state in the sensing node will interact with the thermal radiation field and humidity field in the environment; temperature changes will change the decoherence rate of the quantum state, while humidity changes will affect the phase evolution of the quantum state; through the coupling of the quantum state and the environmental field, the temperature information is encoded as the population distribution of the quantum state, and the humidity information is encoded as the coherent phase of the quantum state. The encoding method realizes the quantization representation of environmental parameters;

[0076] In soil nutrient monitoring, quantum states interact with ion concentrations and organic matter content in the soil; different nutrient components change the energy level structure of quantum states, causing specific energy level transitions in quantum states; soil nutrient information can be accurately extracted by measuring transition spectra, and the superposition characteristics of quantum states allow the detection of multiple nutrient components to be performed simultaneously, improving detection efficiency;

[0077] For pesticide usage records, quantum states will undergo specific quantum chemical reactions with pesticide molecules. Different pesticide molecules will induce quantum states to produce unique decoherence patterns, which can be used as fingerprint features of pesticide types. By analyzing the decoherence dynamics of quantum states, accurate identification of pesticide types and dosage determination can be achieved.

[0078] The data association submodule is responsible for converging the quantum state carrying environmental information to the central node through the quantum channel, realizing the natural association of multi-dimensional key data in the quantum superposition state, so that non-classical associations are generated between key data of different dimensions, and extracting the association network between multi-dimensional key data;

[0079] The quantum measurement submodule is responsible for the central node to measure the quantum superposition state through quantum measurement. The results are presented in the form of probability distribution, which contains the correlation information between multi-dimensional key data.

[0080] The working principle and beneficial effects of the above technical solution are as follows: The network formation sub-module of this embodiment adaptively senses the central node of the network to construct a quantum state preparation system, which prepares a multi-particle entangled state with high coherence. The multi-particle entangled state is distributed to each sensing node through a quantum channel to form a quantum state distribution network. Among them, for the environmental temperature and humidity data, the quantum state in the sensing node will interact with the thermal radiation field and humidity field in the environment. Temperature changes will change the decoherence rate of the quantum state, while humidity changes will affect the phase evolution of the quantum state. Through the coupling of the quantum state and the environmental field, temperature information is encoded as the population distribution of the quantum state, and humidity information is encoded as the coherent phase of the quantum state. The encoding method realizes the quantization representation of environmental parameters. In soil nutrient monitoring, the quantum state will interact with the ion concentration and organic matter content in the soil. Different nutrient components will change the energy level structure of the quantum state, resulting in specific energy level transitions of the quantum state. By measuring the transition spectral lines, soil nutrient information can be accurately extracted. The superposition property of the quantum state enables the detection of multiple nutrient components to be carried out simultaneously, improving the detection efficiency. For pesticide usage records, the quantum state will undergo specific quantum chemical reactions with pesticide molecules. Different pesticide molecules will induce unique decoherence patterns in the quantum state, and this pattern can be used as a fingerprint feature of pesticide types. By analyzing the decoherence dynamics of the quantum state, accurate identification of pesticide types and determination of usage amounts can be achieved. After the data association sub-module converges the quantum states carrying environmental information to the central node through the quantum channel, natural association of multi-dimensional key data is realized in the quantum superposition state, enabling non-classical association between key data in different dimensions and extracting the association network between multi-dimensional key data. The quantum measurement sub-module in the central node measures the quantum superposition state through quantum measurement, and the result is presented in the form of a probability distribution, including the association information between multi-dimensional key data. The network formation sub-module of the above solution can, by constructing a quantum state preparation system, prepare a highly coherent multi-particle entangled state and distribute it to each sensing node through a quantum channel to form a quantum state distribution network, capable of real-time sensing and transmitting environmental parameters such as temperature and humidity, soil nutrients, and pesticide usage. Significance: The establishment of the quantum state distribution network makes the monitoring of environmental parameters more accurate and efficient. The coherence and entanglement characteristics of the quantum state ensure the high-fidelity transmission of data, providing a solid foundation for data processing and analysis. The data association sub-module realizes the natural association of multi-dimensional data, making environmental monitoring data more comprehensive and systematic. The association network provides strong support for multi-dimensional analysis of environmental changes, helping to better understand and predict environmental changes. The quantum measurement sub-module provides a high-precision data measurement method, ensuring the accuracy and reliability of data. Through the form of probability distribution, the association between multi-dimensional data can be more intuitively displayed, providing a scientific basis for decision-making.

[0081] In summary, through the application of quantum technology, the dynamic capture module in this embodiment achieves high-precision monitoring of environmental parameters and natural correlation of multi-dimensional data. It not only improves the efficiency and accuracy of environmental monitoring, but also provides strong support for precision agriculture and environmental protection; through the coherence and superposition characteristics of quantum states, it realizes the quantization representation of environmental parameters and the natural correlation of multi-dimensional data, bringing revolutionary changes to environmental monitoring and agricultural management.

[0082] Embodiment 4: As Figure 4 shown, based on Embodiment 2, the tag binding module provided by the embodiment of the present invention includes:

[0083] A data conversion sub-module, responsible for extracting time series features from multi-dimensional key data, including the change trend of key data in a single dimension and the co-variation pattern between multi-dimensional key data; converting the correlation and time series features of multi-dimensional key data into dynamic coding;

[0084] An encoding conversion sub-module, responsible for converting the time series features in the dynamic coding into a signal sequence of neuron pulses, while the correlation of multi-dimensional key data is converted into a co-variation pattern between signals;

[0085] A feature embedding sub-module, responsible for after signal modulation, converting the time series features in the dynamic coding into timestamp information in the RFID tag, while the correlation of multi-dimensional key data is converted into an associated field in the tag.

[0086] Among them, the formula of the data conversion sub-module:

[0087]

[0088] In the formula, E(t) represents the output function of the data conversion sub-module, representing the converted features at time t; w i represents the weight parameter, representing the weight of the i-th feature; ReLU represents the activation function, representing the rectified linear unit function, that is, when the input is greater than, the input value is output, otherwise the output is ; x i (t) represents the i-th feature value at time t; μ i represents the mean of the i-th feature; represents the exponential function, where λ i is the decay coefficient; Dropout represents a regularization technique that randomly discards some neuron nodes, here representing performing dropout operation on w i ; tanh represents the hyperbolic tangent function;

[0089] The encoding conversion sub-module captures local features in the signal and combines Fourier transform to extract the frequency information formula of the signal:

[0090]

[0091] In the formula, S(t) represents the output function of the encoding conversion sub-module, representing the encoded feature at time t; d i (t) represents the i-th eigenvalue after being processed by the encoding conversion sub-module; σ i represents the standard deviation of the i-th feature; represents the cosine function, representing periodic changes; Wavelet represents wavelet transform; Fourier represents Fourier transform;

[0092] Formula of the feature embedding sub-module:

[0093]

[0094] In the formula, F(t) represents the output function of the feature embedding sub-module, representing the feature embedding at time t; represents the Sigmoid function, representing the probability of a binary classification problem; α j represents the weight parameter, representing the weight of the j-th convolutional kernel; β represents the bias term; Conv(S j (t)) represents a convolutional operation, performing convolution on S j (t).

[0095] The working principle and beneficial effects of the above technical solution are as follows: The data conversion sub-module in this embodiment extracts time series features from multi-dimensional key data, including the change trend of key data in a single dimension and the co-variation pattern between multi-dimensional key data; it converts the correlation and time series features of multi-dimensional key data into dynamic encoding; the encoding conversion sub-module converts the time series features in the dynamic encoding into a signal sequence of neuron pulses, while the correlation of multi-dimensional key data is converted into a co-variation pattern between signals; after the signal modulation is completed by the feature embedding sub-module, the time series features in the dynamic encoding are converted into timestamp information in the RFID tag, and the correlation of multi-dimensional key data is converted into an associated field in the tag. The data conversion sub-module of the above solution is mainly responsible for extracting time series features from multi-dimensional data, being able to identify the change trend of single-dimensional data, such as the change of the sales volume of a certain commodity over time; it can also analyze the co-variation pattern between data in different dimensions, such as the correlation of sales volumes in different regions. Significance: In this way, the dynamic changes of data can be captured, which helps to predict future data trends and enables a deeper understanding of the complex relationships between data. The encoding conversion sub-module converts the time series features in the dynamic encoding into a signal sequence of neuron pulses, that is, simulating the working mode of human brain neurons; at the same time, the correlation of multi-dimensional data is converted into a co-variation pattern between signals, strengthening the mutual influence and interaction between signals. Significance: It concretizes the abstract time series data into neuron activities; in addition, the conversion of the co-variation pattern between signals helps to build a more complex data model, improving the prediction accuracy and robustness of the model. The feature embedding sub-module: embeds the time series features after signal modulation into the RFID tag, presented in the form of a timestamp; at the same time, the correlation of multi-dimensional key data is converted into an associated field in the tag, enhancing the readability and information content of the tag. Significance: By embedding the time series features and data correlation into the RFID tag, each tag can contain rich information, facilitating tracking and identification. Especially in scenarios such as supply chain management and product anti-counterfeiting, it greatly improves the efficiency and accuracy.

[0096] In summary, through highly data processing and conversion by each sub-module of the tag binding module in this embodiment, complex data becomes easy to manage and apply. It not only improves the operability of data but also enhances the prediction ability and information value of data.

[0097] Embodiment 5: As Figure 5 shown, on the basis of Embodiment 1, the real-time tracking and monitoring component provided by the embodiment of the present invention includes:

[0098] A path confirmation module, responsible for using an RFID reading device to scan agricultural products entering the transfer location, obtaining the attribute data of the agricultural products. The attribute data includes the current link and key data of the agricultural products, calling the transfer locations passed by the agricultural products from the transfer path database to obtain a set of transfer locations; determining the transfer path of the agricultural products in combination with the starting transfer location and the ending transfer location of the agricultural products;

[0099] A model construction module, responsible for abstracting the transfer path of agricultural products into a graph structure, so that the transfer network of agricultural products is transformed into a dynamic graph structure;

[0100] Among them, nodes represent key nodes in the transfer path, such as production bases, processing plants, logistics centers, storage points, and sales terminals, etc.; edges represent the connection relationships between nodes, such as transfer routes, transfer times, transfer costs, etc.; node features indicate that each node can contain multi-dimensional features, such as geographical location, temperature and humidity conditions, transportation capacity, and storage capacity, etc.; edge features represent that each edge can contain features such as transportation distance, transportation time, transportation cost, and environmental conditions, etc.;

[0101] A suggestion generation module, responsible for inputting the graph structure data of the transfer path into a graph structure model, including node features, edge features, and historical transfer data; selecting a transfer path according to the scoring results and generating a transfer path suggestion.

[0102] The working principle and beneficial effects of the above technical solution are as follows: The path confirmation module in this embodiment uses an RFID reading device to scan agricultural products entering the transfer location to obtain the attribute data of the agricultural products. The attribute data includes the current link and key data of the agricultural products. The transfer locations passed by the agricultural products are called from the transfer path database to obtain a set of transfer locations; the transfer path of the agricultural products is determined by combining the starting transfer location and the ending transfer location of the agricultural products; the model construction module abstracts the transfer path of the agricultural products into a graph structure, so that the transfer network of the agricultural products is transformed into a dynamic graph structure; where the nodes represent the key nodes in the transfer path, such as production bases, processing plants, logistics centers, storage points, and sales terminals, etc.; the edges represent the connection relationships between the nodes, such as transfer routes, transfer times, transfer costs, etc.; the node features indicate that each node can contain multi-dimensional features, such as geographical location, temperature and humidity conditions, transportation capacity, and storage capacity, etc.; the edge features represent that each edge can contain features such as transportation distance, transportation time, transportation cost, and environmental conditions, etc.; the recommendation generation module inputs the graph structure data of the transfer path into the graph structure model, including node features, edge features, and historical transfer data; through a multi-layer neural network, feature learning is performed on the graph structure to extract the high-order features of the nodes and edges; through the message passing mechanism of the graph structure model, the relationships between the nodes are analyzed, and scores are given to each possible transportation path. The scoring criteria include transportation time, transportation cost, and environmental conditions, etc.; according to the scoring results, the transfer path is selected, and a transfer path recommendation is generated. The path confirmation module of the above solution ensures that each link in the transfer process of each batch of agricultural products can be accurately recorded and traced, improving the reliability and transparency of the traceability system; by integrating real-time data and historical data, a complete transfer path information is constructed, providing data support for path optimization. The model construction module defines multi-dimensional features (such as geographical location, temperature and humidity conditions, transportation capacity, transportation cost, etc.) for each node and edge, enabling the graph structure to comprehensively reflect the complexity of the transfer network. The achieved significance: Through graph structure modeling, the complex transfer network is transformed into a computable and analyzable data model, providing a basis for path optimization; the dynamic characteristics of the graph structure enable it to reflect the changes in the transfer network in real time (such as new nodes, edge feature updates, etc.), providing flexibility for path optimization. The recommendation generation module, through a multi-layer neural network, performs feature learning on the graph structure, extracts the high-order features of the nodes and edges, and captures the potential laws in the transfer network; uses the message passing mechanism of the graph structure model to analyze the relationships between the nodes, scores each possible transfer path (the scoring criteria include transportation time, transportation cost, environmental conditions, etc.), and generates the optimal transfer path recommendation according to the scoring results.Achieved Significance: By using intelligent algorithms to select the optimal transfer path, it reduces transportation costs, improves transportation efficiency, and ensures the quality and safety of agricultural products; dynamically adjusts the path planning according to real-time data (such as temperature and humidity changes, traffic conditions, etc.), enhancing the adaptability and practicality of the system; provides scientific decision-making basis for logistics managers and consumers, improving the transparency and controllability of the agricultural product transfer process.

[0103] In summary, through the collaborative work of the path confirmation module, model construction module, and recommendation generation module, the real-time tracking and monitoring component in this embodiment has achieved the following goals: every link from production to sales can be accurately recorded and tracked, enhancing consumers' trust in the quality of agricultural products; through advanced technologies such as graph neural networks, it realizes intelligent modeling and optimization of the transfer path, improving logistics efficiency; can dynamically adjust the path planning according to real-time data, ensuring the quality and safety of agricultural products; reduces transportation costs and shortens transportation time through path optimization, improving the overall logistics efficiency, and creating greater value for agricultural production and circulation.

[0104] Embodiment 6: As Figure 6 shown, based on Embodiment 5, the path confirmation module provided by the embodiment of the present invention includes:

[0105] A record acquisition sub-module, responsible for calling its historical transfer record from the transfer path database according to the RFID tag number of the agricultural product. Each transfer location is attached with a timestamp, operation type (such as warehousing, outbound, transportation, etc.), and relevant environmental data (such as temperature and humidity, transportation conditions, etc.);

[0106] A set formation sub-module, responsible for sorting the transfer locations in chronological order after obtaining the historical transfer record to form a transfer location set. The set records the transfer trajectory of the agricultural product and also includes multi-dimensional feature information of each location;

[0107] An information supplement sub-module, responsible for verifying and supplementing the transfer location set. If the environmental data of a certain transfer location is missing, it is supplemented through correlation analysis.

[0108] The working principle and beneficial effects of the above technical solution are as follows: The record acquisition sub-module in this embodiment calls the historical transfer record of agricultural products from the transfer path database according to the RFID tag number of the agricultural products. Each transfer location is attached with a timestamp, an operation type (such as warehousing, outbound, transportation, etc.), and relevant environmental data (such as temperature and humidity, transportation conditions, etc.); after the historical transfer record is obtained, the set formation sub-module sorts the transfer locations in chronological order to form a transfer location set, which records the transfer trajectory of the agricultural products and also includes the multi-dimensional feature information of each location; the information supplement sub-module checks and supplements the transfer location set. If the environmental data of a certain transfer location is missing, it is supplemented through correlation analysis. The data retrieval method of the record acquisition sub-module in the above solution is efficient and accurate, and can reflect the transfer status of agricultural products in real time. Significance: Through the record acquisition sub-module, the transfer process of agricultural products is completely recorded, providing basic data for analysis and decision-making; it not only helps to improve the transparency of the supply chain, but also can quickly locate the responsible party when problems occur, ensuring the quality and safety of agricultural products. The set formation sub-module not only records the transfer trajectory of agricultural products, but also includes the multi-dimensional feature information of each location (such as geographical location, operator, environmental conditions, etc.). Significance: Through the set formation sub-module, the transfer trajectory of agricultural products is clearly presented, forming a complete "transfer map"; the structured data form is convenient for subsequent analysis and visual display, helping to better understand the transfer process of agricultural products and optimize supply chain management. The information supplement sub-module is supplemented through correlation analysis (such as inference based on historical data or similar scenarios) to ensure the integrity and accuracy of the data. Significance: The information supplement sub-module solves the problem of missing data, ensuring the integrity and reliability of the transfer path; it is crucial for ensuring the accuracy of agricultural product quality traceability. Especially in a complex supply chain environment, the integrity of data directly affects the scientificity and effectiveness of decision-making.

[0109] In summary, through the complete transfer path record in this embodiment, the transfer process of agricultural products can be clearly understood, enhancing the transparency of the supply chain; through the recording and supplementation of environmental data, enterprises can monitor the storage and transportation conditions of agricultural products in real time to ensure their quality and safety; through the analysis of transfer data, enterprises can discover bottlenecks and problems in the supply chain, optimize resource allocation, and improve operational efficiency; the transparent and traceable transfer path can enhance consumers' trust in the product and improve the brand image.

[0110] Embodiment 7: As Figure 7 shown, on the basis of Embodiment 5, the model construction module provided by the embodiment of the present invention includes:

[0111] The first dynamic adjustment sub-module is responsible for collecting the output data of the production base in real time. When a decrease in output is detected, it automatically updates the production capacity characteristics of the node. The updated node characteristics are propagated through the graph structure to other related nodes and edges, analyzes the impact of the node characteristic changes on the entire graph structure, and provides decision support;

[0112] The second dynamic adjustment sub-module is responsible for collecting the status data of the transportation route in real time. When a transportation route interruption is detected, it automatically updates the transportation time and cost characteristics of the edge. The updated edge characteristics are propagated through the graph structure to other related nodes and edges, analyzes the impact of the edge characteristic changes on the entire graph structure, and provides decision support;

[0113] The real-time reconstruction sub-module is responsible for integrating real-time data from different data sources, including changes in node characteristics and edge characteristics. According to the preprocessed data, it updates the graph structure in real time, performs path optimization, and finds the optimal agricultural product transfer path.

[0114] Among them, the first dynamic adjustment sub-module represents the update and propagation of node production capacity characteristics. The node production capacity characteristic update formula:

[0115]

[0116] In the formula, represents the production capacity characteristic of node i after update; ′ The updated production capacity characteristic; represents the production capacity characteristic of node i before update; ΔP ′ The production capacity characteristic before update; i′ represents the output decrease of node i'; represents the maximum production capacity of node i'; α represents the propagation coefficient, which controls the influence of adjacent nodes on the current node; w i′j′ represents the weight between node i' and node j'; N(i') represents the set of neighbor nodes of node i';

[0117] The graph structure propagation formula:

[0118]

[0119] In the formula, ΔG represents the overall change of the graph structure, n represents the total number of nodes in the graph, w i′j′ represents the weight between node i' and node j';

[0120] The second dynamic adjustment sub-module represents the update and propagation of edge transportation characteristics. The edge transportation characteristic update formula:

[0121]

[0122] In the formula, represents the updated transportation time characteristic of edge i'j'; Denote the transportation time feature ΔD before the update of edge i′j′ i′j′ Denote the transportation interruption time of edge i′j′; Denote the maximum allowable interruption time of edge i′j′; β represents the adjustment coefficient, controlling the impact of interruption on transportation time; Denote edge i ′ j ′ 's current transportation cost; Denote edge i ′ j ′ 's maximum transportation cost;

[0123] Graph structure propagation formula:

[0124]

[0125] In the formula, ΔG′ represents the overall change of the graph structure; w i′j′ Denote the weight between node i′ and node j′;

[0126] The real-time reconstruction sub-module represents the graph structure update and path optimization. The graph structure update formula:

[0127]

[0128] In the formula, G new Denote the updated graph structure; G old Denote the graph structure before the update; γ represents the graph structure update coefficient; ΔC i′ Denote the change in production capacity of node i′; ΔT i′j′ Denote the change in transportation time of edge i′j′;

[0129] Path optimization formula:

[0130]

[0131] In the formula, P opt Denote the optimal path; P represents the set of all possible paths; C i′ Denote the production cost of node i′ in the path; T j′ Denote the transportation time of edge j′ in the path; w l Denote the weight of edge l in the path; w q Denote the weight of edge q in the path. The above formulas realize the dynamic update of node and edge features, the propagation and reconstruction of the graph structure, and the optimization of the optimal path.

[0132] The working principle and beneficial effects of the above technical solution are as follows: The first dynamic adjustment sub-module of this embodiment collects the output data of the production base in real time. When a decrease in output is detected, it automatically updates the production capacity characteristics of the nodes. The updated node characteristics are propagated through the graph structure to other related nodes and edges, analyzes the impact of the node characteristic changes on the entire graph structure, and provides decision-making support. The second dynamic adjustment sub-module collects the status data of the transportation routes in real time. When a transportation route interruption is detected, it automatically updates the transportation time and cost characteristics of the edge. The updated edge characteristics are propagated through the graph structure to other related nodes and edges, analyzes the impact of the edge characteristic changes on the entire graph structure, and provides decision-making support. The real-time reconstruction sub-module integrates the real-time data from different data sources, including the changes in node characteristics and edge characteristics. According to the preprocessed data, it updates the graph structure in real time, performs path optimization, and finds the optimal agricultural product circulation path. The first dynamic adjustment sub-module of the above solution collects the output data of the production base in real time, ensuring the accuracy and timeliness of the data source. It can quickly respond to the output changes of the production base, avoiding resource waste or supply chain interruption caused by information lag. By dynamically adjusting the node characteristics, it reasonably allocates production tasks, ensuring the efficient operation of the supply chain. It provides data support for managers, helping them make scientific and reasonable decisions and reducing operation risks. The second dynamic adjustment sub-module optimizes the logistics path by dynamically adjusting the characteristics of the transportation routes, reducing transportation time and costs. It can quickly respond to transportation interruptions, etc., ensuring the stability of the supply chain. By optimizing the transportation path, it reduces unnecessary logistics expenses and improves the overall economic benefits. The real-time reconstruction sub-module ensures that the system can dynamically reflect the actual state of agricultural product circulation by reconstructing the graph structure in real time, providing a basis for path optimization. It can quickly adapt to various changes in the supply chain (such as output fluctuations, transportation interruptions, etc.), enhancing the adaptability and flexibility of the system.

[0133] In summary, through dynamically adjusting node and edge characteristics and real-time reconstructing the graph structure, this embodiment optimizes the agricultural product circulation path and improves the overall efficiency of the supply chain. Through a data-driven dynamic adjustment mechanism, it realizes the intelligent management of the supply chain, reduces manual intervention, and lowers operation costs. It can quickly respond to various situations (such as output decrease, transportation interruption, etc.), enhancing the risk resistance ability of the supply chain. By optimizing resource allocation and logistics paths, it reduces resource waste and promotes the sustainable development of the supply chain. It can not only achieve the dynamic adjustment and optimization of the supply chain, but also provide strong decision-making support for managers, promoting the entire supply chain system to develop towards intelligence and high efficiency.

[0134] Embodiment 8: As Figure 8 shown, based on Embodiment 5, the recommendation generation module provided by the embodiment of the present invention includes:

[0135] The node feature extraction sub-module is responsible for mapping the initial features such as the geographical location, capacity, and historical transportation volume of each node into a higher-dimensional space; transforming the initial features such as the transportation time, cost, and environmental conditions of each edge into a higher-order representation; capturing the patterns and relationships of the features of nodes and edges through the non-linear transformation of a multi-layer neural network;

[0136] The message passing mechanism sub-module is responsible for each node generating messages based on its own features and the features of its neighbor nodes. The node aggregates the received messages, usually using operations such as summation, mean, or maximum; updates the feature representation of the node according to the aggregated messages, and the updated features contain the information of the node itself and the information of its neighbor nodes; through multiple rounds of message passing, the features of the node gradually capture the global information of the entire graph;

[0137] The transportation path evaluation sub-module is responsible for calculating the total time of the path through the features of the edges (such as transportation time) and the features of the nodes (such as transfer time); calculating the total cost of the path through the features of the edges (such as transportation cost) and the features of the nodes (such as warehousing cost); evaluating the environmental impact of the path through the features of the edges (such as weather, congestion) and the features of the nodes (such as environmental risk), inputting the feature vector of the path, and outputting a score value.

[0138] The working principle and beneficial effects of the above technical solution are as follows: The node feature extraction sub-module in this embodiment maps the initial features such as the geographical location, capacity, and historical transportation volume of each node to a higher-dimensional space; the initial features such as the transportation time, cost, and environmental conditions of each edge are transformed into high-order representations; through the non-linear transformation of the multi-layer neural network, the feature capture patterns and relationships of nodes and edges are obtained; in the message passing mechanism sub-module, each node generates messages based on its own features and the features of its neighbor nodes, and the node aggregates the received messages, usually using operations such as summation, mean, or maximum; according to the aggregated messages, the feature representation of the node is updated, and the updated features contain the information of the node itself and the information of its neighbor nodes; through multiple rounds of message passing, the features of the node gradually capture the global information of the entire graph; the transportation path evaluation sub-module calculates the total time of the path through the features of the edge (such as transportation time) and the features of the node (such as transfer time); calculates the total cost of the path through the features of the edge (such as transportation cost) and the features of the node (such as warehousing cost); evaluates the environmental impact of the path through the features of the edge (such as weather, congestion) and the features of the node (such as environmental risk), inputs the feature vector of the path, and outputs a score value. The feature mapping in the high-dimensional space of the node feature extraction sub-module of the above solution enables the machine learning model to more deeply understand the patterns and relationships in the data, thereby improving the prediction accuracy and generalization ability of the model. The message passing mechanism sub-module effectively simulates the information propagation process in the real world, enabling the model to not only understand local information but also grasp global information, which is particularly important for processing graph-structured data. The transportation path evaluation sub-module can provide a comprehensive evaluation index for decision-makers through a comprehensive scoring mechanism, helping to select the optimal transportation path to achieve maximum cost-effectiveness and minimum environmental impact.

[0139] In summary, this embodiment enables the entire system to not only capture local details but also grasp global information when dealing with complex transportation network problems, providing strong technical support for the optimization of transportation paths; it can significantly improve transportation efficiency and reduce costs.

[0140] Example 9: As Figure 9 shown, on the basis of Example 1, the information interaction feedback component provided by the embodiment of the present invention includes:

[0141] The RFID reading module is responsible for when consumers need to query the quality and safety information of agricultural products, reading the RFID tags on the agricultural products through the RFID reader. The RFID reader emits a radio frequency signal to activate the tag, and the RFID tag transmits the stored information back to the RFID reader;

[0142] The information query module is responsible for showing the information read, including the circulation path of agricultural products, environmental temperature and humidity records, pesticide use records, etc., to consumers;

[0143] The feedback interaction module is responsible for consumers to upload feedback information to the cloud platform through information interaction feedback.

[0144] The working principle and beneficial effects of the above technical solution are as follows: When consumers need to query the quality and safety information of agricultural products, the RFID reading module in this embodiment reads the RFID tag on the agricultural product through an RFID reader. The RFID reader emits a radio frequency signal to activate the tag, and the RFID tag transmits the stored information back to the RFID reader; the information read by the information query module includes the circulation path of the agricultural product, environmental temperature and humidity records, pesticide use records, etc., and is displayed to consumers; through information interaction feedback, consumers of the feedback interaction module upload the feedback information to the cloud platform. The RFID reading module of the above solution can conveniently obtain the traceability information of agricultural products, increase transparency, and enhance trust; for agricultural product enterprises, inventory and logistics can be managed more effectively through RFID technology, improving efficiency. The information query module enhances consumers' confidence in the safety of agricultural products because all key information is traceable and transparent; it helps consumers make more informed purchase decisions, improving consumers' satisfaction and loyalty. The feedback interaction module provides a direct channel for consumers to express opinions and feedback, enhancing consumers' sense of participation; for enterprises, they can timely understand product problems through consumers' feedback, quickly respond to market changes, and improve products and services.

[0145] In summary, the information interaction feedback component of this embodiment not only improves the consumer experience; enables consumers to purchase and consume agricultural products with more confidence, but also provides market information and consumer feedback for enterprises, helping to improve product quality and market competitiveness. The interactive information feedback system is a very valuable tool in modern agricultural product supply chain management.

[0146] Example 10: As Figure 10 shown, on the basis of Examples 1 - 9, the method for the whole - process traceability of agricultural products provided by the embodiment of the present invention based on the Internet of Things and RFID technology includes the following steps:

[0147] S100: Using RFID technology, key data including environmental temperature and humidity, soil nutrients, pesticide use records, and transportation trajectories are automatically collected in various links such as the production, processing, transportation, storage, and sales of agricultural products; the key data is uploaded to the cloud platform in real - time through Internet of Things devices;

[0148] S200: Through Internet of Things technology, the transportation and storage processes of agricultural products are monitored in real - time. Combining with RFID tags, the circulation path of agricultural products is traced; a graph neural network is used to model the circulation path of agricultural products as a graph structure, analyze the relationships between path nodes, and optimize the circulation path planning of agricultural products;

[0149] S300: Provide a convenient query entry, read the RFID tag through the RFID reader, and obtain the quality and safety information of agricultural products in real time.

[0150] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, first, the RFID technology is utilized to automatically collect key data including environmental temperature and humidity, soil nutrients, pesticide usage records, transportation trajectories, etc. in various links such as the production, processing, transportation, storage, and sales of agricultural products; the key data is uploaded to the cloud platform in real time through Internet of Things devices; secondly, the transportation and storage processes of agricultural products are monitored in real time through Internet of Things technology, and combined with RFID tags, the circulation paths of agricultural products are traced; a graph neural network is used to model the circulation paths of agricultural products as a graph structure, analyze the relationships between path nodes, and optimize the circulation path planning of agricultural products; finally, a convenient query entrance is provided, and the RFID reader is used to read the RFID tag to obtain the quality and safety information of agricultural products in real time. The key data collected and uploaded in step S100 of the above solution is uploaded to the cloud platform in real time through Internet of Things devices to ensure the integrity, accuracy, and timeliness of the data; the RFID tag, as a data carrier, can quickly identify and record information, avoiding errors caused by manual entry. Significance: Through real-time data collection and upload, producers and managers can comprehensively master the growth environment, processing process, and logistics status of agricultural products, ensuring standardized operations in each link; at the same time, the transparency of the data provides a reliable basis for regulatory authorities, helping to improve the quality and safety level of agricultural products and enhancing consumers' trust. In step S200, real-time tracking and path optimization monitor the transportation and storage processes of agricultural products in real time through Internet of Things technology, and combine RFID tags to track the circulation paths of agricultural products. A graph neural network (GNN) is used to model the circulation path as a graph structure, analyze the relationships between path nodes, and optimize the circulation path planning of agricultural products; it can dynamically adjust the transportation plan, reduce transportation time and costs, and at the same time avoid losses of agricultural products caused by environmental changes. Significance: Real-time tracking and path optimization not only improve logistics efficiency but also reduce the loss rate of agricultural products, ensuring the quality of agricultural products during transportation and storage; through path optimization, carbon emissions can be reduced, promoting the development of green logistics. In addition, the optimized path planning also saves costs for enterprises and improves overall operational efficiency. In step S300, information interaction and feedback provide a convenient query entrance for consumers. Consumers can obtain the quality and safety information of agricultural products (such as place of origin, production date, inspection report, etc.) in real time through RFID reading devices or the cloud platform; a transparent information display method. Significance: Information interaction and feedback shorten the distance between consumers and producers, enhancing consumers' trust in agricultural products. At the same time, the transparent information display also helps to improve the brand image and promote the market competitiveness of high-quality agricultural products; consumers can select safer and healthier agricultural products by querying information, thus promoting the healthy development of the entire industry. In addition, the feedback data from consumers also provides a direction for producers to improve, promoting the continuous improvement of the quality of agricultural products.

[0151] In summary, through the collaborative work of three steps: data collection and upload, real-time tracking and route optimization, and information interaction and feedback, this embodiment realizes the transparent management of the entire process of agricultural products from production to consumption. It not only improves the quality and safety level of agricultural products, but also optimizes the logistics efficiency, reduces the loss rate, and enhances consumers' trust.

[0152] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of equivalent technologies of the present invention, the present invention also intends to include these changes and modifications.

Claims

1. A full-process traceability system for agricultural products based on the Internet of Things and RFID technology, characterized in that: Include: The data collection and upload component is responsible for automatically collecting key data at all stages of agricultural products using RFID technology; key data is uploaded to the cloud platform in real time through IoT devices; Real-time tracking and monitoring components are responsible for real-time monitoring of the transportation and storage process of agricultural products through the Internet of Things technology, and combining RFID tags to track the circulation path of agricultural products; The graph neural network is used to model the circulation path of agricultural products as a graph structure, analyze the relationship between path nodes, and optimize the circulation path planning of agricultural products; The information interaction feedback component is responsible for providing consumers with a convenient query portal, reading RFID tags through RFID readers, and obtaining real-time quality and safety information of agricultural products.

2. The agricultural product traceability system based on the Internet of Things and RFID technology as claimed in claim 1, characterized in that: Data collection and upload components, including: The dynamic capture module is responsible for dynamically capturing multi-dimensional key data such as environmental temperature and humidity, soil nutrients, pesticide use records, and transportation trajectories by deploying an adaptive sensing network; and realizing correlation analysis between multi-dimensional key data by introducing the quantum entanglement effect; The tag binding module is responsible for converting key data into a standardized format, using a coding mapping mechanism to generate dynamic codes for key data, and binding them to RFID tags; The cloud synchronization module is responsible for uploading the key data bound to the RFID tag to the cloud platform in real time; During the transportation process, the RFID tag communicates with the on-board IoT device in real time, encrypts the transportation trajectory data and uploads it to the cloud platform.

3. The agricultural product traceability system based on the Internet of Things and RFID technology as claimed in claim 2, characterized in that: Dynamic capture module, including: The network formation submodule is responsible for constructing a quantum state preparation system at the central node of the adaptive sensing network to prepare a multi-particle entangled state with high coherence. The multi-particle entangled state is distributed to each sensing node through quantum channels to form a quantum state distribution network. The data association submodule is responsible for converging the quantum state carrying environmental information to the central node through the quantum channel, realizing the natural association of multi-dimensional key data in the quantum superposition state, so that non-classical associations are generated between key data of different dimensions, and extracting the association network between multi-dimensional key data; The quantum measurement submodule is responsible for the central node to measure the quantum superposition state through quantum measurement. The results are presented in the form of probability distribution, which contains the correlation information between multi-dimensional key data.

4. The agricultural product traceability system based on the Internet of Things and RFID technology as claimed in claim 2, characterized in that: Tag binding module, including: The data conversion submodule is responsible for extracting time series features from multi-dimensional key data, including the change trend of key data in a single dimension and the coordinated change pattern between multi-dimensional key data; converting the correlation and time series features of multi-dimensional key data into dynamic coding; The encoding conversion submodule is responsible for converting the time series features in the dynamic encoding into a signal sequence of neuron pulses, and the correlation of multi-dimensional key data is converted into a synergistic pattern between signals; The feature embedding submodule is responsible for converting the time series features in the dynamic code into the timestamp information in the RFID tag after the signal modulation is completed, and the correlation of the multi-dimensional key data is converted into the correlation field in the tag.

5. The agricultural product traceability system based on the Internet of Things and RFID technology as claimed in claim 1, characterized in that: Real-time tracking and monitoring components, including: The path confirmation module is responsible for using RFID reading equipment to scan agricultural products entering the circulation location, obtain the attribute data of agricultural products, call the circulation locations that the agricultural products have passed through from the circulation path database, and obtain the circulation location set; and determine the circulation path of agricultural products in combination with the starting circulation location and the ending circulation location of agricultural products; The model building module is responsible for abstracting the circulation path of agricultural products into a graph structure, so that the circulation network of agricultural products is converted into a dynamic graph structure; The suggestion generation module is responsible for inputting the graph structure data of the flow path into the graph structure model; according to the scoring results, the flow path is selected and the flow path suggestions are generated.

6. The agricultural product traceability system based on the Internet of Things and RFID technology as claimed in claim 5, characterized in that: Path confirmation module, including: The record acquisition submodule is responsible for calling the historical circulation records of agricultural products from the circulation path database according to the RFID tag number of the agricultural products. Each circulation location is accompanied by a timestamp, operation type, and environmental data. The collection formation submodule is responsible for sorting the circulation locations in chronological order after obtaining the historical circulation records to form a circulation location collection, which records the circulation trajectory of agricultural products and also contains the multi-dimensional feature information of each location; The information supplement submodule is responsible for verifying and supplementing the set of transfer locations. If the environmental data of a certain transfer location is missing, it will be supplemented through association analysis.

7. The agricultural product traceability system based on the Internet of Things and RFID technology as claimed in claim 5, characterized in that: It is recommended to generate a module legal person input graph structure model, including node features, edge features and historical flow data.

8. The agricultural product traceability system based on the Internet of Things and RFID technology as claimed in claim 5, characterized in that: It is recommended to generate modules, including: The node feature extraction submodule is responsible for mapping the initial features of each node’s geographic location, capacity, and historical transportation volume into a higher-dimensional space; the initial features of each edge’s transportation time, cost, and environmental conditions are converted into high-order representations; and the features of nodes and edges capture patterns and relationships through nonlinear transformations of multi-layer neural networks; The message passing mechanism submodule is responsible for each node to generate messages based on its own characteristics and the characteristics of neighboring nodes. The node aggregates the received messages and updates the feature representation of the node based on the aggregated messages. The updated features contain the information of the node itself and the information of neighboring nodes. Through multiple rounds of message passing, the characteristics of the node gradually capture the global information of the entire graph. The transport path scoring submodule is responsible for calculating the total time of the path through the characteristics of the edges and nodes; calculating the total cost of the path through the characteristics of the edges and nodes; and evaluating the environmental impact of the path through the characteristics of the edges and nodes. The feature vector of the path is input and the output is the scoring value.

9. The agricultural product traceability system based on the Internet of Things and RFID technology as claimed in claim 1, characterized in that: Information interaction feedback components, including: The RFID reading module is responsible for reading the RFID tag on the agricultural product through the RFID reader when consumers need to inquire about the quality and safety information of the agricultural product. The RFID reader sends a radio frequency signal to activate the tag, and the RFID tag transmits the stored information back to the RFID reader; The information query module is responsible for reading information including the circulation path of agricultural products, environmental temperature and humidity records, and pesticide use records, and displaying them to consumers; The feedback interaction module is responsible for consumers’ feedback through information interaction and uploading the feedback information to the cloud platform.

10. A method for tracing the source of agricultural products based on the Internet of Things and RFID technology, characterized in that: The following steps are involved: Using RFID technology, key data is automatically collected at all stages of agricultural products; key data is uploaded to the cloud platform in real time through IoT devices; Use IoT technology to monitor the transportation and storage process of agricultural products in real time, and combine RFID tags to track the circulation path of agricultural products; The graph neural network is used to model the circulation path of agricultural products as a graph structure, analyze the relationship between path nodes, and optimize the circulation path planning of agricultural products; Provide a convenient query portal, read RFID tags through RFID readers, and obtain quality and safety information of agricultural products in real time.

Images