Agricultural product production base information dynamic monitoring and analysis system

Abstract

The invention relates to the technical field of agricultural product production management, and discloses an agricultural product production base information dynamic monitoring and analysis system. The system comprises a basic data acquisition module for acquiring base and land parcel information and coding and storing the base and land parcel information; the production process dynamic monitoring module is used for collecting and fusing production activity data according to product forms; the environment data integration module is used for collecting, processing and analyzing environment parameters through an Internet of Things sensor network; the detection data integration module is used for detecting product quality data by using multi-mode equipment, screening abnormal values and storing the abnormal values in a block chain; and the traceability code generation module is used for generating batch traceability codes according to the multi-module data so as to realize whole-process data association and consumer query. The problems of disordered information management, incomplete production monitoring, lagged environment monitoring, lack of association of quality detection, difficulty in tracing and the like in a traditional management mode are solved, the management level of an agricultural product production base is improved, the quality safety of agricultural products is guaranteed, the credibility of consumers is enhanced, and agricultural modernization development is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural product production management, and particularly to a dynamic monitoring and analysis system for agricultural product production base information. Background Art

[0002] In the current era of accelerating agricultural modernization, the safe production and quality assurance of agricultural products have become increasingly important. However, the traditional management mode of agricultural product production bases faces many difficulties.

[0003] From the perspective of basic information management, many agricultural product production bases lack a complete and unified basic information management system. The recording methods of information such as the name, address, product type, and output of the base are diverse and not standardized, often resulting in information errors, omissions, and untimely updates. The management of plot information is even more chaotic. The boundaries of plots are poorly defined, the area calculation is inaccurate, and it is impossible to accurately associate plot codes with base codes. This causes great difficulties in resource allocation, production planning, and agricultural product traceability, and cannot provide a reliable basis for subsequent scientific management. For example, when it is necessary to count the output of a certain variety of agricultural products, due to the inaccuracy and incompleteness of the information, it is difficult to quickly and accurately obtain the results, affecting the scientific nature of production decisions.

[0004] In terms of production process management, the traditional method is difficult to comprehensively and real-time monitor and record production activities. During the planting process, agricultural activities such as fertilization, pesticide application, and weeding lack accurate records, and the types and dosages of inputs are not clear. This not only affects the output and quality of agricultural products but also may cause environmental pollution due to excessive use of pesticides, fertilizers, etc. In the breeding field, key information such as feed batches, vaccine types, and the frequency of shed disinfection is not fully recorded, making it difficult to ensure the healthy growth of animals and increasing the risk of disease transmission. In aquaculture, the records of water area disinfection time and feed feeding amount are not standardized, and refined management cannot be achieved, restricting the improvement of the quality and output of aquatic products.

[0005] There are also problems in the environmental monitoring link. In the past, the monitoring of the base environment mainly relied on manual data collection at regular intervals. This method has low efficiency, poor data accuracy, and cannot reflect environmental changes in real time. Environmental parameters such as meteorological data, soil moisture, and biological indicators are crucial for the growth of agricultural products. However, due to backward monitoring means, it is impossible to timely grasp the trend of environmental changes and difficult to provide timely and effective guidance for production activities. For example, in the face of extreme weather, it is impossible to take preventive measures in advance, resulting in crop losses due to disasters.

[0006] In terms of product quality inspection, traditional inspection methods often have limitations. The inspection equipment and methods are single, making it difficult to comprehensively detect various indicators such as agricultural residues, drug residues, and heavy metals. Moreover, the accuracy and reliability of inspection results need to be improved. At the same time, the inspection data lacks effective integration and management, and cannot be correlated and analyzed with data such as the production process and base environment, making it difficult to achieve full-process traceability of agricultural product quality. This has led to a lack of trust among consumers in the quality and safety of agricultural products, restricting the improvement of the market competitiveness of agricultural products.

[0007] With the continuous increase in consumers' attention to the quality and safety of agricultural products, and the increasingly strict requirements of the market for the standardization and traceability of agricultural products, the traditional management mode of agricultural product production bases can no longer meet the needs of modern agricultural development. It is urgent to establish a set of efficient, accurate, and comprehensive dynamic monitoring and analysis system for agricultural product production base information to solve many problems in the traditional management mode and promote the development of agricultural production towards intelligence, science, and safety. Summary of the Invention

[0008] The purpose of the present invention is to provide a dynamic monitoring and analysis system for agricultural product production base information to solve the problems raised in the above background technology.

[0009] To achieve the above purpose, the present invention provides the following technical solutions: A dynamic monitoring and analysis system for agricultural product production base information, the system includes: Basic data collection module: Used to collect base basic information and plot information, generate a unique base code and associate it with the plot code to obtain basic data; Production process dynamic monitoring module: Collect production activity data according to product form classification, including planting farming records, breeding feeding records, and aquaculture management records; Environmental data integration module: Real-time collect base environmental parameters through the Internet of Things sensor network, including meteorological data, soil moisture, and biological indicators; Inspection data integration module: Use multi-mode inspection equipment to obtain product quality data, integrate the inspection results of agricultural residues, drug residues, and heavy metals, and generate inspection data; Traceability code generation module: Generate batch traceability codes based on basic data, production activity data, base environmental parameters, and inspection data to achieve full-process data association and consumer query interface.

[0010] Preferably, the basic data collection module includes: The base basic information includes name, address, product type, and output. The plot boundary is outlined through the Tianditu tool and the area is calculated; The plot code is associated with the base code, and the plot coordinates are encoded using the geographical hash algorithm; Construct a distributed database to store base and plot information.

[0011] Preferably, the production process dynamic monitoring module includes: For planted products, collect records of fertilization, pesticide application, and weeding, and associate the types and dosages of inputs; for farmed products, collect feed batches, vaccine types, and the frequency of shed disinfection; For aquatic products, collect the time of water area disinfection and the feed feeding amount, and mark the operation nodes with timestamps; Construct a multi-modal data fusion model to integrate text records, image data, and sensor readings into a unified time-series log.

[0012] Preferably, the environmental data integration module includes: The Internet of Things sensor network includes a weather station, a soil moisture probe, and a pest monitoring camera. Perform spatio-temporal interpolation processing on meteorological data and soil data to generate a base environment heat map; identify pest image features through a convolutional neural network and output a pest distribution probability map.

[0013] Preferably, the detection data integration module includes: The rapid detection equipment uses the enzyme inhibition rate method to detect agricultural residues, the colloidal gold method to detect drug residues, and the spectral analysis method to detect heavy metals; Construct a detection result outlier screening model to identify out-of-specification data based on the sliding window statistical method; Bind the detection data to the production batch and store it in the blockchain network to ensure immutability.

[0014] Preferably, the geographic hashing algorithm includes: Convert the plot coordinates into longitude and latitude grids, and generate a unique string through multi-level fractal coding; overlay a spatial index tree on the plot boundary to support fast association query and dynamic area calibration.

[0015] Preferably, the multi-modal data fusion model includes: Extract keywords from text records to generate a structured operation event table, use object detection algorithms for image data to identify farm tool types and material stocks, and bind sensor data to operation events through a time-series alignment mechanism.

[0016] Preferably, the spatio-temporal interpolation processing includes: Map discrete sensor data to a three-dimensional grid space and use the Kriging interpolation algorithm to fill in missing values; Overlay meteorological prediction data on the environment heat map to generate the environmental risk warning level for the next 12 hours.

[0017] Preferably, the blockchain network adopts a sharded storage architecture, including: Shard the detection data according to the production batch, and each shard contains a hash pointer and a timestamp; Verify the data upload permission through a smart contract and automatically trigger an alarm for abnormal data.

[0018] Preferably, the generation of the batch traceability code includes: Concatenate the base code, plot code, production batch number, and the hash value of the inspection report into an original string; Use the national cryptographic algorithm to encrypt the string to generate a unique QR code and barcode; After the consumer scans the traceability code, query and decrypt the associated data through the distributed nodes.

[0019] Compared with the prior art, the beneficial effects of the present invention are: At the basic information management level, the system, through the basic data collection module, uses the Tianditu tool to accurately outline the plot boundaries and calculate the area. At the same time, it uses the geohash algorithm to encode the plot coordinates, associates them with the unique base code, and constructs a distributed database to store relevant information. This measure realizes the standardized and precise management of base and plot information. On the one hand, it enables the base managers to quickly and accurately obtain the detailed information of each piece of land, providing strong support for the reasonable planning and utilization of land resources. For example, according to the accurate plot area and soil conditions, accurately arrange the variety and quantity of crops to be planted, avoiding resource waste. On the other hand, during the traceability of agricultural products, it can quickly locate the source plot of the product, improving the traceability efficiency and accuracy, and protecting the consumers' right to know.

[0020] The dynamic monitoring module of the production process is of great significance. For planting, breeding, and aquaculture production activities, this module comprehensively collects various key data, marks the operation nodes with timestamps, and integrates different types of data into a unified time-series log through a multi-modal data fusion model. This helps the managers to have a real-time grasp of the entire production process and promptly discover problems in the production process. For example, during the planting process, if it is found that the fertilization amount is abnormal or the pesticide application time does not meet the specifications, corrective measures can be immediately taken to ensure the quality and safety of agricultural products. At the same time, the complete production records also provide strong evidence for the quality certification and market promotion of agricultural products, enhancing the market competitiveness of the products.

[0021] The environmental data integration module uses the Internet of Things sensor network to collect environmental parameters such as meteorological data, soil moisture, and biological indicators in real time. Through spatio-temporal interpolation processing, a base environmental heat map is generated, and by overlaying meteorological prediction data, an environmental risk warning level for the next 12 hours can also be generated; using a convolutional neural network to identify the characteristics of pest images and output a pest distribution probability map. This enables the base managers to know in advance the trend of environmental changes, formulate countermeasures in advance for bad weather or pest outbreaks, reduce the damage of natural disasters and pests to agricultural products, reduce production risks, and ensure the stable yield of agricultural products.

[0022] The detection data integration module adopts a variety of advanced detection methods to comprehensively detect the pesticide residues, drug residues and heavy metal indicators of agricultural products. The constructed outlier screening model for detection results can accurately identify the exceeded-standard data, bind the detection data with the production batches and store them in the blockchain network to ensure the immutability of the data. This not only guarantees the authenticity and reliability of the detection data, but also realizes the whole-process quality traceability from the production source to the market sales by associating the detection data with the data of other links. Once the quality problems of agricultural products are found, the problem links can be quickly located, and measures such as recall and rectification can be taken to effectively protect the rights and interests of consumers and the market order.

[0023] The traceability code generation module generates batch traceability codes based on multi-link data. Consumers can scan the traceability codes to query the whole-process information of the products. This enhances consumers' trust in the quality and safety of agricultural products and promotes the market circulation of agricultural products. For the production bases, it can improve the brand image, expand the market share, realize high quality and high price, and promote the sustainable development of agricultural product production bases. To sum up, the system comprehensively improves the management level and production efficiency of agricultural product production bases, and is of great significance for ensuring the quality and safety of agricultural products and promoting the development of agricultural modernization. Brief Description of the Drawings

[0024] Figure 1 is the working principle diagram of the information dynamic monitoring and analysis system for agricultural product production bases described in the present invention; Figure 2 is the working flow chart of the basic data collection module; Figure 3 is the working flow chart of the production process dynamic monitoring module; Figure 4 is the working flow chart of the geographical hash algorithm. Detailed Embodiments

[0025] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0026] Please refer to Figures 1-4 , the present invention provides an information dynamic monitoring and analysis system for agricultural product production bases, and its detailed embodiments are described below.

[0027] Basic data collection module: This module is responsible for collecting basic base information and plot information. The basic base information covers key contents such as the base name, address, product type and output. The boundaries of the plot are outlined through the Tiandi Map tool, and the plot area is accurately calculated. In order to achieve effective management and association of data, a unique base code will be generated and the plot code will be associated with it. The plot code uses the geo-hash algorithm to encode the plot coordinates, and then a distributed database is built to store the base and plot information, thereby forming the basic data support for the operation of the entire system.

[0028] Dynamic monitoring module for production process: This module collects production activity data according to product form classification. For planted products, records of fertilization, pesticide application and weeding are collected, and the input types and amounts are associated; for aquaculture products, feed batches, vaccine types and pen disinfection frequencies are collected; for aquatic products, water disinfection times and feed feeding amounts are collected. During data recording, operation nodes are marked with timestamps. At the same time, a multimodal data fusion model is constructed to integrate text records, image data and sensor readings into a unified time series log to more comprehensively and accurately reflect the production process.

[0029] Environmental data integration module: The base environmental parameters are collected in real time with the help of the IoT sensor network, which includes weather stations, soil moisture probes, pest monitoring cameras and other equipment. The collected environmental parameters include meteorological data, soil moisture and biological indicators. The collected meteorological data and soil data are processed in time and space to generate the base environmental thermal map. The convolutional neural network is used to identify the characteristics of pest images and output the pest distribution probability map, which provides a strong basis for base environmental monitoring and pest control.

[0030] Test data integration module: Use multi-mode testing equipment to obtain product quality data. For example, rapid testing equipment uses enzyme inhibition rate method to detect pesticide residues, colloidal gold method to detect drug residues, and spectral analysis method to detect heavy metals. Build a model for screening abnormal values ​​of test results, and identify excessive data based on sliding window statistics. Bind the test data to the production batch and store it in the blockchain network to ensure that the data cannot be tampered with and to ensure the authenticity and reliability of product quality data.

[0031] Traceability code generation module: Generate batch traceability codes based on basic data, production activity data, base environmental parameters and test data. The specific method is to splice the base code, plot code, production batch number and test report hash value into the original string, encrypt the string using the national secret algorithm, and generate a unique QR code and barcode. After the consumer scans the traceability code, the associated data is queried and decrypted through the distributed nodes, realizing the full-process data association and consumer query interface, so that consumers can clearly understand the entire production process of agricultural products.

[0032] The following elaborates on the specific implementation manners of the present invention in more detail through 5 embodiments: Embodiment 1:

[0033] This embodiment details the specific implementation details of the basic data collection module. When collecting the basic information of the base, the staff accurately enter the name of the base, the detailed address, the types of products mainly produced, and the estimated or actual output data in sequence through the interactive interface of the system. For example, [specific base name] is located at [detailed address], mainly produces vegetable products, and the estimated annual output is [X] tons. Using the graphic drawing function of the Tianditu tool, the staff accurately outline along the actual boundary of the plot, and the built-in area calculation algorithm of the Tianditu tool will automatically calculate the plot area. Suppose the plot area is [Y] square meters.

[0034] In the link of generating the plot code, the geohash algorithm is used. The geohash algorithm first converts the plot coordinates into longitude and latitude grids. Its principle is to divide the earth's surface into grids of different precisions. Suppose the plot coordinates are (latitude, longitude), and the latitude range [-90, 90] and the longitude range [-180, 180] are divided according to certain rules, and each division is a fractal operation. Through multi-level fractal coding, a unique string is finally generated. For example, after [specific number of hierarchical divisions] times of fractal coding, the geohash code of the plot is [specific coding string].

[0035] To achieve fast association query and dynamic area calibration, a spatial index tree is overlaid on the plot boundary. The spatial index tree is a data structure that organizes the spatial information of the plot. For example, in a quadtree structure, the entire area is continuously divided into four sub-areas, and each sub-area contains the corresponding plot information. When querying a certain plot or performing area calibration, the target plot can be quickly located through the spatial index tree, greatly improving the efficiency of data query and processing.

[0036] When constructing a distributed database, a suitable distributed database management system is selected, such as [specific distributed database name]. The basic information of the base and the plot information are stored according to the table structure design of the database. Each base information corresponds to a record, including fields such as base code, name, address, etc.; each plot information also corresponds to a record, including fields such as plot code, associated base code, plot area, etc. In this way, the orderly storage and management of basic data are realized.

[0037] Embodiment 2:

[0038] This embodiment focuses on the collection of data related to planted products in the dynamic monitoring module of the production process and the specific implementation of the multi-modal data fusion model. For the data collection of planted products, taking vegetable planting as an example, in the fertilization link, the staff uses a fertilization device with a recording function, and the device automatically records the fertilization time, fertilization type (such as nitrogen fertilizer, phosphate fertilizer, etc.), and fertilization amount. Suppose at [specific fertilization time], [specific nitrogen fertilizer name] was used, and the fertilization amount was [Z] kilograms. When applying pesticides, the application time, pesticide name, application method (such as spraying, broadcasting, etc.), and application dosage are also recorded. For example, at [pesticide application time], [pesticide name] was used for spraying, and the dosage was [W] liters per mu. The weeding record includes the weeding time and the weeding method (manual weeding or mechanical weeding). Suppose mechanical weeding was used for operation at [weeding time].

[0039] In terms of the multi-modal data fusion model, keyword extraction is performed on the text records. For example, for the text of the fertilization record "[specific fertilization time] use [specific nitrogen fertilizer name] to fertilize [Z] kilograms", through the keyword extraction algorithm, keywords such as "fertilization time", "fertilization type", and "fertilization amount" are extracted to generate a structured operation event table. This table is indexed by time and stores the fertilization-related information in an orderly manner.

[0040] For image data, object detection algorithms are used to identify the types of farm tools and the inventory of materials. Suppose the camera installed in the planting area captures an image of the fertilization operation. Based on a deep learning model such as the YOLO (You Only Look Once) algorithm, the object detection algorithm identifies the farm tool in the image, determines that it is a fertilization device, and estimates the remaining inventory of the fertilizer through image analysis techniques.

[0041] In the processing of sensor data, the sensor data is bound to the operation events through a time series alignment mechanism. For example, the soil moisture sensor continuously collects soil moisture data. When the fertilization operation occurs, according to the time stamp, the time of the fertilization operation is associated with the data collected by the soil moisture sensor during this period to form a unified time series log for subsequent comprehensive analysis of the planting production process.

[0042] Embodiment 3:

[0043] This embodiment focuses on introducing the specific implementation process of data acquisition, spatio-temporal interpolation processing, and pest image recognition in the Internet of Things sensor network of the environmental data integration module. The Internet of Things sensor network is deployed at various key positions in the agricultural product production base. The weather station is installed in an open and well-ventilated area to collect meteorological data such as temperature T, humidity H, wind speed V, rainfall R, etc. The soil moisture probes are buried in the soil of different plots at a certain interval to collect soil moisture data in real time, expressed as soil water content S. The pest monitoring cameras are installed at an appropriate height above the crops to take pest images.

[0044] The collected meteorological data and soil data are discrete. In order to generate a more intuitive and comprehensive base environmental heat map, spatio-temporal interpolation processing is required. First, map the discrete sensor data to a three-dimensional grid space, and form a three-dimensional grid with spatial coordinates (x, y) and time t. The Kriging interpolation algorithm is used to fill in the missing values. The formula of the Kriging interpolation algorithm is: , where, is the variable value of the point to be estimated , is the variable value of the known sample point , n is the number of sample points, is the weight coefficient, which is calculated through the semi-variance function. In practical applications, according to the distribution of data points collected by the sensors, calculate the weight coefficients of each sample point, so as to accurately estimate the values of the missing data points.

[0045] When generating the environmental heat map, visualize the meteorological data (such as temperature, humidity, etc.) and soil data (such as soil water content) on the heat map according to the spatial position. At the same time, in order to give early warnings of environmental risks, meteorological prediction data is superimposed on the environmental heat map. The meteorological prediction data is provided by a professional meteorological prediction agency and obtained through a data interface. For example, obtain the temperature prediction value , humidity prediction value and other data for the next 12 hours. According to a certain risk assessment model, generate the environmental risk warning level for the next 12 hours. For example, when the temperature is too high and the humidity is low, it may increase the drought risk of crops, and the system will correspondingly increase the risk warning level to remind the staff to take corresponding measures.

[0046] For pest image recognition, a convolutional neural network (CNN) is utilized. The images captured by the pest monitoring cameras are input into the trained CNN model, which extracts and classifies the image features through multiple convolutional layers, pooling layers, and fully connected layers. For example, for the recognized pest images, the model outputs a pest distribution probability map, representing the likelihood of pest occurrence in different regions with different colors and probability values. Suppose the pest occurrence probability in a certain region is P, where the value range of P is [0, 1]. The larger the P value, the higher the likelihood of pest occurrence in that region. The staff can carry out targeted pest control work based on the pest distribution probability map.

[0047] Example 4:

[0048] This example elaborates in detail the working principle of the detection equipment, the outlier screening model, and the specific implementation method of blockchain storage in the detection data integration module. In terms of the detection equipment, the rapid detection equipment uses the enzyme inhibition rate method to detect pesticide residues. The principle of the enzyme inhibition rate method is to utilize the inhibitory effect of organophosphorus and carbamate pesticides on acetylcholinesterase and calculate the pesticide residue content by detecting the change in enzyme activity. Suppose during the detection process, the enzyme activity of the sample without added pesticide is , and the enzyme activity after adding the pesticide sample is A. Then the calculation formula for the enzyme inhibition rate is: , When the enzyme inhibition rate exceeds a certain threshold, it indicates that the pesticide residues in the agricultural products exceed the standard.

[0049] The colloidal gold method is used to detect drug residues. The colloidal gold method is an immunoassay technique based on the specific binding of antigens and antibodies. The sample containing the drug reacts with the antibody immobilized on the test card, and the drug residue content is judged by observing the color change on the test card. When using the spectral analysis method to detect heavy metals, the absorption or emission characteristics of different heavy metal elements under specific spectra are utilized, and the heavy metal content is determined by measuring the spectral intensity. Suppose the spectral intensity for detecting a certain heavy metal element is , and according to the pre-established standard curve, the content of this heavy metal in the agricultural products can be calculated .

[0050] An outlier screening model for detection results is constructed to identify the out-of-standard data based on the sliding window statistical method. The sliding window statistical method refers to setting a window with a fixed length on the time series data. Suppose the window length is m, and the statistical features of the data, such as the mean and the standard deviation , are calculated within the window. The calculation formulas are respectively: , , Among them, is the i-th data within the window. When a certain data point exceeds the range of the mean plus or minus a certain multiple of the standard deviation, such as or (k is an empirical constant, usually taken as 2 or 3), then it is determined that this data point is an outlier, that is, non-compliant data.

[0051] In terms of data storage, the detection data is bound to the production batch and stored in the blockchain network. The blockchain network adopts a sharded storage architecture, sharding the detection data according to the production batch. Each shard contains a hash pointer and a timestamp. The hash pointer is used to point to the previous shard of the data in this shard, forming the chain structure of the blockchain to ensure the traceability of the data. The timestamp records the time when the data is stored to ensure the chronological order of the data. The data upload permission is verified through a smart contract, and only authorized users can upload detection data. When abnormal data is detected, the smart contract automatically triggers an alarm for abnormal data to notify relevant staff to handle it in a timely manner to ensure the quality and safety of agricultural products.

[0052] Example 5:

[0053] This example focuses on the actual operation of the traceability code generation module, covering the generation and encryption of batch traceability codes and the specific process of consumers querying data.

[0054] In the stage of generating batch traceability codes, first, multi-source key information is integrated. The base code is the unique code that identifies the agricultural product production base, which contains information such as the basic attributes and geographical location of the base. Suppose the base code is "JD001", and this code is used in the entire system to accurately locate the base. The plot code corresponds to the specific planting or breeding plot and is generated through the geographical hash algorithm, which can accurately identify the spatial location of the plot. For example, the plot code is "DK123". The production batch number is the number used to divide the production process of agricultural products into batches, used to distinguish products produced at different times and under different conditions. Suppose a certain batch number is "20240901 - 01", representing the first batch of products produced on September 1, 2024. The hash value of the inspection report is a fixed-length string obtained by performing a hash operation on the product quality inspection report. It can uniquely determine the content of the inspection report and has the property of non-tampering. Suppose the hash value of the inspection report is "8f95a6d4...".

[0055] The above information is concatenated to form the original string, that is, the original string S = "JD001DK12320240901 -018f95a6d4...". This original string contains the key information of agricultural products from the place of origin to quality inspection, laying the foundation for subsequent traceability.

[0056] Next, the original string is encrypted. This system uses the national cryptographic algorithm for encryption to ensure the security and privacy of data. The SM4 block cipher algorithm in the national cryptographic algorithm plays a key role in this process. The SM4 algorithm is a symmetric encryption algorithm, and the same key is used for both encryption and decryption. Assuming the key is K, its length is usually 128 bits. During the encryption process, the original string S is divided according to the block length specified by the SM4 algorithm. Each group of data undergoes a series of complex operations under the action of the key K, including non-linear transformation, linear transformation and other steps, and finally the encrypted ciphertext is generated. After encryption, a unique QR code and barcode are generated. The QR code can store more information and has error correction capabilities, while the barcode is convenient for quick identification on traditional scanning devices. Using professional QR code and barcode generation tools, the encrypted ciphertext is converted into scannable graphic codes, which are the entrances for consumers to query agricultural product information.

[0057] When consumers scan the traceability code, the relevant information query process is immediately started. Consumers use the mobile phone scanning software to scan the QR code or barcode, and the scanning information will be sent to the distributed node network of the system. The distributed nodes are a network architecture composed of multiple servers, which work together to store and manage data. After receiving the query request, these nodes will search for the corresponding basic data, production activity data, base environment parameters and detection data in the blockchain network or other distributed storage systems according to the key identification information in the traceability code.

[0058] In the blockchain network, data is stored in the form of a distributed ledger. Each block contains data records within a certain time range and the hash value of the previous block, forming a chain structure. Nodes quickly locate the corresponding block in the blockchain through information such as the hash value and timestamp in the traceability code to obtain relevant data. For other distributed storage systems, technologies such as distributed file system (DFS) or distributed database may be used, and nodes accurately find the location where the data is stored according to the index information of the data.

[0059] After the data is found, a decryption operation is performed using the decryption algorithm corresponding to the encryption algorithm. Taking the SM4 algorithm as an example, the same key K is used to perform reverse operations on the ciphertext to restore the original string S. Then, the system will parse the original string and extract information such as the base code, plot code, production batch number and detection report hash value contained therein, and use this as an index to query detailed agricultural product information in the database.

[0060] Finally, present the queried information to consumers in an intuitive and understandable manner. For example, through a specially developed mobile application, display the origin information of agricultural products on the interface, including the base name and address; production activity information, such as fertilization and pesticide application records for planted products, feed feeding and vaccination records for farmed products; base environment information, such as meteorological data and soil moisture; and detection data, such as agricultural residue, drug residue and heavy metal detection results, etc. Consumers can comprehensively understand the entire production process of agricultural products through this interface, meet their right to know about food safety and quality, and enhance their trust in agricultural products.

[0061] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0062] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An information dynamic monitoring and analysis system for an agricultural product production base, characterized in that, include: Basic data collection module: used to collect basic base information and plot information, generate a unique base code and associate it with the plot code to obtain basic data; Dynamic monitoring module for production process: collects production activity data according to product form, including planting records, breeding and feeding records, and aquatic management records; Environmental data integration module: collects base environmental parameters in real time through the IoT sensor network, including meteorological data, soil moisture and biological indicators; Test data integration module: Use multi-mode testing equipment to obtain product quality data, integrate pesticide residues, drug residues and heavy metal test results, and generate test data; Traceability coding generation module: Generates batch traceability codes based on basic data, production activity data, base environmental parameters and test data to achieve full-process data association and consumer query interface.

2. The dynamic monitoring and analysis system for agricultural product production base information according to claim 1, characterized in that, The basic data acquisition module includes: The basic information of the base includes name, address, product type and output. The boundaries of the plot are outlined and the area is calculated through the Tiandi map tool; The plot code is associated with the base code, and the geo-hash algorithm is used to encode the plot coordinates; Build a distributed database to store base and plot information.

3. The dynamic monitoring and analysis system for agricultural product production base information according to claim 1, characterized in that, The production process dynamic monitoring module includes: For planting products, records of fertilization, pesticide application, and weeding are collected, and the types and amounts of inputs are associated; for breeding products, feed batches, vaccine types, and the frequency of pen disinfection are collected; Aquatic products collect water disinfection time and feed feeding amount, and mark the operation node with a timestamp; Build a multimodal data fusion model to integrate text records, image data, and sensor readings into a unified time series log.

4. The dynamic monitoring and analysis system for agricultural product production base information according to claim 1, characterized in that The environmental data integration module includes: an Internet of Things sensor network including a weather station, a soil moisture probe and a pest monitoring camera, which performs spatiotemporal interpolation processing on meteorological data and soil data to generate a base environmental thermal map; and identifies pest image features through a convolutional neural network to output a pest distribution probability map.

5. The dynamic monitoring and analysis system for agricultural product production base information according to claim 1, characterized in that The detection data integration module includes: Rapid testing equipment uses enzyme inhibition rate method to detect pesticide residues, colloidal gold method to detect drug residues, and spectral analysis method to detect heavy metals; Construct an outlier screening model for test results and identify data exceeding the standard based on sliding window statistics; Bind the test data to the production batch and store it in the blockchain network to ensure that it cannot be tampered with.

6. The dynamic monitoring and analysis system for agricultural product production base information according to claim 2, wherein, The geo-hash algorithm includes: converting the plot coordinates into longitude and latitude grids, generating a unique string through multi-level fractal coding; superimposing a spatial index tree on the plot boundary to support fast association query and dynamic area calibration.

7. The dynamic monitoring and analysis system for agricultural product production base information according to claim 3, wherein The multimodal data fusion model includes: extracting keywords from text records, generating a structured operation event table, using a target detection algorithm to identify the type of agricultural implements and material inventory on image data, and binding sensor data to operation events through a time alignment mechanism.

8. The dynamic monitoring and analysis system for agricultural product production base information according to claim 4, characterized in that, The spatiotemporal interpolation process comprises: Map the discrete sensor data to a three-dimensional grid space and use the Kriging interpolation algorithm to fill in the missing values; Meteorological forecast data is superimposed on the environmental heat map to generate an environmental risk warning level for the next 12 hours.

9. The dynamic monitoring and analysis system for agricultural product production base information according to claim 5, characterized in that, The blockchain network adopts a shard storage architecture, including: The detection data is sharded by production batches, and each shard contains a hash pointer and a timestamp; Verify the data upload permission through a smart contract and automatically trigger an alarm for abnormal data.

10. The dynamic monitoring and analysis system for agricultural product production base information according to claim 1, characterized in that, The generation of the batch traceability code includes: Concatenate the base code, plot code, production batch number, and the hash value of the inspection report into an original string; Use the national cryptographic algorithm to encrypt the string and generate a unique QR code and barcode; After the consumer scans the traceability code, query and decrypt the associated data through a distributed node.

Images