Product anti-counterfeiting traceability monitoring system and method based on the Internet of Things

Abstract

The embodiment of the present invention provides a product anti-counterfeiting traceability monitoring system and method based on the Internet of Things, belonging to the field of data traceability technology. The system includes an exception handling module that uses a platform layer to perform exception identification on first data to obtain first exception data; performs exception identification on second data to obtain second exception data, and determines a target quality type based on the first exception data and the second exception data; a false detection module that uses a platform layer to perform false detection on first information based on the first data to obtain a target detection result; a data association module that uses a platform layer to correct the first information based on the target quality type and the target detection result to obtain second information, and associates the first exception data and the second exception data based on the second information to obtain relevant traceability information; and a data monitoring module that uses an application layer to obtain a target query identifier corresponding to a target user, and obtains third information corresponding to the target query identifier and target traceability information in a database based on the target query identifier.

Description

Technical Field

[0001] The present invention relates to the field of data traceability technology, and in particular to a product anti-counterfeiting traceability monitoring system and method based on the Internet of Things. Background Art

[0002] In modern society, with the intensification of globalization and market competition, product quality and safety have become key concerns for consumers and businesses. However, existing product anti-counterfeiting technologies mostly rely on simple identification methods such as barcodes and QR codes. While easy to implement, these technologies are prone to duplication and tampering, and cannot effectively provide full product traceability information.

[0003] With the rapid development of technologies such as the Internet of Things (IoT), big data, and cloud computing, IoT-based intelligent anti-counterfeiting and traceability technologies have gradually become an important means of solving this problem. Through technologies such as RFID, sensors, and GPS, relevant data on products during production, transportation, and sales can be collected and monitored in real time, ensuring product authenticity and traceability. However, existing IoT-based anti-counterfeiting and traceability systems still have the following technical problems:

[0004] First, it is impossible to ensure the accuracy and completeness of the data collected during large-scale production and transportation; second, it is impossible to promptly identify and handle abnormal situations in the production and transportation processes in order to take effective countermeasures; third, it is impossible to prevent forged information and false detection to ensure the authenticity of product information; finally, it is impossible to effectively link and store data from different sources so that subsequent queries and traceability can provide a complete and reliable basis.

[0005] Therefore, there is an urgent need for a product anti-counterfeiting traceability monitoring system based on the Internet of Things, which can comprehensively improve the accuracy, real-time performance and security of traceability information and solve at least one of the above technical problems. Summary of the Invention

[0006] The main purpose of the embodiments of the present invention is to provide a product anti-counterfeiting and traceability monitoring system and method based on the Internet of Things, aiming to solve the problem in the related art that the anti-counterfeiting and traceability process cannot promptly identify and handle abnormal situations in the production and transportation processes, thereby resulting in inaccurate traceability results.

[0007] In a first aspect, an embodiment of the present invention provides a product anti-counterfeiting and traceability monitoring system based on the Internet of Things, comprising:

[0008] a data acquisition module, configured to determine first information according to a target identifier of a target object using a perception layer of the Internet of Things, and to collect first data of the target object during a production process and second data of the target object during a transportation process based on the perception layer;

[0009] an exception handling module, configured to use the platform layer of the Internet of Things to perform exception identification on the first data to obtain first exception data; perform exception identification on the second data to obtain second exception data, and determine a target quality type corresponding to the target object based on the first exception data and the second exception data;

[0010] a false detection module, configured to use the platform layer to perform false detection on the first information according to the first data to obtain a target detection result;

[0011] a data association module, configured to utilize the platform layer to modify the first information according to the target quality type and the target detection result to obtain second information, and to associate the first abnormal data with the second abnormal data according to the second information to obtain relevant traceability information corresponding to the second information;

[0012] A data storage module, configured to associate the target identifier, the second information, and the related traceability information using the platform layer and store the associations in a database;

[0013] The data monitoring module is used to obtain a target query identifier corresponding to a target user by using the application layer of the Internet of Things, and obtain third information and target traceability information corresponding to the target query identifier in the database according to the target query identifier.

[0014] In a second aspect, an embodiment of the present invention provides a product anti-counterfeiting traceability monitoring method based on the Internet of Things, comprising:

[0015] Determine first information according to a target identifier of a target object using a perception layer of the Internet of Things, and collect first data of the target object during a production process and second data of the target object during a transportation process according to the perception layer;

[0016] Using the platform layer of the Internet of Things to perform abnormality identification on the first data to obtain first abnormal data; performing abnormality identification on the second data to obtain second abnormal data, and determining the target quality type corresponding to the target object based on the first abnormal data and the second abnormal data;

[0017] Using the platform layer to perform false detection on the first information according to the first data to obtain a target detection result;

[0018] Using the platform layer to modify the first information according to the target quality type and the target detection result to obtain second information, and correlating the first abnormal data with the second abnormal data according to the second information to obtain relevant traceability information corresponding to the second information;

[0019] Utilizing the platform layer to associate the target identifier, the second information, and the relevant traceability information and store them in a database;

[0020] The target query identifier corresponding to the target user is obtained by utilizing the application layer of the Internet of Things, and the third information and target traceability information corresponding to the target query identifier are obtained in the database according to the target query identifier.

[0021] Embodiments of the present invention provide a product anti-counterfeiting and traceability monitoring system and method based on the Internet of Things. The system includes: a data acquisition module that utilizes the perception layer of the Internet of Things to determine first information based on a target object's target identifier, enabling precise focus on a specific target object. Simultaneously, first data from the production process and second data from the transportation process are collected separately, achieving data coverage of the target object's entire process, from production to transportation. This facilitates a comprehensive understanding of the target object's status at different stages, providing a rich and accurate data foundation for subsequent quality assessment, anomaly detection, and other tasks. Furthermore, an anomaly handling module identifies anomalies in the first and second data, enabling timely detection of anomalies that occur during production and transportation. By determining the target quality type corresponding to the target object, product quality can be effectively assessed and classified. Furthermore, a fraud detection module performs fraud detection on the first information based on the first data, effectively preventing data falsification. Obtaining target detection results ensures that subsequent analysis and processing based on this information is reliable. Furthermore, a data association module modifies the first information based on the target quality type and target detection results to obtain second information. The first and second anomaly data are then associated with the modified second information to form relevant traceability information, achieving effective data integration. This helps to establish a comprehensive and systematic information system, facilitating subsequent data analysis and traceability. The data storage module then associates the target identifier, the second information, and the relevant traceability information and stores them in the database, thus realizing long-term data preservation. Finally, the data monitoring module enables the target user to use the application layer of the Internet of Things to obtain the corresponding third information and target traceability information through the target query identifier, thereby enabling the target user to obtain accurate and true traceability information under the target query identifier, and also solves the problem in the related technology that the anti-counterfeiting traceability process cannot timely identify and handle abnormal situations in the production and transportation process, which leads to inaccurate traceability results. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 A schematic diagram of the module structure of a product anti-counterfeiting and traceability monitoring system based on the Internet of Things provided by an embodiment of the present invention;

[0024] Figure 2 A flowchart of a product anti-counterfeiting and traceability monitoring method based on the Internet of Things is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0026] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0027] It should be understood that the terms used in this specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0028] Embodiments of the present invention provide a product anti-counterfeiting and traceability monitoring system and method based on the Internet of Things (IoT). The IoT-based product anti-counterfeiting and traceability monitoring system can be applied to terminal devices, such as tablet computers, laptop computers, desktop computers, personal digital assistants, and wearable devices. The terminal device can also be a server or a server cluster.

[0029] The following embodiments of the present invention are described in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0030] Please refer to Figure 1 , Figure 1 A schematic diagram of the module structure of a product anti-counterfeiting and traceability monitoring system based on the Internet of Things provided by an embodiment of the present invention.

[0031] like Figure 1As shown, the product anti-counterfeiting and traceability monitoring system 100 based on the Internet of Things includes a data acquisition module 101, an exception handling module 102, a false detection module 103, a data association module 104, a data storage module 105, and a data monitoring module 106, wherein the data acquisition module 101 is used to use the perception layer of the Internet of Things to determine the first information according to the target identification of the target object, and collect the first data of the target object in the production process and the second data in the transportation process according to the perception layer; the exception handling module 102 is used to use the platform layer of the Internet of Things to perform anomaly identification on the first data to obtain first abnormal data; perform anomaly identification on the second data to obtain second abnormal data, and determine the target quality type corresponding to the target object according to the first abnormal data and the second abnormal data; the false detection module 103 , used to use the platform layer to perform false detection on the first information according to the first data to obtain a target detection result; a data association module 104, used to use the platform layer to correct the first information according to the target quality type and the target detection result to obtain second information, and associate the first abnormal data and the second abnormal data according to the second information to obtain relevant traceability information corresponding to the second information; a data storage module 105, used to use the platform layer to associate the target identifier, the second information and the relevant traceability information and store them in a database; a data monitoring module 106, used to use the application layer of the Internet of Things to obtain a target query identifier corresponding to the target user, and obtain third information and target traceability information corresponding to the target query identifier in the database according to the target query identifier.

[0032] Exemplarily, the target identifier is a unique identifier such as an RFID tag or QR code affixed to the target object when it is sold. Then, the data acquisition module 101 uses the perception layer of the Internet of Things to obtain the first information corresponding to the target object from the database based on the target identifier of the target object. The first information is the basic information corresponding to the target object, including but not limited to the production time, production address, target type, target quality level, etc. of the target object. That is, the first information is the basic information describing the target object.

[0033] Exemplarily, at the same time, the data acquisition module 101 uses an image sensor to collect first data of the target object in the production process according to the perception layer. The first data is the image data corresponding to the target object in the production process, and uses temperature and humidity sensors to collect the environmental parameters of the target object in the transportation process in real time to obtain the corresponding second data, that is, the second data is the environmental parameter information corresponding to the target object in the transportation process.

[0034] For example, a data access interface is established at the IoT platform layer to ensure that the first and second data are accurately and promptly transmitted to the exception handling module 102. The first data includes image data related to the operation, which contains rich operational information. The images in the first data are then preprocessed, including operations such as cropping, scaling, and normalization, to improve the quality of the image data. Features, such as color, texture, and shape, are then extracted from the preprocessed images. Finally, the extracted features are input into a trained machine learning model for classification to determine whether the image contains operational anomalies, thereby obtaining the corresponding first anomaly data. The second data primarily includes environmental parameter data, such as temperature, humidity, and air pressure. To identify data containing environmental parameter anomalies, a pre-established anomaly identification rule is used. The environmental parameter data in the second data is then compared with the anomaly identification rule. If any environmental parameter data does not conform to the rule, it is marked as an anomaly, thereby obtaining the corresponding second anomaly data.

[0035] For example, a large amount of historical data is collected, including first anomaly data and corresponding quality grade labels. This data is then preprocessed and feature extracted, and then fed into a model for training. During the training process, the model parameters are continuously adjusted so that the model can learn the relationship between the first anomaly data and the quality grade. The current first anomaly data is then fed into the trained quality grade prediction model for prediction, and a first quality type is determined based on the prediction results. For example, if the prediction results indicate a high quality grade for the target object, the first quality type can be defined as "high quality"; if the prediction results indicate a low quality grade, the first quality type can be defined as "defective," etc. Based on the obtained first quality type, the second anomaly data is used to perform quality adjustment to obtain a target quality type corresponding to the target object. The quality adjustment rules need to comprehensively consider the impact of the first quality type and the second anomaly data. For example, if the first quality type is "high quality," but the second anomaly data indicates a serious anomaly in environmental parameters, potentially impacting the quality of the target object, the target quality type can be appropriately downgraded. Based on the quality adjustment rules, the first quality type is adjusted based on the first quality type and the second anomaly data to determine the target quality type corresponding to the target object.

[0036] Exemplarily, the false detection module 103 uses the platform layer to perform attribute recognition on the first data to obtain target attribute information corresponding to the target object, and then compares the target attribute information with the first information, thereby performing false detection on the first information based on the comparison result to obtain a target detection result.

[0037] Exemplarily, the data association module 104 compares the target quality type with the quality type in the first information. When the level of the quality type in the first information is greater than the target quality type, the quality type in the first information is modified. At the same time, the information in the target detection result that is inconsistent with the first information is modified accordingly according to the target attribute information to obtain the second information. The second information is the more accurate basic information after the production data and transportation data are corrected. In addition, the first abnormal data and the second abnormal data in the process of determining the target quality type in the second information are associated to facilitate subsequent data traceability, and then the first abnormal information and the second abnormal information are determined as the relevant traceability information corresponding to the second information.

[0038] Exemplarily, the data storage module 105 uses the platform layer to associate the target identifier, the second information and the related traceability information and store them in the database.

[0039] Exemplarily, the data monitoring module 106 utilizes the application layer of the Internet of Things to receive the target query identifier corresponding to the target user, thereby obtaining the third information and target traceability information corresponding to the target query identifier after comparing the target query identifier with the target identifier in the database.

[0040] In some embodiments, the exception handling module includes: a data acquisition module for collecting normal image data corresponding to the target object during the production process using the platform layer, and obtaining an exception description text corresponding to the target object based on expert experience; an image generation module for performing an exception adjustment on the normal image data based on the exception description text using the platform layer to obtain abnormal image data corresponding to the target object; a model determination module for determining a target abnormality recognition model corresponding to the target object based on the normal image data and the abnormal image data using the platform layer; an abnormality recognition module for performing abnormality recognition on the first data based on the target abnormality recognition model using the platform layer to obtain first abnormal data; a data analysis module for obtaining normal sensor data corresponding to the target object during transportation using the platform layer, and performing data association analysis based on the normal sensor data and the second data to obtain second abnormal data; a damage determination module for obtaining frequency information and time information corresponding to the second abnormal data using the platform layer, and determining a target damage parameter corresponding to the target object during transportation based on the second abnormal data, the frequency information, and the time information; and a quality determination module for determining the target quality type corresponding to the target object based on the first abnormal data and the target damage parameter using the platform layer.

[0041] For example, the platform layer establishes stable connections with various image acquisition devices (such as industrial cameras and surveillance cameras) used in the production process. Through this data interface, normal image data of the target object during production is acquired periodically or in real time. Experts, drawing on their extensive experience and in-depth understanding of the target object's production process, can describe in detail any possible anomalies, such as surface defects and dimensional deviations, and organize these descriptions into standardized textual descriptions of the anomaly.

[0042] Exemplarily, the image generation module analyzes the changing patterns of image features corresponding to different abnormalities based on the anomaly description text. For example, if the anomaly description is "scratches on the product surface," a strategy is developed to simulate the scratch effect on a normal image, such as adding lines or changing local colors. The module then uses an image processing algorithm to process the normal image data according to the anomaly adjustment strategy to generate abnormal image data corresponding to the target object.

[0043] For example, the model determination module divides normal image data and abnormal image data into a training set and a test set in a certain ratio (e.g., 7:3). The training set is used to train the abnormality recognition model, and the test set is used to evaluate the model's performance, thereby utilizing machine learning or deep learning models, such as convolutional neural networks (CNNs). The model is trained using the training set, and its parameters are continuously adjusted to enable it to accurately distinguish between normal and abnormal images. The trained model is then evaluated using the test set, and metrics such as accuracy, recall, and F1 score are calculated. Based on the evaluation results, the model is optimized, such as by adjusting the model structure and adding training data, until satisfactory performance is achieved and the model is designated as the target abnormality recognition model.

[0044] Exemplarily, the anomaly recognition module inputs the first data into the target anomaly recognition model, and the model classifies the image based on the learned features and patterns to determine whether an anomaly exists, and marks the image data identified as abnormal as first anomaly data.

[0045] For example, the data analysis module establishes connections at the platform level with various sensors (such as temperature sensors, humidity sensors, and vibration sensors) during transportation, collecting real-time sensor data from the target object during transportation. Statistical analysis is performed on this normal sensor data to determine the normal range and fluctuation patterns of various parameters. Statistical analysis methods and machine learning algorithms are then used to compare and correlate the second data with the normal sensor data, detecting whether any data points in the second data deviate significantly from the normal range. These data points are marked as abnormal data, or second abnormal data.

[0046] For example, corresponding frequency and time information are extracted from the second anomaly data. Frequency information reflects the frequency of the anomaly, while time information records the specific time and duration of the anomaly. A damage assessment model is then established based on the second anomaly data, frequency information, and time information. For example, a weighted summation method can be used to quantify and comprehensively evaluate different factors to determine the target damage parameter corresponding to the target object during transportation.

[0047] Exemplarily, the quality determination module inputs the current first abnormal data into a trained quality grade prediction model for prediction. Based on the prediction results, the module determines a first quality type. Based on the first quality type, the module then performs quality adjustment using the target damage parameter to obtain a target quality type corresponding to the target object. The quality adjustment rules need to comprehensively consider the impact of the first quality type and the target damage parameter.

[0048] Specifically, the target quality type is determined by combining the first abnormal data with the target damage parameter, making the quality assessment more comprehensive and accurate. Traditional quality assessments may focus only on one aspect of the production process or the transportation process, but this method takes factors from both processes into account, more realistically reflecting the actual quality status of the target object.

[0049] In some embodiments, the image generation module includes: a text feature extraction module for performing feature extraction on the abnormal description text using the text feature extraction network of the image generation model in the platform layer to obtain first text feature information; an image feature extraction module for performing feature extraction on the normal image data using the image feature extraction network of the image generation model to obtain first image feature information; a feature fusion module for performing feature fusion on the first text feature information and the first image feature information using the parameter sharing network of the image generation model to obtain second text feature information and second image feature information; and an association analysis module for performing association degree analysis on the second text feature information and the second image feature information using the image-text analysis network of the image generation model. Obtain a graphic-text association value, and determine a corresponding graphic-text association matrix based on the graphic-text association value; an anomaly detection module, used to use the anomaly recognition network of the image generation model to determine a segmentation threshold using an optimization algorithm based on the graphic-text association matrix, and determine the image anomaly features corresponding to the normal image data under the abnormal description text and the text anomaly features corresponding to the abnormal description text under the normal image data based on the segmentation threshold and the graphic-text association matrix; an initial generation module, used to use the image generation network of the image generation model to generate an image based on the text anomaly features and the image anomaly features to obtain initial image data; an image fusion module, used to fuse the initial image data with the normal image data to obtain the abnormal image data corresponding to the target object.

[0050] For example, the text feature extraction module selects a suitable text feature extraction network from the image generation model at the platform level, such as a network based on the Transformer architecture. This network is initialized and configured, including hyperparameters such as the learning rate and batch size, to ensure efficient operation. The anomaly description text is then input into the configured text feature extraction network to obtain first text feature information.

[0051] For example, an image feature extraction network, such as a convolutional neural network (CNN), is selected from an image generation model. Normal image data is then input into the network. The network extracts image features such as edges, textures, and colors through operations such as convolution and pooling, ultimately outputting first image feature information.

[0052] Exemplarily, the feature fusion module constructs a parameter-sharing network for the image generation model. This network inputs the first text feature information and the first image feature information into the parameter-sharing network. The network then interacts and integrates these two features based on its internal parameters and structure, thereby generating the second text feature information and the second image feature information.

[0053] Exemplarily, the association analysis module utilizes a graph-text analysis network within an image generation model. This network can be constructed using, for example, an attention mechanism to better analyze the degree of association between text and image features. The second text feature information and the second image feature information are then input into the graph-text analysis network. The network calculates the similarity or correlation between the text and image features, generating graph-text association values. Based on these association values, a corresponding graph-text association matrix is ​​constructed, with the elements in the matrix representing the strength of association between different text and image features.

[0054] Exemplarily, the anomaly detection module utilizes an optimization algorithm, such as a genetic algorithm or simulated annealing algorithm, to determine a segmentation threshold. Based on the image-text association matrix, the module then searches for the optimal segmentation threshold, enabling accurate identification of abnormal features. The module then analyzes the normal image data and abnormal description text based on the determined segmentation threshold and the image-text association matrix. Portions exceeding the segmentation threshold are identified as image abnormality features and text abnormality features, corresponding to the abnormal portion of the normal image data within the abnormal description text and the abnormal portion of the abnormal description text within the normal image data, respectively.

[0055] Exemplarily, the initial generation module trains the image generation network of the image generation model to learn the mapping relationship between abnormal features and image generation. The trained image generation network then inputs the text abnormality features and image abnormality features into the trained image generation network. The network generates corresponding initial image data based on these abnormal features, thereby generating an image based on the abnormal portion of the normal image data under the abnormal description text.

[0056] Exemplarily, the image fusion module performs weighted fusion on the initial image data and the abnormal part of the normal image data under the abnormal description text to obtain abnormal image data corresponding to the target object.

[0057] In some embodiments, the model determination module includes: a data encoding module, used to encode the normal image data using the first encoder of the target abnormality recognition model to obtain a first feature representation, and simultaneously encode the abnormal image data using the second encoder of the target abnormality recognition model to obtain a second feature representation, wherein the network structure between the first encoder and the second encoder is the same and the network parameters are shared; an information reconstruction module, used to use the information reconstruction layer of the target abnormality recognition model to perform feature dimensionality reduction on the first feature representation to obtain a first low-dimensional representation and perform feature dimensionality reduction on the second feature representation to obtain a second low-dimensional representation, then perform a high-dimensional restoration operation on the first low-dimensional representation to obtain a first high-dimensional representation and perform a high-dimensional restoration operation on the second low-dimensional representation to obtain a second high-dimensional representation, and then perform similarity calculation on the first feature representation and the first high-dimensional representation to obtain a first similarity value and perform similarity calculation on the first feature representation and the second high-dimensional representation to obtain a second similarity value, and train the information reconstruction layer according to the first similarity value and the second similarity value to obtain the information reconstruction layer corresponding to the information reconstruction layer. information reconstruction parameters, and adjusting the first high-dimensional representation according to the information reconstruction parameters to obtain a third high-dimensional representation and adjusting the second high-dimensional representation to obtain a fourth high-dimensional representation; a feature processing module, used to use the feature processing layer of the target abnormality recognition model to perform feature compression on the third high-dimensional representation to obtain a third feature representation and to perform feature compression on the fourth high-dimensional representation to obtain a fourth feature representation; a data decoding module, used to use the first decoder of the target abnormality recognition model to decode the third feature representation to obtain a fifth feature representation and to decode the fourth feature representation to obtain a sixth feature representation; a loss calculation module, used to use the difference calculation layer of the target abnormality recognition model to perform difference calculation on the fifth feature representation and the sixth feature representation to obtain the target difference value corresponding to the abnormal image data and the normal image data, and determine the loss function between the abnormal image data and the normal image data according to the target difference value; a parameter adjustment module, used to adjust the parameters of the target abnormality recognition model according to the loss function until the target abnormality recognition model corresponding to the preset conditions is obtained.

[0058] Exemplarily, the data encoding module determines the first and second encoders in the target anomaly recognition model, and both have the same network structure and shared parameters. Normal image data is then input into the first encoder, which performs a series of transformations and feature extraction operations on the image data to convert it into a first feature representation. Simultaneously, abnormal image data is input into the second encoder. Due to parameter sharing, the second encoder encodes the abnormal image data in the same manner to obtain a second feature representation.

[0059] Exemplarily, the information reconstruction module utilizes the information reconstruction layer of the target anomaly recognition model to perform a feature dimensionality reduction operation on the first and second feature representations, converting the high-dimensional feature representations into low-dimensional representations, respectively, to obtain first and second low-dimensional representations. The first and second low-dimensional representations are then subjected to a high-dimensional restoration operation. A decoder or deconvolutional network, for example, can be used to restore the low-dimensional representations to high-dimensional representations, obtaining first and second high-dimensional representations. The similarity between the first feature representation and the first high-dimensional representation is then calculated to obtain a first similarity value. The similarity between the first feature representation and the second high-dimensional representation is then calculated to obtain a second similarity value. Based on these two similarity values, the information reconstruction layer is trained using an optimization algorithm (such as stochastic gradient descent) to adjust its parameters until satisfactory results are achieved, thereby obtaining information reconstruction parameters corresponding to the information reconstruction layer. Based on the obtained information reconstruction parameters, the first and second high-dimensional representations are then adjusted to obtain third and fourth high-dimensional representations, respectively.

[0060] Exemplarily, the feature processing module determines the feature processing layer of the target anomaly recognition model, which can employ structures such as fully connected layers and pooling layers. The feature processing layer is configured, with its parameters and hyperparameters set. The third and fourth high-dimensional representations are input into the feature processing layer for feature compression. By reducing the dimensionality and number of features, the third and fourth feature representations are obtained, reducing data redundancy and improving model efficiency and generalization.

[0061] Exemplarily, the data decoding module selects the first decoder of the target anomaly recognition model. The decoder's structure and functionality correspond to the encoder. The decoder is configured, including initializing parameters and setting hyperparameters. The third feature representation is input to the first decoder to obtain the fifth feature representation, and the fourth feature representation is input to the first decoder to obtain the sixth feature representation.

[0062] Exemplarily, the loss calculation module utilizes the difference layer of the target anomaly recognition model and uses methods such as mean square error (MSE) and cross entropy loss to perform difference calculations on the fifth feature representation and the sixth feature representation to obtain a target difference value between the abnormal image data and the normal image data, thereby determining the loss function between the abnormal image data and the normal image data based on the target difference value, and obtaining the corresponding loss value under the loss function.

[0063] Exemplarily, the parameter adjustment module uses the stochastic gradient descent method combined with the loss value to adjust the parameters of the target anomaly recognition model. In each iteration, the value of the loss function is calculated until the preset conditions are met (such as the loss function converges to a smaller value, the maximum number of iterations is reached, etc.), thereby obtaining the corresponding target anomaly recognition model that meets the preset conditions.

[0064] Specifically, by performing a series of operations on normal and abnormal image data, including encoding, reconstruction, compression, and decoding, the model can more deeply learn the differentiating features between normal and abnormal images. These differential features can help the model more accurately identify abnormal images, improving the accuracy of abnormality recognition.

[0065] In some embodiments, the data analysis module includes: a window segmentation module for determining a target window and cutting the second data according to the target window to obtain a plurality of initial window data; a matrix conversion module for determining a first matrix corresponding to the normal sensing data under multidimensional data and a second matrix corresponding to the initial window data under the same multidimensional data; an association processing module for performing matrix similarity calculation based on the first matrix and the second matrix to obtain a data association degree between the normal sensing data and the initial window data, and determining a data difference degree between the normal sensing data and the initial window data based on the data association degree; a distance calculation module for calculating the normal sensing data. The data distance between the sensor data and the initial window data is determined, and the target correlation between the normal sensor data and the initial window data is determined by fusing the data distance, the data correlation and the data difference; a distribution analysis module is used to perform data distribution analysis on the normal sensor data to obtain first distribution information and to perform data distribution analysis on the initial window data to obtain second distribution information; a difference determination module is used to fuse the first distribution information and the second distribution information according to the target correlation to determine the correlation difference value between the initial window data and the normal sensor data; a data screening module is used to obtain the second abnormal data from the initial window data according to the correlation difference value.

[0066] Exemplarily, the window segmentation module determines the size and step size of the target window based on expert experience or historical experience, and then segments the second data based on the determined target window. Starting from the starting position of the data, the data is sequentially segmented according to the size and step size of the target window, thereby obtaining multiple initial window data.

[0067] For example, the multidimensional data in the matrix conversion module can include different sensor indicators such as temperature, humidity, and pressure. The normal sensor data is then sorted and arranged according to the determined multidimensional data dimensions to construct a corresponding first matrix. Similarly, each initial window data is also constructed into a second matrix according to the same multidimensional data dimensions.

[0068] Exemplarily, the association processing module calculates the data correlation between the normal sensor data and the initial window data using a matrix similarity calculation method, such as cosine similarity or Euclidean distance. The correlation processing module then determines the data difference between the normal sensor data and the initial window data based on the calculated data correlation. For example, the data difference can be calculated by subtracting the data correlation from 1.

[0069] For example, the distance calculation module uses a data distance metric, such as Manhattan distance, to calculate the data distance between the normal sensor data and the initial window data. Based on the importance of the data and the actual situation, different weights are assigned to the data distance, data relevance, and data difference. These weights are then combined through weighted summation or other methods to determine the target relevance between the normal sensor data and the initial window data.

[0070] Exemplarily, the distribution analysis module obtains first distribution information corresponding to the normal sensing data and second distribution information corresponding to the initial window data by performing histogram analysis or kernel density estimation on the normal sensing data or the initial window data.

[0071] Exemplarily, the difference determination module performs weighted averaging on the first distribution information and the second distribution information in combination with the target correlation degree, thereby calculating the correlation difference value between the initial window data and the normal sensing data through the weighted averaged data, which can comprehensively reflect the degree of difference between the two.

[0072] Exemplarily, the data screening module sets an outlier threshold based on historical experience, and then compares the associated difference value of each initial window data with the outlier threshold, and screens out the initial window data whose associated difference value exceeds the outlier threshold as the second abnormal data.

[0073] In some embodiments, the difference determination module includes: a distribution difference analysis module, configured to calculate the difference between the first distribution information and the second distribution information to obtain a target distribution difference; a spatial analysis module, configured to determine the spatial distribution difference between the initial window data and the normal sensor data based on the target distribution difference in combination with the target correlation degree and the data distance; and a difference calculation module, configured to determine the correlation difference value between the initial window data and the normal sensor data based on the spatial distribution difference and the target distribution difference; wherein the correlation difference value is obtained according to the following formula:

[0074] ;

[0075] ;

[0076] in, represents the spatial distribution difference between the initial window data and the normal sensing data, represents the target distribution difference between the first distribution information and the second distribution information, represents the target relevance, Indicates the normal sensing data and the initial window data The data distance between them, exp represents the exponential function, R1 represents the normal sensing data The corresponding first matrix is, Represents the initial window data The corresponding second matrix is, represents the correlation difference value between the initial window data and the normal sensor data, n represents the total data volume corresponding to the union result obtained by performing union calculation on the normal sensor data and the initial window data, abs represents the absolute value, represents the first distribution information corresponding to the i-th union result under the normal sensing data, Represents the second distribution information corresponding to the i-th union result under the initial window data.

[0077] For example, the distribution difference analysis module calculates the absolute value or square value of the difference between the first distribution information and the second distribution information to obtain a target distribution difference, which can reflect the degree of difference between the two data distributions in terms of values.

[0078] For example, the spatial analysis module calculates the spatial distribution difference between the initial window data and the normal sensor data by fusing the target distribution difference, target correlation, and data distance according to the following formula. This difference can reflect the difference between the two sets of data from a more comprehensive spatial perspective:

[0079] ;

[0080] in, represents the spatial distribution difference between the initial window data and the normal sensing data, represents the target distribution difference between the first distribution information and the second distribution information, represents the target relevance, Indicates the normal sensing data and the initial window data The data distance between them, exp represents the exponential function, R1 represents the normal sensing data The corresponding first matrix is, Represents the initial window data The corresponding second matrix.

[0081] For example, the calculation difference module integrates the spatial distribution difference and the target distribution difference according to the influence mechanism of the spatial distribution difference and the target distribution difference on the correlation difference value using the following formula to ultimately determine the correlation difference value between the initial window data and the normal sensing data:

[0082] ;

[0083] in, represents the spatial distribution difference between the initial window data and the normal sensing data, represents the correlation difference value between the initial window data and the normal sensor data, n represents the total data volume corresponding to the union result obtained by performing union calculation on the normal sensor data and the initial window data, abs represents the absolute value, represents the first distribution information corresponding to the i-th union result under the normal sensing data, Represents the second distribution information corresponding to the i-th union result under the initial window data.

[0084] Specifically, the distribution difference analysis module directly compares the distribution information of the two sets of data and can keenly capture the differences in the data distribution patterns, which is crucial for discovering potential abnormal patterns. Combined with the spatial analysis module's consideration of data differences from a comprehensive spatial perspective, and the calculation difference module's integration of multiple difference information, the associated difference value can fully and accurately reflect the difference between the initial window data and normal sensor data, thereby greatly improving the accuracy of anomaly detection. Therefore, by separately analyzing the target distribution difference and spatial distribution difference, and then integrating them into the associated difference value, it is possible to gain a deeper understanding of the changes in the data distribution and spatial structure. This helps analysts discover potential patterns, trends, and abnormal characteristics in the data, providing more valuable information for further data mining and business decision-making.

[0085] In some embodiments, the false detection module includes: a similarity calculation module for eliminating the first abnormal data in the first data to obtain third data, and then performing similarity calculation on any two data in the third data to obtain an image similarity value; a data arrangement module for performing duplicate data screening on the third data according to the image similarity value to obtain fourth data, and obtaining a target reference image from the fourth data, and then arranging the similarities between the fourth data and the target reference image to obtain initial arrangement data; an arrangement screening module for performing mutual correlation information calculation on two consecutively adjacent data in the initial arrangement data to obtain a target correlation value, and obtaining a correlation value sequence corresponding to the initial arrangement data in a calculation order based on the target correlation value; an arrangement merging module for determining a preset value, and merging the initial arrangement data according to the preset value and the correlation value sequence to obtain target arrangement data; a data classification module for performing target classification on each sub-data in the target arrangement data according to a target classification model to obtain an initial data type corresponding to the sub-data; a classification merging module for fusing the initial data types to obtain a target data type corresponding to the first data, and performing false detection on the first information according to the target data type to obtain the target detection result.

[0086] Exemplarily, the similarity calculation module first removes the first abnormal data from the first data to obtain third data, and then calculates the image similarity value between any two data in the third data according to the structural similarity index.

[0087] Exemplarily, the data arrangement module sets a similarity threshold based on the calculated image similarity value. When the image similarity value of two data items exceeds the threshold, they are determined to be duplicate data, and one of the data items is removed, thereby obtaining a fourth data item. A representative data item is selected from the fourth data item as a target reference image. The most typical, common, or characteristic data item in the data set can be selected as a reference image. The similarity between each data item in the fourth data item and the target reference image is then calculated, and the data items are arranged in order of similarity from high to low or from low to high to obtain the initial arrangement data item.

[0088] For example, the permutation and screening module uses a cross-correlation function (e.g., a cross-correlation coefficient) to calculate a target correlation value between two consecutive data points in the initial permutation data. This cross-correlation information can reflect the temporal or spatial correlation between the two data points. The target correlation values ​​of each pair of adjacent data points are then arranged in the order of calculation to form a correlation value sequence corresponding to the initial permutation data.

[0089] For example, the permutation and merging module sets a preset value. This preset value can serve as a threshold for determining whether adjacent data can be merged. The module traverses the correlation value sequence. When the target correlation value of two adjacent data items is greater than the preset value, the two adjacent data items are merged into one. This process is repeated until all data items that meet the conditions are merged, ultimately obtaining the target permutation data.

[0090] For example, the data classification module uses a classification model, such as a convolutional neural network (CNN) or support vector machine (SVM), to train the target classification model using labeled training data, enabling it to accurately classify data. Each sub-data element in the target permutation data is then input into the trained target classification model, and the model outputs the initial data type corresponding to the sub-data element. The initial data type can be the attribute type corresponding to a specific attribute information of the target object.

[0091] Exemplarily, the classification and merging module uses a majority voting method to merge the initial data types of each sub-data to obtain the target data type corresponding to the first data. Based on the target data type and pre-set false detection rules (such as data type inconsistency with the business scenario, data type anomaly, etc.), false detection is performed on the first information, ultimately obtaining a target detection result.

[0092] Specifically, comprehensive consideration of multiple features, such as image similarity and correlation, can more comprehensively describe the relationships between data, thereby improving the accuracy of false positive detection. Different features can reflect the authenticity of data from different perspectives, and multi-dimensional analysis can reduce false positives and missed positives. In addition, arranging and merging data can reduce the amount of data, reducing the complexity and computational effort of subsequent processing.

[0093] In some embodiments, after obtaining the first data and the second data, the system further includes: a data storage module, used to use the perception layer of the Internet of Things to store the first data and the second data in the database, so that the platform layer of the Internet of Things obtains the first data and the second data from the database for data analysis.

[0094] Exemplarily, after obtaining the first data and the second data, the system also selects the corresponding database according to the data storage module, and then establishes a connection between the perception layer and the database, and then stores the first data and the second data in the database, so that the platform layer of the Internet of Things obtains the first data and the second data from the database for data analysis.

[0095] In some embodiments, the system also includes: an exception reminder module, which is used to generate a target reminder text based on the target detection result when the target detection result meets the preset result, and send the target reminder text to the target terminal, so that the target user corresponding to the target terminal performs exception processing according to the target reminder text.

[0096] For example, if the target detection result indicates abnormal content, the abnormality reminder module generates a target reminder text based on the target detection result combined with the text generation rules, and then sends the target reminder text to the target terminal. After receiving the target reminder text, the target terminal notifies the target user in a clear manner, such as a sound prompt, vibration, or pop-up window. The target user opens the reminder message to view a detailed description of the abnormality. The target user then develops a corresponding abnormality handling plan based on the abnormality information provided in the target reminder text and combines their own professional knowledge and experience. According to the developed abnormality handling plan, the target user then performs the corresponding operation on the target terminal.

[0097] See also Figure 2 , Figure 2 The embodiment of the present application provides a product anti-counterfeiting and traceability monitoring method based on the Internet of Things, which includes steps S201 to S206:

[0098] Step S201: Determine first information according to a target identifier of a target object using a perception layer of the Internet of Things, and collect first data of the target object during a production process and second data of the target object during a transportation process according to the perception layer;

[0099] Step S202: using the platform layer of the Internet of Things to perform abnormality identification on the first data to obtain first abnormal data; performing abnormality identification on the second data to obtain second abnormal data, and determining the target quality type corresponding to the target object based on the first abnormal data and the second abnormal data;

[0100] Step S203: Using the platform layer to perform false detection on the first information according to the first data to obtain a target detection result;

[0101] Step S204: using the platform layer to modify the first information according to the target quality type and the target detection result to obtain second information, and correlating the first abnormal data with the second abnormal data according to the second information to obtain relevant traceability information corresponding to the second information;

[0102] Step S205: using the platform layer to associate the target identifier, the second information, and the relevant traceability information and store them in a database;

[0103] Step S206: Utilize the application layer of the Internet of Things to obtain a target query identifier corresponding to the target user, and obtain third information and target traceability information corresponding to the target query identifier in the database according to the target query identifier.

[0104] In some embodiments, the product anti-counterfeiting and traceability monitoring method based on the Internet of Things can be applied to terminal devices.

[0105] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the above-described Internet of Things-based product anti-counterfeiting and traceability monitoring method can refer to the corresponding process in the aforementioned Internet of Things-based product anti-counterfeiting and traceability monitoring system embodiment, and will not be repeated here.

[0106] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of the product anti-counterfeiting and traceability monitoring system based on the Internet of Things provided in the description of the embodiment of the present invention.

[0107] The storage medium may be an internal storage unit of the terminal device described in the aforementioned embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc. equipped on the terminal device.

[0108] Those skilled in the art will appreciate that all or some of the steps, systems, and functional modules / units in the methods, systems, and devices disclosed above may be implemented as software, firmware, hardware, or any combination thereof. In hardware embodiments, the division between functional modules / units described above does not necessarily correspond to the division between physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is well known to those skilled in the art, the term computer storage media encompasses both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0109] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or system. In the absence of further limitations, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system that includes the element.

[0110] The serial numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be based on the scope of protection of the claims.

Claims

1. A product anti-counterfeiting traceability monitoring system based on the Internet of Things, characterized by: The system comprises: a data acquisition module, configured to determine first information according to a target identifier of a target object using a perception layer of the Internet of Things, and to collect first data of the target object during a production process and second data of the target object during a transportation process based on the perception layer; an exception handling module, configured to use the platform layer of the Internet of Things to perform exception identification on the first data to obtain first exception data; perform exception identification on the second data to obtain second exception data, and determine a target quality type corresponding to the target object based on the first exception data and the second exception data; a false detection module, configured to use the platform layer to perform false detection on the first information according to the first data to obtain a target detection result; a data association module, configured to utilize the platform layer to modify the first information according to the target quality type and the target detection result to obtain second information, and to associate the first abnormal data with the second abnormal data according to the second information to obtain relevant traceability information corresponding to the second information; A data storage module, configured to associate the target identifier, the second information, and the related traceability information using the platform layer and store the associations in a database; A data monitoring module is configured to obtain a target query identifier corresponding to a target user by using the application layer of the Internet of Things, and obtain third information and target traceability information corresponding to the target query identifier in the database according to the target query identifier; The exception handling module includes: A data acquisition module, configured to use the platform layer to collect normal image data corresponding to the target object during the production process, and obtain abnormal description text corresponding to the target object based on expert experience; An image generation module, configured to utilize the platform layer to perform abnormal adjustment on the normal image data according to the abnormal description text to obtain abnormal image data corresponding to the target object; A model determination module, configured to determine a target abnormality recognition model corresponding to the target object according to the normal image data and the abnormal image data using the platform layer; an anomaly identification module, configured to use the platform layer to perform anomaly identification on the first data according to the target anomaly identification model to obtain the first anomaly data; a data analysis module, configured to obtain normal sensor data corresponding to the target object during transportation using the platform layer, and to perform data association analysis based on the normal sensor data and the second data to obtain the second abnormal data; a damage determination module, configured to obtain frequency information and time information corresponding to the second abnormal data using the platform layer, and determine a target damage parameter corresponding to the target object during transportation based on the second abnormal data, the frequency information, and the time information; a quality determination module, configured to determine, by utilizing the platform layer, the target quality type corresponding to the target object according to the first abnormal data and the target damage parameter; Wherein, the false detection module includes: a similarity calculation module, configured to remove the first abnormal data from the first data to obtain third data, and then perform similarity calculation on any two data in the third data to obtain an image similarity value; a data arrangement module, configured to perform duplicate data screening on the third data according to the image similarity value to obtain fourth data, obtain a target reference image from the fourth data, and further arrange the similarities between the fourth data and the target reference image to obtain initial arrangement data; an arrangement and screening module, configured to calculate mutual correlation information of two consecutively adjacent data in the initial arrangement data to obtain a target correlation value, and obtain a correlation value sequence corresponding to the initial arrangement data according to the target correlation value in a calculation order; an arrangement merging module, configured to determine a preset value, and merge the initial arrangement data according to the preset value and the correlation value sequence to obtain target arrangement data; A data classification module is used to perform target classification on each sub-data in the target arrangement data according to a target classification model to obtain an initial data type corresponding to the sub-data; A classification and merging module is used to fuse the initial data type to obtain a target data type corresponding to the first data, and perform false detection on the first information according to the target data type to obtain the target detection result.

2. The system according to claim 1, wherein: The image generation module includes: A text feature extraction module, configured to extract features from the abnormality description text using a text feature extraction network of the image generation model in the platform layer to obtain first text feature information; An image feature extraction module, configured to extract features from the normal image data using the image feature extraction network of the image generation model to obtain first image feature information; a feature fusion module, configured to perform feature fusion on the first text feature information and the first image feature information using a parameter sharing network of the image generation model to obtain second text feature information and second image feature information; an association analysis module, configured to perform an association analysis on the second text feature information and the second image feature information using the image-text analysis network of the image generation model to obtain an image-text association value, and determine a corresponding image-text association matrix according to the image-text association value; an anomaly detection module, configured to use the anomaly recognition network of the image generation model to determine a segmentation threshold using an optimization algorithm according to the image-text association matrix, and to determine, based on the segmentation threshold and the image-text association matrix, image anomaly features corresponding to the normal image data under the anomaly description text and text anomaly features corresponding to the anomaly description text under the normal image data; An initial generation module, configured to generate an image using the image generation network of the image generation model according to the abnormal text features and the abnormal image features to obtain initial image data; An image fusion module is used to fuse the initial image data and the normal image data to obtain the abnormal image data corresponding to the target object.

3. The system according to claim 1, wherein: The model determination module includes: a data encoding module, configured to encode the normal image data using a first encoder of the target anomaly recognition model to obtain a first feature representation, and simultaneously encode the abnormal image data using a second encoder of the target anomaly recognition model to obtain a second feature representation, wherein the first encoder and the second encoder have the same network structure and share network parameters; an information reconstruction module, configured to use the information reconstruction layer of the target anomaly recognition model to perform feature dimensionality reduction on the first feature representation to obtain a first low-dimensional representation and to perform feature dimensionality reduction on the second feature representation to obtain a second low-dimensional representation, then perform a high-dimensional restoration operation on the first low-dimensional representation to obtain a first high-dimensional representation and a high-dimensional restoration operation on the second low-dimensional representation to obtain a second high-dimensional representation, and then perform a similarity calculation on the first feature representation and the first high-dimensional representation to obtain a first similarity value and a similarity calculation on the first feature representation and the second high-dimensional representation to obtain a second similarity value, train the information reconstruction layer according to the first similarity value and the second similarity value to obtain information reconstruction parameters corresponding to the information reconstruction layer, and adjust the first high-dimensional representation according to the information reconstruction parameters to obtain a third high-dimensional representation and adjust the second high-dimensional representation to obtain a fourth high-dimensional representation; a feature processing module, configured to perform feature compression on the third high-dimensional representation using the feature processing layer of the target anomaly recognition model to obtain a third feature representation and to perform feature compression on the fourth high-dimensional representation to obtain a fourth feature representation; a data decoding module, configured to decode the third feature representation using a first decoder of the target anomaly recognition model to obtain a fifth feature representation and decode the fourth feature representation to obtain a sixth feature representation; a loss calculation module, configured to perform a difference calculation on the fifth feature representation and the sixth feature representation using a difference calculation layer of the target abnormality recognition model to obtain a target difference value corresponding to the abnormal image data and the normal image data, and determine a loss function between the abnormal image data and the normal image data according to the target difference value; The parameter adjustment module is used to adjust the parameters of the target anomaly recognition model according to the loss function until the target anomaly recognition model corresponding to the preset conditions is obtained.

4. The system according to claim 1, wherein: The data analysis module includes: a window segmentation module, configured to determine a target window and segment the second data according to the target window to obtain a plurality of initial window data; a matrix conversion module, configured to determine a first matrix corresponding to the normal sensing data under multidimensional data and a second matrix corresponding to the initial window data under the same multidimensional data; an association processing module, configured to perform matrix similarity calculation based on the first matrix and the second matrix to obtain a data association degree between the normal sensing data and the initial window data, and determine a data difference degree between the normal sensing data and the initial window data based on the data association degree; a distance calculation module, configured to calculate a data distance between the normal sensing data and the initial window data, and then fuse the data distance, the data correlation degree, and the data difference degree to determine a target correlation degree between the normal sensing data and the initial window data; a distribution analysis module, configured to perform data distribution analysis on the normal sensing data to obtain first distribution information and to perform data distribution analysis on the initial window data to obtain second distribution information; a difference determination module, configured to determine a correlation difference value between the initial window data and the normal sensor data by fusing the first distribution information and the second distribution information according to the target correlation degree; A data screening module is used to obtain the second abnormal data from the initial window data according to the associated difference value.

5. The system according to claim 4, characterized in that The difference determination module includes: a distribution difference analysis module, configured to calculate a difference between the first distribution information and the second distribution information to obtain a target distribution difference; a spatial analysis module, configured to determine a spatial distribution difference between the initial window data and the normal sensing data according to the target distribution difference in combination with the target association degree and the data distance; a difference calculation module, configured to determine the correlation difference value between the initial window data and the normal sensing data according to the spatial distribution difference and the target distribution difference; The correlation difference value is obtained according to the following formula: ； ； in, represents the spatial distribution difference between the initial window data and the normal sensing data, represents the target distribution difference between the first distribution information and the second distribution information, represents the target relevance, Indicates the normal sensing data and the initial window data The data distance between them, exp represents the exponential function, R1 represents the normal sensing data The corresponding first matrix is, Represents the initial window data The corresponding second matrix is, represents the correlation difference value between the initial window data and the normal sensor data, n represents the total data volume corresponding to the union result obtained by performing union calculation on the normal sensor data and the initial window data, abs represents the absolute value, represents the first distribution information corresponding to the i-th union result under the normal sensing data, Represents the second distribution information corresponding to the i-th union result under the initial window data.

6. The system according to any one of claims 1 to 5, characterized in that After obtaining the first data and the second data, the system further includes: A data storage module is used to use the perception layer of the Internet of Things to store the first data and the second data in the database, so that the platform layer of the Internet of Things obtains the first data and the second data from the database for data analysis.

7. The system according to claim 6, characterized in that The system further comprises: The abnormality reminder module is used to generate a target reminder text according to the target detection result when the target detection result meets the preset result, and send the target reminder text to the target terminal, so that the target user corresponding to the target terminal performs abnormal processing according to the target reminder text.

8. A product anti-counterfeiting traceability monitoring method based on the Internet of Things, characterized in that: The method comprises: Determine first information according to a target identifier of a target object using a perception layer of the Internet of Things, and collect first data of the target object during a production process and second data of the target object during a transportation process according to the perception layer; Using the platform layer of the Internet of Things to perform abnormality identification on the first data to obtain first abnormal data; performing abnormality identification on the second data to obtain second abnormal data, and determining the target quality type corresponding to the target object based on the first abnormal data and the second abnormal data; Using the platform layer to perform false detection on the first information according to the first data to obtain a target detection result; Using the platform layer to modify the first information according to the target quality type and the target detection result to obtain second information, and correlating the first abnormal data with the second abnormal data according to the second information to obtain relevant traceability information corresponding to the second information; Utilizing the platform layer to associate the target identifier, the second information, and the relevant traceability information and store them in a database; Obtaining a target query identifier corresponding to a target user by using the application layer of the Internet of Things, and obtaining third information and target traceability information corresponding to the target query identifier in the database according to the target query identifier; The determining of the target quality type corresponding to the target object according to the first abnormal data and the second abnormal data includes: Using the platform layer to collect normal image data corresponding to the target object during the production process, and obtaining abnormal description text corresponding to the target object based on expert experience; Using the platform layer to perform abnormal adjustment on the normal image data according to the abnormal description text to obtain abnormal image data corresponding to the target object; Determining a target abnormality recognition model corresponding to the target object according to the normal image data and the abnormal image data using the platform layer; Using the platform layer to perform anomaly recognition on the first data according to the target anomaly recognition model to obtain the first abnormal data; Using the platform layer to obtain normal sensor data corresponding to the target object during transportation, and performing data association analysis based on the normal sensor data and the second data to obtain the second abnormal data; Obtaining frequency information and time information corresponding to the second abnormal data using the platform layer, and determining a target damage parameter corresponding to the target object during transportation based on the second abnormal data, the frequency information, and the time information; Determining the target quality type corresponding to the target object according to the first abnormal data and the target damage parameter using the platform layer; The step of using the platform layer to perform false detection on the first information according to the first data to obtain a target detection result includes: Eliminating the first abnormal data from the first data to obtain third data, and then performing similarity calculation on any two data in the third data to obtain an image similarity value; performing duplicate data screening on the third data according to the image similarity value to obtain fourth data, obtaining a target reference image from the fourth data, and further arranging the similarities between the fourth data and the target reference image to obtain initial arrangement data; Calculating mutual correlation information on two consecutively adjacent data in the initial arrangement data to obtain a target correlation value, and obtaining a correlation value sequence corresponding to the initial arrangement data in a calculation order according to the target correlation value; Determining a preset value, and merging the initial arrangement data according to the preset value and the correlation value sequence to obtain target arrangement data; Performing target classification on each sub-data in the target arrangement data according to a target classification model to obtain an initial data type corresponding to the sub-data; The initial data types are fused to obtain a target data type corresponding to the first data, and false detection is performed on the first information according to the target data type to obtain the target detection result.

Images