Industrial Internet of Things data security acquisition system based on block chain

Abstract

The invention discloses an industrial Internet of Things data security acquisition system based on a block chain, and belongs to the technical field of electronic data processing, and the system comprises an acquisition network establishment module which is used for connecting an industrial Internet of Things and obtaining a sensing industrial data source and is used for interacting an industrial data sensing layer in real time; the traceability inspection result obtaining module is used for encrypting and transmitting a sensing industrial data source to the edge computing layer; the enhanced industrial data source acquisition module is used for activating data enhancement dual channels in the edge calculation layer to perform enhancement processing on the sensing industrial data source based on the plurality of traceability inspection results; and the trusted industrial data block establishment module is used for inputting the enhanced industrial data source into the block chain trusted layer. The technical problem that in the prior art, industrial Internet of Things data is prone to being tampered and forged in the collection process, and consequently the reliability and credibility of the data are insufficient is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic data processing, and in particular to an industrial Internet of Things data security collection system based on blockchain. Background Art

[0002] With the rapid development of the Industrial Internet of Things, the amount of data generated by industrial equipment, sensors, and systems has grown exponentially. This data is widely used in areas such as equipment monitoring, production optimization, and intelligent decision-making. However, as the amount of data increases, data security, reliability, and privacy issues have gradually become prominent, becoming an important challenge facing the Industrial Internet of Things system.

[0003] Currently, industrial IoT data collection mostly relies on traditional centralized control systems, which are vulnerable to attacks or data tampering, resulting in data leakage or loss. At the same time, traditional traceability and data verification methods lack an effective credibility assessment mechanism, making it difficult to ensure data quality. Existing technologies have failed to fully combine decentralized technologies such as blockchain to ensure data security and credibility, and improvement is urgently needed. Summary of the invention

[0004] This application provides a blockchain-based industrial Internet of Things data security collection system to solve the technical problem in the prior art that industrial Internet of Things data is easily tampered with and forged during the collection process, resulting in insufficient data reliability and credibility.

[0005] In view of the above problems, this application provides an industrial Internet of Things data security collection system based on blockchain.

[0006] The present application provides a blockchain-based industrial Internet of Things data security collection system, which includes a collection network establishment module, which is used to connect the industrial Internet of Things and establish an industrial data collection network, wherein the industrial data collection network includes an industrial data perception layer, an edge computing layer and a blockchain trusted layer; a perceived industrial data source acquisition module, which is used to interact with the industrial data perception layer in real time to obtain a perceived industrial data source; a traceability inspection result acquisition module, which is used to encrypt and transmit the perceived industrial data source to the edge computing layer, and the traceability inspection channel in the edge computing layer performs traceability inspection on the perceived industrial data source to obtain multiple traceability inspection results; an enhanced industrial data source acquisition module, which is used to activate the data enhancement dual channels in the edge computing layer based on the multiple traceability inspection results to enhance the perceived industrial data source and obtain an enhanced industrial data source; a trusted industrial data block establishment module, which is used to input the enhanced industrial data source into the blockchain trusted layer, and the blockchain trusted layer performs on-chain and off-chain secure storage of the enhanced industrial data source to establish a trusted industrial data block.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The data collection solution that combines blockchain technology with the industrial Internet of Things, including the collaborative work of the industrial data perception layer, edge computing layer, and blockchain trust layer, solves the technical problem that the industrial Internet of Things data is easily tampered with and forged during the collection process in the existing technology, resulting in insufficient data reliability and credibility. Through real-time data collection and blockchain storage, the data is ensured to be tamper-proof and highly reliable, achieving the technical effect of enhancing data transparency, ensuring data security, and improving the accuracy of equipment monitoring and management.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of the structure of the industrial Internet of Things data security collection system based on blockchain provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of the structure of a trusted industrial data block establishment module in a blockchain-based industrial Internet of Things data security collection system provided in an embodiment of the present application.

[0011] Explanation of the accompanying drawings: collection network establishment module 11, perception industrial data source acquisition module 12, traceability inspection result acquisition module 13, enhanced industrial data source acquisition module 14, trusted industrial data block establishment module 15, multiple industrial data shard acquisition unit 151, off-chain storage block establishment unit 152, on-chain evidence block establishment unit 153, on-chain and off-chain mapping model construction unit 154, storage block alignment unit 155. DETAILED DESCRIPTION

[0012] The overall idea of ​​the technical solution provided by this application is as follows: The embodiment of the present application provides a blockchain-based industrial Internet of Things data security collection system. By combining blockchain technology with the industrial Internet of Things, secure collection and trusted storage of industrial data are achieved. The solution includes real-time data collection through the industrial data perception layer, preliminary data processing and verification by the edge computing layer, and then encrypted storage of the data through the blockchain trusted layer. This not only ensures the security of data during collection and transmission, but also effectively prevents data tampering, improves data reliability and transparency, and adapts to the high security requirements of industrial equipment monitoring and management.

[0013] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0014] Examples, such as Figure 1 As shown, the embodiment of the present application provides an industrial Internet of Things data security collection system based on blockchain, which includes: The collection network establishment module 11 is used to connect the industrial Internet of Things and establish an industrial data collection network, wherein the industrial data collection network includes an industrial data perception layer, an edge computing layer and a blockchain trusted layer.

[0015] Specifically, the industrial data acquisition network refers to a network system used to obtain and transmit data from industrial equipment. In this network, data is transmitted to different levels for processing, analysis, and storage. The industrial data perception layer is the bottom layer of the Internet of Things, responsible for sensing and collecting data from field equipment and sensors. The edge computing layer is located between the perception layer and the blockchain layer, responsible for preliminary data processing, analysis, and screening at a location close to the data source, reducing the burden of data transmission and improving response speed. The blockchain trust layer uses blockchain technology to decentralize the storage and encryption of data to ensure the immutability and security of the data and the long-term reliability of the data.

[0016] First, connect to the industrial Internet of Things and obtain real-time data through various sensing devices. These data will first be transmitted to the next layer through the industrial data sensing layer. Next, the data transmitted by the sensing layer will be sent to the edge computing layer. This layer is responsible for preliminary processing of the data. For example, the temperature data can be screened, cleaned or simply preprocessed through edge computing to reduce unnecessary data transmission. The edge computing layer can use local computing resources to monitor the status of industrial equipment, feedback abnormal data in a timely manner, and ensure real-time response. Finally, the data preliminarily processed by the edge computing layer will be transmitted to the blockchain trusted layer. The introduction of blockchain technology ensures the immutability and security of data. Each piece of data will be packaged into a block and stored in the blockchain to form a chain.

[0017] By building an industrial data collection network, the entire system can achieve more efficient and secure data collection, processing and storage. The industrial data perception layer can accurately obtain real-time data, the edge computing layer can reduce the pressure of data transmission and improve the system response speed, and the blockchain trust layer ensures the security, integrity and traceability of the data.

[0018] The perceived industrial data source acquisition module 12 is used to interact with the industrial data perception layer in real time to obtain the perceived industrial data source.

[0019] Specifically, perceived industrial data sources refer to data sources collected by industrial sensors and equipment, such as real-time temperature data collected by temperature sensors and real-time pressure values ​​collected by pressure sensors.

[0020] First, real-time data exchange is carried out with the perception layer through various sensing devices. Sensing devices such as temperature sensors, humidity sensors, gas detectors, etc., the system establishes connections with these devices through sensor interfaces to obtain data in real time. To ensure that data can be transmitted in a timely and accurate manner, wireless communication technology or wired communication technology is usually used for data exchange. Wireless communication technology is particularly suitable for situations where large-scale coverage or on-site installation is more complex. For example, in large factories, the use of LoRa wireless technology can ensure long-distance transmission and cover every corner of the workshop.

[0021] Through real-time interaction with the industrial data perception layer, the system can accurately collect real-time data of equipment and environment, thus laying the foundation for subsequent data processing and analysis.

[0022] The traceability inspection result obtaining module 13 is used to encrypt and transmit the perceived industrial data source to the edge computing layer, and the traceability inspection channel in the edge computing layer performs traceability inspection on the perceived industrial data source to obtain multiple traceability inspection results.

[0023] Specifically, the traceability inspection channel is a processing unit in the edge computing layer, which is used to trace the source and verify the credibility of the perceived industrial data. It can confirm whether the data is authentic by analyzing the source, transmission process, environment and other information of the data.

[0024] First, the perception data obtained from the industrial data perception layer is sent to the edge computing layer through encrypted transmission. The purpose of encrypted transmission is to protect the data from external tampering or theft during transmission and ensure the security of the data. For example, AES (Advanced Encryption Standard) or TLS (Transport Layer Security Protocol) is used to encrypt the data to ensure the confidentiality of the data when it is transmitted in the network.

[0025] Next, the traceability verification channel in the edge computing layer performs traceability verification on the received encrypted data. Traceability verification is to trace and verify the source of data to ensure that the data has not been tampered with and comes from a reliable device or sensor. Traceability verification determines the credibility of data by analyzing multiple dimensions of the sensor data source, such as the device status information of the sensor (such as whether it is working properly), the environmental information of the sensor (such as the temperature and humidity environment where the sensor is located), and the data transmission path (such as whether the data is transmitted through an encrypted channel).

[0026] Through encrypted transmission and traceability verification, the system ensures the security of data during transmission and effectively avoids the risk of data tampering or forgery.

[0027] The enhanced industrial data source acquisition module 14 is used to activate the data enhancement dual channels in the edge computing layer to enhance the perceived industrial data source based on the multiple traceability inspection results to obtain an enhanced industrial data source.

[0028] Specifically, the data enhancement dual channel refers to two processing channels used in the edge computing layer, which enhance the quality of data through different processing methods, including data cleaning channel and anomaly correction channel. Among them, the data cleaning channel is responsible for processing trusted data, removing noise, errors or inconsistent information, and improving data quality. The traceability anomaly correction channel is responsible for correcting untrustworthy data and correcting possible errors or anomalies based on traceability information. Enhanced industrial data source refers to the perceived industrial data source after data enhancement processing. The processed data is more accurate and reliable, and is suitable for subsequent data analysis or storage.

[0029] First, the system analyzes the credibility of each piece of data based on the traceability inspection results of the previous steps. If the data is judged to be credible (i.e., the traceability is credible), it enters the data cleaning channel; if the data is judged to be untrustworthy, it enters the traceability anomaly correction channel. For credible data, it is processed through the data cleaning channel. This channel is responsible for removing noise or inconsistencies in the data. For example, for the temperature data collected by the sensor, if some of the data points have errors, the cleaning channel will remove these errors to ensure the consistency and accuracy of the data. For untrustworthy data, correction is performed through the traceability anomaly correction channel. This channel corrects the data based on traceability information (such as device status, environmental conditions, etc.). For example, if a temperature sensor generates abnormal data due to a fault, the traceability correction channel will repair the data based on the device's historical status and ambient temperature information.

[0030] After cleaning and correcting, the trusted data and untrusted data will be processed through their respective channels to obtain two enhanced data areas: Trusted industrial data area: After data cleaning, the data is ensured to be error-free and the quality is improved. Corrected industrial data area: After traceability and anomaly correction, the untrusted data is corrected and the data quality is also improved. Finally, the data in the trusted industrial data area and the corrected industrial data area are merged to obtain the final enhanced industrial data source. This step ensures that data from different sources are processed uniformly and improves the credibility of the overall data.

[0031] By using dual data enhancement channels, the system can effectively improve the quality and credibility of industrial data. The data cleaning channel can remove noise from trusted data to ensure that only accurate data is used further; while the traceability anomaly correction channel can correct untrustworthy data to prevent erroneous data from affecting decision-making. This significantly improves the robustness and accuracy of the system in the face of uncertain environments and data quality fluctuations.

[0032] The trusted industrial data block establishment module 15 is used to input the enhanced industrial data source into the blockchain trusted layer, and the blockchain trusted layer securely stores the enhanced industrial data source on and off the chain to establish a trusted industrial data block.

[0033] Specifically, on-chain and off-chain secure storage means storing part of the data on the blockchain (on-chain) to ensure the data’s immutability, while storing most of the data in an off-chain storage system (off-chain) to reduce the storage pressure on the blockchain.

[0034] First, the system inputs the multi-processed enhanced industrial data sources into the blockchain trusted layer. These data have been cleaned, anomaly corrected and enhanced to ensure their quality and credibility. In the blockchain trusted layer, the data will be stored in two parts: Off-chain storage: Due to the limited storage space of the blockchain, the actual data content will be stored in a distributed storage system outside the blockchain (such as IPFS or cloud storage). These off-chain stored data can store larger-scale industrial data, such as raw sensor data, equipment logs, etc. On-chain storage: In order to ensure the immutability and long-term traceability of the data, the key features of the data (such as summary, hash value, data source ID, timestamp, etc.) will be stored on the blockchain. By storing these feature information in the blockchain, the uniqueness of the data on the chain can be ensured and it can be prevented from being tampered with.

[0035] By storing the key features of the enhanced industrial data source on the blockchain, the system forms a trusted industrial data block. The block contains verified, reliable data and corresponding on-chain evidence. The decentralized nature of the blockchain allows anyone to verify the authenticity of the data, while also ensuring that the data will not be tampered with during storage. Through blockchain encryption technology, the data stored on the blockchain cannot be tampered with, and all data changes can be traced. The source, storage process and modification history of the data can be traced at any time to ensure data transparency and security.

[0036] Through this step, the system achieves enhanced secure storage and verification of industrial data sources, using blockchain technology to ensure the data’s immutability and long-term traceability.

[0037] Furthermore, the traceability inspection result acquisition module includes: an industrial data extraction unit, used to extract the nth industrial data according to the perceived industrial data source, wherein n is a positive integer; a traceability scenario information acquisition unit, used to connect the industrial data perception layer, retrieve the perception device status information and perception device environment information corresponding to the nth industrial data, and obtain the nth traceability scenario information; a traceability credibility coefficient acquisition unit, used to perform credibility evaluation according to the nth traceability scenario information, and obtain the nth traceability credibility coefficient; a traceability inspection result output unit, used to input the nth traceability credibility coefficient into the traceability inspection channel, output the nth traceability inspection result, and add the nth traceability inspection result to the multiple traceability inspection results.

[0038] Specifically, the nth industrial data refers to the nth specific data selected from the perceived industrial data source, where n is a positive integer greater than or equal to 1. Perception device status information refers to the working status data of the equipment related to the industrial data source, such as whether the sensor is working properly or whether there is a fault. Perception device environment information refers to the parameters of the environment in which the perception device is located, such as external factors such as temperature and humidity, which may affect the operation of the device. Traceability scenario information is data generated based on device status and environmental information, which is used to describe the background of the data collection process and help understand the source of the data, collection conditions, and possible sources of errors. Credibility evaluation analyzes the traceability scenario information and evaluates the credibility of the data. It is usually measured by calculating the credibility coefficient, and data with a high credibility coefficient is considered more credible. The traceability credibility coefficient is a value calculated based on the traceability scenario information and credibility evaluation, which is used to indicate the credibility of a piece of data. The higher the value, the more credible the data.

[0039] First, the perception industrial data source is the data collected from the perception layer of the industrial Internet of Things. The data is transmitted to the edge computing layer through encryption. The traceability inspection channel in the edge computing layer is responsible for tracing the data to ensure the reliability of the data source. A specific industrial data is selected from multiple perception data sources as the nth industrial data. It may be the temperature value collected by the temperature sensor at a certain moment, or a reading of the pressure sensor. The system then retrieves the perception device status information and perception device environment information related to this nth industrial data. For example, if this data comes from a temperature sensor, the system will check the working status of the sensor (whether it is operating normally) and the environmental conditions such as temperature and humidity of the environment in which it is located. This information forms the nth traceability scenario information, which provides a basis for subsequent credibility evaluation.

[0040] The system uses the collected traceability scenario information to conduct a credibility evaluation. A credibility evaluation model, such as a machine learning model or a rule-based system, is usually used to analyze the device status and environmental information. For example, if the temperature sensor is in normal working condition and the ambient temperature is stable, the credibility of the data is high. On the contrary, if the device is in a faulty state or the environment is abnormal, the data credibility is low. Based on the credibility evaluation results, the system generates a traceability credibility coefficient, which reflects the reliability of the data. Finally, the nth traceability credibility coefficient is input into the traceability inspection channel, and the channel determines whether the data is credible by comparing the set predetermined credibility threshold. If the credibility coefficient is higher than the preset threshold, the data passes the inspection and is considered credible; otherwise, the data is marked as unreliable. The traceability inspection results will be added to multiple traceability inspection results.

[0041] Through this traceability inspection process, the system can evaluate the credibility of each piece of industrial data in real time, thereby ensuring the reliability and validity of the data. It effectively prevents data anomalies caused by sensor failure, data tampering or environmental factors, reduces the impact of erroneous data on production decisions, and thus improves the reliability and security of the entire industrial Internet of Things system.

[0042] Furthermore, the traceability credibility coefficient obtaining unit includes: a sample set loading unit, used to connect to the industrial Internet of Things, load the traceability scenario sample set and the traceability credibility evaluation sample set; an evaluation model obtaining unit, used to perform supervised learning on K traceability credibility evaluation learners according to the traceability scenario sample set and the traceability credibility evaluation sample set, and obtain K traceability credibility evaluation models that meet the predetermined traceability credibility evaluation accuracy, wherein K is a positive integer greater than 1; a scene information input unit, used to input the nth traceability scenario information into the K traceability credibility evaluation models, and obtain K traceability credibility evaluation coefficients; a mean calculation unit, used to perform mean calculation on the K traceability credibility evaluation coefficients, and output the nth traceability credibility coefficient.

[0043] Specifically, the provenance trust evaluation learner is a machine learning model used to evaluate the credibility of data. An evaluation mechanism is constructed by learning the provenance scenario sample set and the provenance trust evaluation sample set. The provenance trust evaluation model is a model obtained through training, which can output the credibility evaluation of the data based on the input provenance scenario information.

[0044] First, the system loads traceability scenario sample sets and traceability trust evaluation sample sets from the industrial Internet of Things. These sample sets contain traceability scenario information that has been obtained in the past and the corresponding known trust labels for subsequent model training. The sample sets can include different types of sensing devices and working environments, including various possible sensor states and environmental conditions. For example, the state information and environmental information of a temperature sensor may include whether the device is working properly, the temperature and humidity of the working environment, etc.

[0045] Next, the system will input the traceability scenario sample set and the traceability trust evaluation sample set into K traceability trust evaluation learners for supervised learning. By analyzing these sample sets, the learner learns how to evaluate the credibility of the data based on the traceability scenario information. Specifically, representative traceability scenario sample sets and corresponding credibility labels are collected as training data. Then, a suitable machine learning algorithm, such as decision tree, support vector machine (SVM) or deep learning model, is selected to train the sample set. During the training process, the model generates a credibility evaluation model by learning the relationship between the characteristics of the traceability scenario (such as equipment status, environmental information, etc.) and credibility. Finally, the performance of the model is evaluated using methods such as cross-validation to ensure that the accuracy of its credibility evaluation meets the predetermined requirements. Among them, each model can focus on different characteristics of the traceability scenario, such as sensor status, environmental changes, etc.

[0046] After the training is completed, the newly acquired nth traceability scenario information is input into the K traceability trust evaluation models. The model will give K traceability trust evaluation coefficients respectively, that is, the credibility evaluation value of each model for the data. For example, the nth traceability scenario information may include the working status, temperature and humidity of the temperature sensor, and different learning models may evaluate its credibility based on different characteristics and obtain different results. In order to integrate the evaluation results of multiple models, the K traceability trust evaluation coefficients are averaged to obtain a final nth traceability trust coefficient. By taking the average, the deviation that may occur in a single model can be reduced, and the accuracy and stability of the evaluation can be improved.

[0047] Finally, the calculated nth traceability credibility coefficient is output, which is used to indicate the credibility of the nth data. This credibility coefficient will be used for subsequent traceability inspection to ensure that the data can be stored and used correctly.

[0048] Through this step, the system uses multiple machine learning models to evaluate the traceability scenario information, greatly improving the accuracy of data credibility assessment. The multi-model comprehensive evaluation method can effectively avoid the risks caused by sensor failure or data tampering, thereby ensuring the data accuracy and reliability of the entire IoT system.

[0049] Furthermore, the traceability verification channel includes a traceability verification operator, and the traceability verification operator includes: a traceability credibility judgment unit, if the nth traceability credibility coefficient is greater than or equal to a predetermined traceability credibility coefficient, the nth traceability verification result is traceability credibility; a traceability untrustworthy judgment unit, if the nth traceability credibility coefficient is less than the predetermined traceability credibility coefficient, the nth traceability verification result is traceability untrustworthy.

[0050] Specifically, the traceability verification operator is the core component in the traceability verification channel, which is responsible for judging based on the traceability credibility coefficient and outputting the conclusion whether it is credible, and using a predetermined credibility threshold to judge the data. The predetermined traceability credibility coefficient is a set credibility threshold used for comparison with the traceability credibility coefficient as a standard for whether the data is credible.

[0051] First, extract the nth data from the perception data source, and calculate the nth traceability credibility coefficient of the data through the above steps. For example, if the state of the temperature sensor is normal and the environment is stable, the credibility of the data is high, and a higher credibility coefficient is obtained. Then, compare the nth traceability credibility coefficient with the preset predetermined traceability credibility coefficient. The predetermined credibility coefficient is a set standard value that indicates the minimum credibility requirement that the data should meet. For example, a predetermined credibility coefficient of 0.8 means that only data with a credibility coefficient greater than or equal to 0.8 is considered credible. According to the comparison result, the traceability verification operator outputs the corresponding test result. If the nth traceability credibility coefficient is greater than or equal to the predetermined credibility coefficient, "traceability is credible" is output; otherwise, "traceability is unreliable" is output.

[0052] Through the judgment mechanism of the traceability verification operator, the system can efficiently evaluate the credibility of data and ensure that only highly reliable data can enter subsequent processing or storage. The system can filter out unreliable data in a timely manner to ensure the safety and efficiency of the production process.

[0053] Furthermore, the enhanced industrial data source acquisition module 14 includes: a data enhancement dual-channel unit, the data enhancement dual-channel includes a data cleaning model and a traceability anomaly correction model; an industrial data source classification unit, used to classify the perceived industrial data source according to the multiple traceability inspection results, and establish a trusted industrial data area and an untrusted industrial data area; a first enhanced industrial data area acquisition unit, used to input the trusted industrial data area into the data cleaning model to obtain a first enhanced industrial data area; a corrected industrial data area acquisition unit, used to perform data correction on the untrusted industrial data area according to the traceability anomaly correction model to obtain a corrected industrial data area; a second enhanced industrial data area acquisition unit, used to perform enhancement processing on the corrected industrial data area according to the data cleaning model to obtain a second enhanced industrial data area; an enhanced industrial data area fusion unit, used to fuse the first enhanced industrial data area and the second enhanced industrial data area to obtain the enhanced industrial data source.

[0054] Specifically, the data cleaning model is used to clean and optimize the model of industrial data, aiming to remove noise, outliers or erroneous information in the data to make the data more consistent and accurate. The traceability anomaly correction model is used to correct the model of untrusted data, and correct anomalies or errors in the data through traceability information (such as equipment status and environmental conditions). The trusted industrial data area contains all data that have passed the traceability inspection and are considered to be trusted. After the data is evaluated for credibility, it enters this area for further processing. The untrusted industrial data area contains all data that are considered to be untrusted. These data need to be corrected by the traceability anomaly correction model to improve their credibility. The first enhanced industrial data area is the data area obtained by processing the data cleaning model, and all cleaned data are in this area. The second enhanced industrial data area is the data area corrected by the traceability anomaly correction model. This part of the data was originally untrusted data, but after processing, it is enhanced and trusted data.

[0055] First, the system will classify all perceived industrial data sources based on the previous traceability test results. According to the traceability test results, the data is divided into two categories: trusted industrial data area and untrusted industrial data area. For example, if the reading value of the temperature sensor is consistent with the preset standard and the traceability test is passed, it will be assigned to the trusted industrial data area; if the data reading is abnormal or the working state of the sensor is unstable, it will be assigned to the untrusted industrial data area.

[0056] Next, all data belonging to the trusted industrial data zone will be input into the data cleaning model. Among them, the construction method of the data cleaning model usually includes the following steps: Collect and preprocess the original data to identify missing values, duplicate values ​​and outliers. Use statistical analysis methods or rule-based algorithms (such as Z-score, IQR) to detect abnormal data. Apply strategies such as interpolation, filling or deletion to handle missing values ​​and outliers to ensure the consistency and integrity of the data. In order to improve the performance of the model, combine machine learning methods such as decision trees or clustering algorithms to automatically identify and repair noise in the data. Finally, through cross-validation and evaluation indicators, ensure that the model cleaning effect achieves the expected accuracy. The data cleaning model will identify and remove noise, erroneous values ​​or inconsistencies in the data to ensure the consistency and accuracy of the data. For example, if there is a momentary and drastic fluctuation in the temperature data within a certain period of time (which may be caused by a short-term sensor failure), the data cleaning model will remove these abnormal points and retain the real temperature fluctuation data. The cleaned data forms the first enhanced industrial data zone.

[0057] For data belonging to the untrusted industrial data area, they will first be input into the traceability anomaly correction model. Among them, the method for constructing the traceability anomaly correction model includes the following steps: collect raw data with traceability information and mark abnormal data. Based on historical data and equipment status information, supervised learning algorithms (such as regression analysis, decision trees, or support vector machines) are used to model the data and learn the relationship between data and traceability information. The model will correct errors in the data based on traceability information (such as equipment status, working environment, etc.). For example, if the data collected by the sensor does not match other equipment or historical data, the correction model will make corrections based on factors such as the working status of the sensor and environmental changes to adjust the data to a reasonable range. After correction, this part of the data forms a corrected industrial data area.

[0058] Finally, the system further enhances the data in the corrected industrial data area. The enhancement process usually uses a data cleaning model to clean up the noise in the data again and generate a second enhanced industrial data area. Then, the system merges the first enhanced industrial data area (cleaned trusted data) with the second enhanced industrial data area (corrected untrusted data) to obtain the final enhanced industrial data source.

[0059] Through this data enhancement dual-channel processing method, the system can significantly improve the quality and credibility of data. The data cleaning model ensures the purity and consistency of reliable data, avoiding analysis errors caused by noise or erroneous values; the traceability anomaly correction model repairs unreliable data to make it closer to the actual situation, so that unreliable data can also play a role, avoiding production stagnation or decision-making errors caused by missing data.

[0060] Furthermore, the corrected industrial data area obtaining unit includes: an untrusted industrial data area traversal unit, used to traverse the untrusted industrial data area and extract the first untrusted industrial data; a traceability scenario information corresponding unit, used to use the traceability scenario information corresponding to the first untrusted industrial data as the untrusted traceability scenario information; an anomaly detection unit, used to perform anomaly detection based on the untrusted traceability scenario information and obtain a traceability scenario anomaly detection result; a first corrected industrial data obtaining unit, used to input the first untrusted industrial data and the traceability scenario anomaly detection result into the traceability anomaly correction model, obtain the first corrected industrial data, and add the first corrected industrial data to the corrected industrial data area.

[0061] Specifically, untrusted traceability scenario information refers to the equipment and environment information related to untrusted industrial data, including background data such as equipment status and working environment, to help determine the credibility of the data.

[0062] First, the system traverses the untrusted industrial data area and extracts the first untrusted industrial data. For each piece of untrusted data, the system extracts the traceability scenario information related to it, such as the working status of the equipment, ambient temperature and humidity, etc. Through these traceability scenario information, the system can understand the background of the data and possible sources of anomalies. For example, if the temperature sensor works in an extreme environment, abnormal data may be generated, and the traceability scenario information will provide relevant context. Based on the extracted untrusted traceability scenario information, the system performs anomaly detection. This process uses data analysis methods such as statistical tests and model-based detection methods (such as decision trees, cluster analysis, etc.) to discover anomalies in traceability scenarios.

[0063] The first untrusted industrial data and the anomaly detection results of the traceability scenario are input into the traceability anomaly correction model. The correction model uses the traceability information to correct the data. For example, if the sensor data is inaccurate due to equipment failure, the correction model will repair the data value according to the normal working state or environmental conditions of the equipment to obtain the first corrected industrial data. The corrected data will be added to the corrected industrial data area to ensure that the quality and credibility of these data are improved after the anomaly correction. The corrected data can be used for subsequent storage, analysis and decision-making.

[0064] Through this process of the traceability anomaly correction model, the system can significantly improve the credibility of untrusted data, thereby ensuring the accuracy and reliability of subsequent data. This step can accurately correct abnormal data using the traceability information of the equipment and environment, avoiding the errors that may be caused by relying on simple filtering or mean filling to process abnormal data.

[0065] Further, such as Figure 2As shown, the trusted industrial data block establishment module 15 includes: a plurality of industrial data shard acquisition units, which are used to perform sharding processing on the enhanced industrial data source to obtain a plurality of industrial data shards; an off-chain storage block establishment unit, which is used to perform off-chain encrypted storage of the plurality of industrial data shards according to the blockchain trusted layer, and establish an off-chain storage block; an on-chain evidence block establishment unit, which is used to perform on-chain secure storage of key features of the plurality of industrial data shards according to the blockchain trusted layer, and establish an on-chain evidence block; an on-chain and off-chain mapping model construction unit, which is used to construct an on-chain and off-chain mapping model according to the mapping relationship between the on-chain evidence block and the off-chain storage block; and a storage block alignment unit, which is used to align the on-chain evidence block with the off-chain storage block according to the on-chain and off-chain mapping model to generate the trusted industrial data block.

[0066] Specifically, sharding refers to splitting a large data set into multiple small parts (shards) for more efficient storage and processing. Each shard contains a subset of the original data, which facilitates distributed storage and parallel processing. On-chain evidence blocks are data blocks stored on the blockchain, containing key features of the data (such as data hash values, summaries, timestamps, etc.). These evidence blocks ensure the immutability and traceability of data on the blockchain. Off-chain storage blocks are encrypted data blocks stored outside the blockchain, containing detailed content of enhanced industrial data sources. Off-chain storage can store large amounts of data, while blockchain storage has limited space. The on-chain and off-chain mapping model is a model used to establish the correspondence between on-chain evidence blocks and off-chain storage blocks. This model helps the system align on-chain evidence information with off-chain stored data to ensure data integrity.

[0067] First, the system shards the enhanced industrial data source and splits the original data into multiple small data shards. For example, a set of sensor data such as temperature and pressure is split into multiple data fragments, each of which contains data for a certain time range or a specific device. This processing method improves the efficiency of data storage and transmission and can disperse storage pressure. Then, the system stores the sharded data in off-chain storage blocks. Due to the limited storage space of the blockchain, the complete data needs to be stored in an external distributed storage system (such as IPFS or cloud storage). Before storage, the system encrypts the data to ensure the privacy and security of the data. At the same time, the system extracts key features of the sharded data, such as data summary (hash value), timestamp, data source ID, etc., and stores these features on the blockchain.

[0068] Construct an on-chain and off-chain mapping model that establishes a corresponding relationship between the on-chain evidence block and the off-chain storage block. For example, the on-chain evidence block records the hash value of the temperature data, while the off-chain storage block stores the specific temperature value. The mapping model ensures the corresponding relationship between these data, thereby ensuring the accuracy and consistency of the data. Specifically, extract the key features of the off-chain storage block and the on-chain evidence block, such as data summary (hash value), timestamp, and data source ID. Use these features to establish a corresponding relationship, and ensure data consistency by recording the mapping between each on-chain evidence block and the corresponding off-chain storage block. Use a database or distributed ledger technology to store the mapping relationship for subsequent query and verification.

[0069] Finally, the system aligns the on-chain evidence block with the off-chain storage block according to the mapping model to generate a trusted industrial data block. This data block contains enhanced and encrypted industrial data to ensure its security, integrity, and long-term traceability.

[0070] Through this process, the system achieves secure storage and efficient management of industrial data. The data is sharded and encrypted and stored outside the blockchain, ensuring the effective use of storage space, while the key features are stored on the blockchain, ensuring the data is tamper-proof and verifiable.

[0071] Furthermore, the on-chain evidence block establishment unit includes: a shard summary block acquisition unit, which is used to perform summary feature recognition on the multiple industrial data shards to obtain a shard summary block; a shard storage address block acquisition unit, which is used to collect off-chain storage address parameters corresponding to the multiple industrial data shards to obtain a shard storage address block; a shard source block acquisition unit, which is used to collect source feature parameters of the multiple industrial data shards to obtain a shard source block; a shard access control block acquisition unit, which is used to perform access control feature configuration on the multiple industrial data shards to obtain a shard access control block; an industrial data key feature block establishment unit, which is used to merge the shard summary block, the shard storage address block, the shard source block and the shard access control block to establish an industrial data key feature block; an on-chain secure storage unit, which is used to perform on-chain secure storage of the industrial data key feature block according to the blockchain trusted layer to obtain the on-chain evidence block.

[0072] Specifically, summary feature recognition refers to hashing data to generate a summary (or hash value) of the data. The hash value is the unique identifier of the data and can be used to verify the integrity and immutability of the data. Among them, the shard summary block is a data block generated after the summary feature recognition of the data shard. The industrial data key feature block is a block composed of multiple key features, including the hash value, storage address, source information, and access control of the shard, to ensure the integrity, source traceability, and security of the data.

[0073] First, each industrial data shard is hashed to generate a shard summary block. This step ensures the uniqueness of each data shard by calculating the hash value of the data (for example, using the SHA-256 algorithm). For example, the data shard of the temperature sensor is hashed to obtain a unique summary that represents the characteristics of the data. Then, the system obtains the storage address of each data shard stored outside the blockchain, that is, the shard storage address block. These data are stored in distributed storage systems (such as IPFS, distributed cloud storage), so the system needs to record the specific storage location of each shard. For example, a file storing temperature data may be stored in a specific node of the IPFS network, and the address information is used as part of the storage address block. Further, the system collects source feature parameters related to each data shard, such as the device information of the data source, the collection time, etc., to form a shard source block. For example, the source characteristics of temperature data may include information such as the device ID of the temperature collection device, the sensor model, and the collection environment. The system configures the access rights of each data shard to form a shard access control block. This step ensures data security by setting access rights.

[0074] Then, the system merges the above four features (shard summary block, shard storage address block, shard source block, and shard access control block) to form an industrial data key feature block. This key feature block contains all the key information of the data shard, ensuring its uniqueness and traceability on the blockchain. Finally, the industrial data key feature block is stored in the blockchain trusted layer to form an on-chain evidence block. The evidence block is permanently stored on the blockchain to ensure the immutability and security of the data. The hash value and other feature information in the evidence block can be verified at any time to ensure that the data has not been tampered with.

[0075] Through this step, the system realizes the secure storage and verification of industrial data, ensuring the security and traceability of data in the distributed storage system. The key information of each data shard is stored on the blockchain, ensuring that the data source can be verified, the storage location can be traced, and only authorized users can access the data.

[0076] In summary, the blockchain-based industrial Internet of Things data security collection system provided by the embodiment of the present application has the following technical effects: 1. By combining blockchain and industrial IoT, the security and credibility of the data collection process are ensured. Through the collaborative work of the perception layer, edge computing layer and blockchain layer, the reliability and transparency of the data are improved, data tampering and forgery are effectively prevented, and the intelligence of industrial equipment monitoring and management is enhanced.

[0077] 2. Data enhancement dual channels improve the quality of credible and unreliable data through cleaning and correction processing. Through the dual effects of cleaning model and anomaly correction model, the accuracy and integrity of industrial data are ensured, and the reliability of data analysis results is enhanced.

[0078] 3. The blockchain's on-chain and off-chain storage solutions ensure that data cannot be tampered with and can be traced over a long period of time. By processing and encrypting data in shards, and combining on-chain evidence blocks with off-chain storage blocks, data security and integrity are enhanced, meeting the storage needs of large-scale industrial data.

[0079] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0080] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. The industrial Internet of Things data security collection system based on blockchain is characterized by: The system comprises: A collection network establishment module, used to connect the industrial Internet of Things and establish an industrial data collection network, wherein the industrial data collection network includes an industrial data perception layer, an edge computing layer, and a blockchain trusted layer; A perception industrial data source acquisition module, used for interacting with the industrial data perception layer in real time to obtain a perception industrial data source; A traceability inspection result obtaining module is used to encrypt and transmit the perceived industrial data source to the edge computing layer, and the traceability inspection channel in the edge computing layer performs traceability inspection on the perceived industrial data source to obtain multiple traceability inspection results; An enhanced industrial data source acquisition module is used to activate the data enhancement dual channels in the edge computing layer to enhance the perceived industrial data source based on the multiple traceability inspection results to obtain an enhanced industrial data source; The trusted industrial data block establishment module is used to input the enhanced industrial data source into the blockchain trusted layer, and the blockchain trusted layer securely stores the enhanced industrial data source on and off the chain to establish a trusted industrial data block.

2. The industrial Internet of Things data security collection system based on blockchain as claimed in claim 1 is characterized in that: The traceability test result acquisition module includes: An industrial data extraction unit, configured to extract nth industrial data according to the sensed industrial data source, wherein n is a positive integer; A traceability scene information obtaining unit, used to connect to the industrial data perception layer, retrieve the perception device state information and perception device environment information corresponding to the nth industrial data, and obtain the nth traceability scene information; A traceability credibility coefficient obtaining unit, used to perform credibility evaluation according to the nth traceability scenario information to obtain the nth traceability credibility coefficient; The traceability inspection result output unit is used to input the nth traceability credibility coefficient into the traceability inspection channel, output the nth traceability inspection result, and add the nth traceability inspection result to the multiple traceability inspection results.

3. The industrial Internet of Things data security collection system based on blockchain as claimed in claim 2 is characterized in that: The traceability credibility coefficient obtaining unit includes: A sample set loading unit, used to connect to the industrial Internet of Things and load a traceability scenario sample set and a traceability trusted evaluation sample set; An evaluation model obtaining unit, configured to perform supervised learning on K traceability trustworthy evaluation learners according to the traceability scenario sample set and the traceability trustworthy evaluation sample set, to obtain K traceability trustworthy evaluation models that meet a predetermined traceability trustworthy evaluation accuracy, wherein K is a positive integer greater than 1; A scene information input unit, used to input the nth traceability scene information into the K traceability trust evaluation models to obtain K traceability trust evaluation coefficients; The mean calculation unit is used to perform mean calculation on the K traceability credibility evaluation coefficients and output the nth traceability credibility coefficient.

4. The industrial Internet of Things data security collection system based on blockchain as claimed in claim 2 is characterized in that: The traceability verification channel includes a traceability verification operator, and the traceability verification operator includes: A traceability credibility judgment unit, if the nth traceability credibility coefficient is greater than or equal to a predetermined traceability credibility coefficient, the nth traceability inspection result is traceability credibility; The traceability unreliable judgment unit is configured to determine that if the nth traceability credibility coefficient is less than the predetermined traceability credibility coefficient, the nth traceability inspection result is that the traceability is unreliable.

5. The industrial Internet of Things data security collection system based on blockchain as claimed in claim 1 is characterized in that: The enhanced industrial data source acquisition module includes: A data enhancement dual-channel unit, wherein the data enhancement dual-channel includes a data cleaning model and a traceability anomaly correction model; An industrial data source classification unit, configured to classify the perceived industrial data sources according to the plurality of traceability inspection results, and establish a trusted industrial data area and an untrusted industrial data area; A first enhanced industrial data area obtaining unit, configured to input the trusted industrial data area into the data cleaning model to obtain a first enhanced industrial data area; A corrected industrial data area obtaining unit, used for performing data correction on the untrusted industrial data area according to the traceability anomaly correction model to obtain a corrected industrial data area; A second enhanced industrial data area obtaining unit, configured to perform enhancement processing on the corrected industrial data area according to the data cleaning model to obtain a second enhanced industrial data area; The enhanced industrial data area fusion unit is used to fuse the first enhanced industrial data area and the second enhanced industrial data area to obtain the enhanced industrial data source.

6. The industrial Internet of Things data security collection system based on blockchain as claimed in claim 5 is characterized in that: The correction industrial data area obtaining unit comprises: An untrusted industrial data area traversal unit, used for traversing the untrusted industrial data area to extract first untrusted industrial data; A traceability scenario information corresponding unit, configured to use the traceability scenario information corresponding to the first untrusted industrial data as the untrusted traceability scenario information; An anomaly detection unit, used to perform anomaly detection based on the untrusted traceability scenario information to obtain a traceability scenario anomaly detection result; The first corrected industrial data obtaining unit is used to input the first untrusted industrial data and the traceability scenario anomaly detection result into the traceability anomaly correction model to obtain the first corrected industrial data, and add the first corrected industrial data to the corrected industrial data area.

7. The industrial Internet of Things data security collection system based on blockchain as claimed in claim 1 is characterized in that: The trusted industrial data block establishment module includes: A plurality of industrial data shard obtaining units, used for performing sharding processing on the enhanced industrial data source to obtain a plurality of industrial data shards; An off-chain storage block establishing unit, configured to perform off-chain encrypted storage on the plurality of industrial data shards according to the blockchain trusted layer, and establish an off-chain storage block; An on-chain evidence block establishment unit, used to securely store key features of the multiple industrial data shards on-chain according to the blockchain trusted layer, and establish an on-chain evidence block; An on-chain and off-chain mapping model construction unit, used to construct an on-chain and off-chain mapping model according to the mapping relationship between the on-chain evidence block and the off-chain storage block; A storage block alignment unit is used to align the on-chain evidence block and the off-chain storage block according to the on-chain and off-chain mapping model to generate the trusted industrial data block.

8. The industrial Internet of Things data security collection system based on blockchain as claimed in claim 7 is characterized in that: The on-chain evidence block establishment unit includes: A fragment summary block obtaining unit, configured to perform summary feature recognition on the plurality of industrial data fragments to obtain fragment summary blocks; A shard storage address block obtaining unit, used to collect off-chain storage address parameters corresponding to the multiple industrial data shards to obtain a shard storage address block; A slice source block obtaining unit, used for collecting source characteristic parameters of the plurality of industrial data slices to obtain slice source blocks; A shard access control block obtaining unit, configured to perform access control feature configuration on the plurality of industrial data shards to obtain shard access control blocks; An industrial data key feature block establishing unit, used to merge the slice summary block, the slice storage address block, the slice source block and the slice access control block to establish an industrial data key feature block; The on-chain secure storage unit is used to securely store the key feature block of industrial data on the chain according to the blockchain trusted layer to obtain the on-chain evidence block.

Images