Data Access Method and System for Smart Internet of Things Gateway

Abstract

The present invention relates to a data access method and system for an intelligent Internet of Things gateway. The method includes: using a device feature library to perform feature matching and protocol identification on multiple sensors and terminal devices connected to the intelligent Internet of Things gateway to obtain the device protocol types; parsing the original data to obtain standardized data; performing encryption processing to obtain an encrypted security data packet and an encrypted session key; performing multi-factor transmission channel selection to obtain an optimal transmission channel combination; based on the optimal transmission channel combination, sending the encrypted security data packet to the Internet of Things platform, verifying the received data confirmation information based on a consensus algorithm, and outputting a data access status report through a data visualization interface and an AI voice assistant. The present invention can dynamically adjust the processing strategy according to device characteristics, data characteristics, and network environment, improving the flexibility and adaptability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent Internet of Things gateways, and particularly relates to a data access method and system for an intelligent Internet of Things gateway. Background Art

[0002] As a key node connecting various sensors, terminal devices and cloud platforms, the intelligent Internet of Things gateway plays an increasingly important role in data collection, processing and transmission. However, currently, there are a wide variety of Internet of Things devices with different communication protocols, which brings huge challenges to device access and data standardization. Traditional Internet of Things gateways are often inefficient in dealing with diverse devices and protocols and are difficult to meet the access requirements of large-scale heterogeneous devices.

[0003] In addition, the security and privacy protection of Internet of Things data have also received increasing attention. During data transmission, how to effectively protect sensitive information and prevent data leakage and tampering has become an urgent problem to be solved. At the same time, the complex and changeable network environment also poses challenges to the reliable transmission of data. How to achieve efficient and stable data transmission with limited network resources has become the key point for the optimization of Internet of Things systems. Summary of the Invention

[0004] The main purpose of the present invention is to provide a data access method and system for an intelligent Internet of Things gateway. The present invention can dynamically adjust the processing strategy according to device characteristics, data characteristics and network environment, improving the flexibility and adaptability of the system.

[0005] To achieve the above purpose, the present invention provides a data access method for an intelligent Internet of Things gateway, including the following steps:

[0006] Use a device feature library to perform feature matching and protocol identification on multiple sensors and terminal devices connected to the intelligent Internet of Things gateway to obtain the device protocol type;

[0007] Based on the device protocol type, activate the corresponding protocol parsing plug-in to parse the original data to obtain a parsing result, and call the edge computing microservice to input the parsing result and the original data into a semantic ontology model for data standardization processing to obtain standardized data;

[0008] Calculate the sensitivity level of the standardized data, and select an encryption algorithm according to the sensitivity level to encrypt the standardized data to obtain an encrypted security data packet and an encrypted session key;

[0009] Perform multi-dimensional evaluation on the current network environment of the intelligent Internet of Things gateway to obtain network evaluation data, and input the network evaluation data into a deep reinforcement learning model for multi-factor transmission channel selection to obtain an optimal transmission channel combination;

[0010] Based on the optimal transmission channel combination, send the encrypted security data packet to the IoT platform, verify the received data confirmation information based on the consensus algorithm, and output a data access status report through the data visualization interface and the AI voice assistant.

[0011] The present invention also provides a data access system for a smart IoT gateway, including:

[0012] An identification unit, configured to perform feature matching and protocol identification on multiple sensors and terminal devices connected to the smart IoT gateway by using a device feature library to obtain the device protocol type;

[0013] An analysis unit, configured to activate a corresponding protocol analysis plugin based on the device protocol type, analyze the original data to obtain an analysis result, and call an edge computing microservice to input the analysis result and the original data into a semantic ontology model for data standardization processing to obtain standardized data;

[0014] An encryption unit, configured to calculate the sensitivity of the standardized data, and select an encryption algorithm to encrypt the standardized data according to the sensitivity to obtain an encrypted security data packet and an encrypted session key;

[0015] A selection unit, configured to perform multi-dimensional evaluation on the current network environment of the smart IoT gateway to obtain network evaluation data, and input the network evaluation data into a deep reinforcement learning model for multi-factor transmission channel selection to obtain an optimal transmission channel combination;

[0016] An output unit, configured to send the encrypted security data packet to the IoT platform based on the optimal transmission channel combination, verify the received data confirmation information based on the consensus algorithm, and output a data access status report through the data visualization interface and the AI voice assistant.

[0017] The present invention also provides a computer device, including a memory and a processor, where a computer program is stored in the memory, and when the processor executes the computer program, the steps of the method described in any one of the above are implemented.

[0018] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in any one of the above are implemented.

[0019] In summary, the technical solution provided by the present invention realizes the automatic identification and protocol matching of various sensors and terminal devices through the device feature library and protocol recognition technology, improves the efficiency and accuracy of device access, and solves the problem of heterogeneous device access. By using the semantic ontology model and edge computing technology, the original data is intelligently parsed and standardized, realizing the unified expression of data from different sources. Through sensitivity evaluation and dynamic encryption algorithm selection, differential encryption processing is performed on the data, which not only ensures data security but also optimizes the use efficiency of encryption resources. The deep reinforcement learning model is used for multi-factor transmission channel selection, realizing the intelligent scheduling and optimized utilization of network resources, and improving the efficiency and reliability of data transmission. Through the data visualization interface and AI voice assistant, the intuitive display and voice broadcast of the data access status are realized, improving the convenience of system operation and maintenance and the user experience. The present invention has strong adaptability and can dynamically adjust the processing strategy according to device characteristics, data characteristics, and network environment, improving the flexibility and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic diagram of the steps of the data access method of the intelligent IoT gateway in an embodiment of the present invention;

[0021] Figure 2 is a block diagram of the structure of the data access system of the intelligent IoT gateway in an embodiment of the present invention;

[0022] Figure 3 is a schematic block diagram of the structure of a computer device in an embodiment of the present invention.

[0023] The implementation, functional features, and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] In order to make the object, technical solution, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0025] Referring to Figure 1 , this embodiment provides a data access method for an intelligent IoT gateway, including the following steps:

[0026] S1, using the device feature library to perform feature matching and protocol recognition on multiple sensors and terminal devices connected to the intelligent IoT gateway to obtain the device protocol type;

[0027] Among them, the communication interface of the intelligent Internet of Things gateway is monitored in real time to identify newly connected sensors and terminal devices. Record the physical connection characteristics of the sensors and terminal devices, generate a device connection information list, and the physical connection characteristics include the device's hardware identifier, MAC address, connection port, etc. Extract the protocol identifiers, data frame formats, and communication parameters of multiple pre-stored communication protocols from the device feature library, and construct a protocol feature matrix based on these characteristics. The protocol identifier describes the characteristics of a specific protocol, such as communication type, packet structure, and protocol version, while the data frame format and communication parameters include the frame header, frame tail, and related check fields in protocol communication. After constructing the protocol feature matrix, calculate the similarity between the physical connection characteristics in the device connection information list and the protocol feature matrix to obtain the similarity score between the device and each protocol. Based on the similarity score, select several candidate protocols with the highest similarity for each device to form the candidate protocol set of the device. For each communication protocol in the device candidate protocol set, perform packet capture and protocol simulation, and calculate the matching degree of each protocol by sending simulated packets to the device and analyzing the device's response. By simulating the real communication environment, detect the device's response to a specific protocol, evaluate the compatibility between the device and the protocol, and generate a protocol matching score table. The protocol matching score table contains the matching degree scores of each candidate protocol. Combining the previous similarity scores and comprehensively considering these two indicators, select the protocol with the highest number of votes for each device as the final recognition result to obtain the preliminary mapping relationship between the device and the protocol. In the preliminary device-protocol mapping relationship, for devices with a confidence level lower than the preset threshold, perform adaptive protocol learning. Extract the key characteristics of these devices during the communication process, compare the key characteristics with the known protocols in the device feature library to generate a temporary protocol. Apply the temporary protocol to the real-time data stream of the corresponding device for protocol parsing test. Calculate the parsing success rate and data integrity index through the test to evaluate the effectiveness of the temporary protocol. If the parsing success rate and data integrity index of the temporary protocol meet the preset conditions, it means that the temporary protocol can stably and accurately parse the device data and meet the access requirements. Therefore, add the temporary protocol to the device feature library and update the device-protocol mapping relationship accordingly to obtain the protocol type of the device. By continuously expanding the device feature library, the protocol recognition ability and compatibility of the system will gradually increase, enabling it to adapt to a wider range of device types and communication protocols.

[0028] S2. Activate the corresponding protocol parsing plug-in based on the device protocol type, parse the original data to obtain the parsing result, and call the edge computing microservice to input the parsing result and the original data into the semantic ontology model for data standardization processing to obtain the standardized data;

[0029] Specifically, according to the device protocol type, retrieve the protocol parsing plugin that matches it from the protocol parsing plugin library. The protocol parsing plugin is predefined with parsing rules for different protocols during design and can effectively support the protocol parsing of various devices. Load the protocol parsing plugin into the parsing engine of the intelligent Internet of Things gateway to ensure that the plugin can operate normally and provide parsing services in subsequent data processing. After the protocol parsing plugin is successfully loaded, input the original data into the plugin, and decompose, extract, and transform the original data based on the preset parsing rules to obtain the corresponding parsing results. The parsing rules include operations such as segmenting data frames, extracting specific fields, and converting data formats, so as to convert the data from the original protocol format of a specific device into a more general form. Perform data integrity verification on the parsing results, including calculating the data checksum, comparing the checksum with the preset threshold, and generating a data validity flag to identify whether there are abnormalities or damages in the data during transmission and parsing. Transmit the parsing results and the data validity flag to the edge computing microservice and trigger the edge computing task at the same time. The edge computing microservice processes the data on the local gateway, such as performing format conversion, preliminary statistical analysis, or filtering on the data, to generate preliminarily processed data. Extract the semantic ontology model related to the device protocol type from the semantic ontology library and construct a semantic mapping rule set. The semantic ontology model is a knowledge-based description of device data and device attributes, and through these models, the original data of different devices is converted into a unified semantic expression. The semantic mapping rule set is a mapping rule constructed based on the semantic ontology model, guiding how to perform semantic annotation on the preliminarily processed data and the original data. Using these rules, after annotating the data, generate data entities with semantic tags, which contain the basic content of device data and also integrate semantic information about the device and its data, making the meaning of the data clearer and facilitating subsequent reasoning and analysis. Perform ontology reasoning on the data entities with semantic tags. By using description logic algorithms to analyze and deduce the relationships between data, the description logic algorithms can reveal the implicit relationships between data and logically associate different data entities to construct a semantic association network. Based on the constructed semantic association network, perform normalization processing on the data to obtain standardized data.

[0030] Further, according to the device protocol type, construct a query statement containing protocol identifiers and keywords, and use the SPARQL query language to retrieve the semantic ontology library, and extract multiple candidate ontology models related to the device protocol type from it. SPARQL is a query language for querying ontology libraries. Through precise query conditions, it can effectively find ontology models related to the device protocol type. Conduct a structural analysis of each candidate ontology model, extract the core concepts, attributes, and relationship information of each ontology model, and construct an ontology feature vector based on this. The ontology feature vector is used to describe the relationships between concepts and their attribute features in the ontology model. Assign weights to each feature to form a weighted ontology feature vector set. The calculation of feature weights is based on their importance in the ontology structure. For example, the weights of core concepts and key relationships are higher, while the weights of secondary attributes are lower. The weighted feature vector set helps to quantify the overall features of the ontology model. Match the weighted ontology feature vector set with the knowledge graph in the corresponding field, and select the candidate ontology model with the highest similarity as the most matching semantic ontology model. The domain knowledge graph, as rich background knowledge, effectively supports the precise matching of ontology models through its structure and semantic information. By matching the similarity with the knowledge graph, filter out the ontology model most relevant to the device protocol type to ensure that the selected ontology model has high semantic relevance. Based on the selected semantic ontology model, extract the defined class, attribute, and relationship information to construct a semantic mapping rule set. This semantic mapping rule set is used to describe the mapping relationship from data fields to semantic concepts, as well as the attribute constraints and inference rules between these concepts. Parse the preliminarily processed data and the original data into key-value pairs, and according to the semantic mapping rule set, assign corresponding semantic concepts and attributes to each key-value pair to generate a preliminary semantic annotation result. The process of key-value pair parsing extracts each field in the data and matches it with the concepts and attributes in the semantic mapping rule set to assign clear semantic labels and attributes to the data fields, realizing the preliminary semanticization of the data. Conduct a context analysis on the preliminary semantic annotation result, extract the association information between adjacent data items, calculate the mutual information value between each data item, and construct a data item association matrix based on this. The mutual information value reflects the degree of association between data items, and the data item association matrix describes the connections between different data items in terms of semantics and statistics. By constructing the association matrix, mine the deep semantic relationships between data items. On this basis, based on the data item association matrix, calculate the vector representation of semantic concepts in the knowledge graph, and through the calculation of cosine similarity, select the semantic concept with the highest cosine similarity as the final semantic label. According to the obtained final semantic label, convert the preliminary semantic annotation result into the Resource Description Framework (RDF) format. The RDF format is a standard format for describing resources and their relationships. Each data item is represented as a triple of subject-predicate-object in RDF, thus constructing the association relationship between data.Assign a globally unique URI identifier to each triple to ensure the uniqueness and identifiability of data entities on a global scale, and finally obtain data entities with semantic tags.

[0031] S3, calculate the sensitivity of the standardized data, and select an encryption algorithm to encrypt the standardized data according to the sensitivity to obtain an encrypted security data packet and an encrypted session key;

[0032] It should be noted that for feature extraction of standardized data, a pre-trained word embedding model is used to map data fields into vector representations, obtaining a set of data feature vectors. The word embedding model is a model pre-trained through natural language processing technology, which converts the information in data fields into numerical vector forms with certain semantic representations, enabling the features of data fields to be effectively expressed in the vector space. The set of data feature vectors is input into the sensitivity evaluation model for sensitivity evaluation. The sensitivity evaluation model is based on a multi-layer perceptron structure. The multi-layer perceptron is a feed-forward neural network with strong feature learning ability and is suitable for processing high-dimensional numerical data. During the model training process, the cross-entropy loss function is adopted to ensure that the model can accurately distinguish data fields with different sensitivities. Through in-depth analysis of data features, the model outputs the sensitivity scores of each data field, obtaining a set of sensitivity scores. Cluster analysis is performed on the set of sensitivity scores. The data fields are divided into different sensitivity levels to form the data sensitivity classification result. Through the clustering method, data fields with similar sensitivity scores are grouped together to form several sensitivity levels, such as low sensitivity, medium sensitivity, and high sensitivity levels. According to the data sensitivity classification result, the corresponding encryption algorithm is selected from the predefined encryption algorithm library. For data fields with low sensitivity, a lightweight encryption algorithm is selected. For data fields with high sensitivity, strong encryption algorithms such as AES (Advanced Encryption Standard) are used to ensure the security of data during transmission and storage, obtaining the encryption algorithm selection scheme. Based on the encryption algorithm selection scheme, data fields with different sensitivity levels are encrypted separately, and at the same time, an encryption session key is generated, obtaining the preliminary encrypted data and the encryption session key. In this process, each data field selects a different encryption algorithm for processing according to its sensitivity level, and the encryption session key is used for verification when decrypting the data. The generated encryption session key is unique for each encrypted data segment to ensure the security and immutability of data during transmission. After the preliminary encryption is completed, the encrypted data is block-processed, and a unique identifier and version information are added to each data block to construct the encrypted data packet structure, obtaining the structured encrypted data. The data block-processing is to improve the efficiency during transmission and the flexibility of data management. The unique identifier and version information of each data block ensure that the data can be correctly recombined and decoded at the receiving end and the version situation of the data can be traced, thus ensuring the consistency of the data. On this basis, integrity protection is performed on the structured encrypted data. The HMAC (Keyed-Hash Message Authentication Code) value of each data packet is calculated and appended to the data packet, obtaining the encrypted data packet with integrity protection. The calculation of the HMAC value is to ensure that the data has not been tampered with during transmission. The receiving party verifies the HMAC value to judge the integrity of the data packet and prevent malicious attacks and data leakage.The encrypted session key is encrypted using an asymmetric encryption algorithm, and the encrypted session key is combined with the integrity-protected encrypted data packet to obtain an encrypted security data packet and an encrypted session key. Asymmetric encryption algorithms such as RSA are used for the encryption of the session key. This encryption method has the characteristics of public key encryption and private key decryption, which can ensure the security of the encrypted session key during transmission.

[0033] S4. Perform a multi-dimensional evaluation on the current network environment of the intelligent IoT gateway to obtain network evaluation data, and input the network evaluation data into a deep reinforcement learning model for multi-factor transmission channel selection to obtain an optimal transmission channel combination;

[0034] Specifically, perform parallel scans on all network interfaces of the intelligent IoT gateway, collect the status information of the interfaces through SNMP (Simple Network Management Protocol), and obtain a network interface list. The SNMP protocol is a protocol for network device management, through which important information such as the working status and traffic statistics of each network interface can be efficiently obtained. By monitoring the status of the network interfaces in real time, determine which interfaces are active and which interfaces are available. Based on the network interface list, perform network performance tests on each active interface to evaluate the quality of each network interface. Use the ICMP protocol to measure the round-trip delay of each interface, test the bandwidth of each interface through the iPerf tool, measure the packet loss rate using a UDP traffic generator, and additionally measure the signal strength and signal-to-noise ratio for wireless interfaces to obtain an original network performance data matrix containing multi-dimensional metrics. The ICMP protocol is used to test network connectivity and latency, and its round-trip delay can reflect the delay characteristics of network transmission; the iPerf tool is a commonly used bandwidth test tool that measures the actual bandwidth of each network interface by generating TCP or UDP traffic; the UDP traffic generator is used to measure the packet loss rate, reflecting the stability of the network interface under load. The signal strength and signal-to-noise ratio of wireless interfaces are important indicators for measuring the quality of wireless networks. Through these test data, evaluate the performance of each network interface. Generate a network interface evaluation vector based on the original network performance data matrix. By weighted fusion of multiple performance metrics, obtain the comprehensive score of each interface. Based on the comprehensive score, sort the network interfaces in descending order, and select the top N interfaces as the candidate transmission channel set. Perform time series fusion on the network performance data of the candidate transmission channel set and historical transmission data to construct a state space matrix. Each row of the state space matrix represents the network state at a time point, and the columns include network performance metrics such as bandwidth utilization and delay jitter. Through time series fusion, make full use of the information in historical data, capture the dynamic change characteristics of network performance, and describe the current network state. Represent the current network state as input into a deep reinforcement learning model. This deep reinforcement learning model adopts a double DQN structure. The double DQN structure is an improved Q-learning algorithm that reduces the problem of overestimation of Q values through two sets of independent Q networks, thereby improving the stability of the model and the accuracy of decision-making. In the forward propagation process of the model, calculate the Q values of each possible transmission channel combination to obtain a transmission channel evaluation matrix containing the Q values of all possible combinations. The Q value represents the quality of each transmission channel combination in the current network state. The higher the Q value, the better the performance of the transmission channel combination and the more suitable it is for the current data transmission requirements. Based on the transmission channel evaluation matrix, calculate the probability of each transmission channel combination being selected. By calculating the probability distribution of all possible channel combinations, quantify the priority of each combination in the current situation, and select the combination with the highest probability as the optimal transmission channel combination.

[0035] S5. Based on the optimal transmission channel combination, send the encrypted security data packets to the IoT platform, verify the received data confirmation information based on the consensus algorithm, and output the data access status report through the data visualization interface and the AI voice assistant.

[0036] Among them, according to the optimal transmission channel combination, the encrypted security data packets are fragmented, splitting large data packets into multiple small data packets. Each data fragment is attached with a unique sequence number and checksum to ensure the order and integrity of the fragments, obtaining a set of data fragments. The purpose of fragmentation is to improve the flexibility and efficiency of data transmission, enabling each fragment to be independently transmitted through different transmission paths, effectively utilizing the available bandwidth and resources of the transmission channels. Based on the set of data fragments, the optimal transmission path for each fragment is calculated. Combining the optimal transmission channel combination, the selection of the transmission path is performed for each data fragment, and different fragments are assigned to different transmission channels to form a fragmentation transmission scheme, thereby ensuring that the transmission processes of the various fragments do not interfere with each other, maximizing the utilization of the bandwidth and resources of the transmission channels, and enhancing the overall data transmission performance and stability. Through a dynamic fragmentation allocation strategy, the transmission paths of the fragments are flexibly adjusted according to changes in the network environment, thus achieving efficient transmission in a complex network environment. According to the fragmentation transmission scheme, the data fragments are simultaneously sent to the IoT platform using multi-threaded parallel transmission technology. During the parallel transmission process, in order to ensure the reliability of the data, a timeout retransmission mechanism is initiated, that is, whenever it is detected that a certain data fragment has not been successfully delivered within the predetermined time, a retransmission operation is triggered to ensure that the data can ultimately reach the target platform. At the same time, the sending status of each data fragment is recorded, including information such as success, failure, and retransmission times, forming a data transmission log. When the IoT platform successfully receives the data, a data confirmation message is returned. This data confirmation message contains the sequence number of the successfully received data fragment and a digital signature, which is used to ensure the authenticity and integrity of the data. The digital signature is verified using an asymmetric encryption algorithm to ensure that the data is indeed sent by the IoT platform and has not been tampered with during the transmission process. In this way, the validity of the data is initially verified to ensure the security of the data during transmission. The initial verification result is input into a Byzantine fault-tolerant consensus algorithm model. The Byzantine fault-tolerant consensus algorithm is an algorithm used to solve the consistency problem among nodes in a distributed system, verifying the validity of data through multiple rounds of voting among multiple distributed nodes. When more than 2 / 3 of the nodes reach a consensus on a certain data fragment, it is considered that the data fragment has been correctly received, and thus the confirmation result of data reception is output. Based on the data reception confirmation result, the success rate, average delay, and throughput of data transmission are calculated, and a data access status report is constructed. The success rate of data transmission reflects the proportion of data packets that successfully reach the IoT platform during the transmission process, while the average delay is used to measure the average time required for the data to be confirmed from the time of sending, and the throughput represents the amount of data successfully transmitted per unit time. Through the comprehensive calculation of these metrics, the data access performance of the intelligent IoT gateway is comprehensively evaluated, and a data access status report is generated. Through the data visualization interface, the content in the data access status report is presented in the form of an interactive chart.The AI voice assistant uses text-to-speech (TTS) technology to convert the data access status report into voice output, enabling users to obtain the status information of data transmission in a voice manner.

[0037] In one example, the device feature library is used to perform feature matching and protocol identification on multiple sensors and terminal devices connected to the intelligent Internet of Things gateway to obtain the device protocol type, including: real-time monitoring of the communication interface of the intelligent Internet of Things gateway, identifying newly connected sensors and terminal devices, and recording the physical connection features of the sensors and terminal devices to obtain a device connection information list; extracting the protocol identifiers, data frame formats, and communication parameters of multiple pre-stored communication protocols from the device feature library to construct a protocol feature matrix; calculating the similarity between the physical connection features in the device connection information list and the protocol feature matrix to obtain a device-protocol similarity score, and based on the device-protocol similarity score, selecting the top K candidate protocols with the highest similarity for each device to obtain a device candidate protocol set; for each communication protocol in the device candidate protocol set, performing packet capture and protocol simulation, calculating the protocol matching degree by sending simulated packets to the device and analyzing the response to obtain a protocol matching score table; according to the protocol matching score table, comprehensively considering the similarity score and the protocol matching degree, selecting the protocol with the highest number of votes as the identification result of the device to obtain a preliminary device-protocol mapping relationship; for devices with a confidence level lower than the preset threshold in the preliminary device-protocol mapping relationship, performing adaptive protocol learning and extracting key features, comparing the key features with the known protocol library to generate a temporary protocol; applying the temporary protocol to the real-time data stream of the corresponding device for protocol parsing test, calculating the parsing success rate and data integrity index, if the parsing success rate and data integrity index meet the preset conditions, adding the temporary protocol to the device feature library and updating the device-protocol mapping relationship to obtain the device protocol type.

[0038] In this example, the communication interface of the intelligent Internet of Things gateway is monitored in real time by means of periodic polling or interrupt triggering. When a new device is connected, the system can quickly detect the connection of the device and record the physical connection features of the device, including information such as the MAC address, port number, and device type of the device, to form a device connection information list. Extract the protocol identifiers, data frame formats, and communication parameters of multiple pre-stored communication protocols from the device feature library and construct a protocol feature matrix. The protocol feature matrix is used to describe the features of each protocol, and the protocol feature matrix is expressed as:

[0039] P = {p 1 , p 2 , …, p m};

[0040] where P represents the protocol feature matrix, p iRepresents the feature vector of protocol i, including protocol identifier, data frame format, communication parameters, etc. Calculate the similarity between the physical connection features in the device connection information list and the protocol feature matrix to obtain the similarity score between the device and the protocol. The similarity is calculated using the cosine similarity method, and the calculation formula is as follows:

[0041]

[0042] Among them, S ij Represents the similarity score between device i and protocol j, V i Represents the physical connection feature vector of device i, p j Represents the feature vector of protocol j, and the symbol · represents the dot product of two vectors, ||V i || and ||p j|| respectively represent the norms of the device feature vector and the protocol feature vector. Based on the similarity scores, the K candidate protocols with the highest similarity for each device are selected to obtain the candidate protocol set of the device. For example, suppose there is a newly connected temperature sensor, and the system detects that its physical features include a specific MAC address, the connected port number, and the type of the initial handshake packet, etc. Calculate the similarity between these features and various protocols in the protocol feature library. Suppose high similarity scores are obtained for several protocol types, such as the Modbus protocol, the MQTT protocol, etc., then these K candidate protocols are used as the protocol types supported by the device. To determine the specific communication protocol, packet capture and protocol simulation are performed for each communication protocol in the candidate protocol set. By sending simulated packets to the device and analyzing the device's response to these packets, the protocol matching degree is calculated. By capturing the communication packets between the device and the IoT gateway, simulating the standard operations of each candidate protocol, and observing whether the device can correctly respond, a protocol matching score table is obtained. Suppose the Modbus protocol is simulated and a specific read register request is sent. If the response returned by the device conforms to the standard data frame format of the Modbus protocol, it indicates that the device is very likely to support the Modbus protocol. According to the protocol matching score table, comprehensively considering the similarity scores and protocol matching degrees between the device and each protocol, the protocol with the highest number of votes is selected as the final identification result of the device, and a preliminary device-protocol mapping relationship is obtained. For devices with a confidence level lower than the preset threshold, adaptive protocol learning is performed. The process of adaptive protocol learning includes in-depth analysis of the device's data stream and extraction of key communication features. These key features are compared with the known protocol library. If it is found that some features cannot be matched to the known protocols, a temporary protocol is generated to describe these new features. For example, for some new types of custom devices whose communication protocols are not widely standardized, by learning their data interaction behaviors and extracting the feature fields in the frame format, a temporary protocol is generated. Apply the generated temporary protocol to the device's real-time data stream for protocol parsing testing to verify the effectiveness of the protocol. Calculate the success rate of temporary protocol parsing and the data integrity index. If both the parsing success rate and the data integrity index meet the preset conditions, it indicates that the temporary protocol can correctly describe the device's communication behavior. Add the temporary protocol to the device feature library and update the device-protocol mapping relationship to finally obtain the protocol type of the device.

[0043] In one example, the corresponding protocol parsing plugin is activated based on the device protocol type to parse the raw data, obtaining a parsing result, and the edge computing microservice is called to input the parsing result and the raw data into the semantic ontology model for data standardization processing, obtaining standardized data, including: retrieving a matching protocol parsing plugin from the protocol parsing plugin library according to the device protocol type, and loading the protocol parsing plugin into the parsing engine of the intelligent Internet of Things gateway to obtain the protocol parsing plugin; inputting the raw data into the protocol parsing plugin, decomposing, extracting, and converting the raw data using preset parsing rules to obtain a parsing result, and performing data integrity verification on the parsing result, calculating a data checksum, and comparing it with a preset threshold to obtain a data validity flag; transmitting the parsing result and the data validity flag to the edge computing microservice and triggering an edge computing task to obtain preliminarily processed data; extracting the semantic ontology model related to the device protocol type from the semantic ontology library, constructing a semantic mapping rule set, and performing semantic annotation on the preliminarily processed data and the raw data according to the semantic mapping rule set to generate a data entity with semantic tags; performing ontology reasoning on the data entity with semantic tags, analyzing and deducing data relationships using description logic algorithms to obtain a semantic association network, and performing normalization processing based on the semantic association network to obtain standardized data.

[0044] In this example, according to the device protocol type, a query is executed in the protocol parsing plugin library to find the parsing plugin corresponding to the protocol used by the device. Suppose the protocol type of a certain device is the Modbus protocol. The Modbus protocol parsing plugin is extracted from the plugin library and loaded into the parsing engine of the intelligent Internet of Things gateway. After loading, the raw data is input into the protocol parsing plugin, and the raw data is decomposed, extracted, and converted using the preset parsing rules in the plugin to obtain a structured parsing result. The parsing rules in the protocol parsing plugin are defined as a specific data frame structure and a method for extracting fields. For example, the data frame of the Modbus protocol usually consists of parts such as function code, starting address, data length, and data value. The parsing plugin will extract the raw data in segments according to these rules, decompose each field, and perform corresponding data type conversions to obtain the parsed result. Suppose the data sent by the device is a read register request. The parsing plugin will extract the function code, address, and data value respectively, and convert these fields into structured data for easy processing. Perform integrity verification on the parsing result to ensure that the data has not been tampered with during transmission and parsing. The integrity verification process is completed by calculating the checksum of the data. The calculation formula for the checksum is:

[0045]

[0046] where C represents the calculated data checksum, D iRepresents the parsed data fields, where n is the total number of data fields and M is a preset constant used for modulo operation. A checksum value is obtained through this formula, and then this value is compared with a preset threshold to determine the validity of the data. If the calculated checksum value matches the preset check value, the data is marked as valid; otherwise, the data has been damaged or tampered with during transmission. The parsed result and the data validity flag are transmitted to the edge computing microservice to trigger corresponding edge computing tasks. The edge computing microservice can perform preliminary calculations and processing on the data, reducing the processing pressure on the central system and improving the efficiency of data processing. After completing the edge computing tasks, semantic annotation is performed on the preliminarily processed data to improve the understandability and operability of the data in the Internet of Things platform. A semantic ontology model related to the device protocol type is extracted from the semantic ontology library to construct a semantic mapping rule set. The semantic ontology model is a way of knowledge representation that defines concepts and their relationships in a specific domain. For example, the ontology model corresponding to the Modbus protocol contains concepts such as "function code" and "register address". Based on these concepts, a semantic mapping rule set is constructed, which defines the mapping relationship between data fields and semantic concepts. The preliminarily processed data and the original data are semantically annotated according to the semantic mapping rule set to generate data entities with semantic tags. Ontology reasoning is performed on the data entities with semantic tags. By analyzing and deriving the relationships between the data, the hidden associations in the data are revealed. The reasoning process relies on the description logic algorithm. Description logic is a logical tool for knowledge representation and reasoning that can effectively handle the hierarchical structure and attribute relationships between concepts. Suppose there is data from a temperature sensor. The reasoning reveals the potential association between the data "high temperature" and "device abnormal alarm", and constructs a semantic association network. The formula for description logic reasoning is as follows:

[0047] R = f(C 1 , C 2 , …, C m );

[0048] where R represents the inferred relationship, C 1 , C 2 , …, C m represents the set of concepts participating in the reasoning, f is the reasoning function, and the relationships between concepts are revealed through the reasoning function to form a semantic association network. Based on the semantic association network, the data is normalized to obtain standardized data. The data from different devices and different protocols is converted into a unified format so that they can be uniformly processed and analyzed in the Internet of Things platform.

[0049] In one example, a semantic ontology model related to the device protocol type is extracted from the semantic ontology library, a semantic mapping rule set is constructed, and the preliminarily processed data and the original data are semantically annotated according to the semantic mapping rule set to generate data entities with semantic tags, including: constructing a query statement according to the device protocol type, the query statement including a protocol identifier and keywords, retrieving the semantic ontology library using the SPARQL query language, extracting the ontology model related to the device protocol type, and obtaining multiple candidate ontology models; performing a structural analysis on each candidate ontology model, extracting core concepts, attributes, and relationships, constructing an ontology feature vector, and calculating feature weights to obtain a weighted ontology feature vector set; performing a similarity matching between the weighted ontology feature vector set and the corresponding domain knowledge graph, and selecting the candidate ontology model with the highest similarity as the most matching semantic ontology model; based on the semantic ontology model, extracting class, attribute, and relationship definitions, and constructing a semantic mapping rule set, the semantic mapping rule set including the mapping relationship from data fields to semantic concepts, attribute constraints, and inference rules; parsing the preliminarily processed data and the original data into key-value pair forms, and according to the semantic mapping rule set, assigning corresponding semantic concepts and attributes to each key-value pair to generate a preliminary semantic annotation result; performing a context analysis on the preliminary semantic annotation result, extracting the association information between adjacent data items, calculating the mutual information value, constructing a data item association matrix, and at the same time, based on the data item association matrix, calculating the vector representation of the semantic concept in the knowledge graph, and selecting the semantic concept with the highest cosine similarity as the final semantic tag; converting the preliminary semantic annotation result into the Resource Description Framework format according to the final semantic tag, each data item being represented as a triple of subject-predicate-object, and assigning a globally unique URI identifier to each triple to obtain data entities with semantic tags.

[0050] In this example, a query statement is constructed according to the device protocol type. The query statement contains a protocol identifier and keywords, which are used to describe the semantic features related to this protocol. For example, for a device using the Modbus protocol, the query statement may contain the protocol identifier "Modbus" and keywords such as "register" and "function code". Through these keywords, the semantic requirements related to the device protocol type are described. The SPARQL query language is used to retrieve the semantic ontology library. SPARQL is a query language specifically designed for querying semantic networks and ontology libraries, similar to the role of SQL in relational databases. Through the constructed query statement, multiple candidate ontology models related to the device protocol type are extracted from the semantic ontology library. For example, during the query process of the Modbus protocol, the SPARQL query statement matches relevant ontology models such as "Modbus communication model" and "industrial protocol model", obtaining a set of candidate ontology models. Structural analysis is performed on each candidate ontology model, and core concepts, attributes, and relationships are extracted from it to construct an ontology feature vector. The feature vector is used to quantitatively represent the structure and semantic features of the ontology model. The feature vector is represented as:

[0051] F i ={c 1 ,c 2 ,…,c n ,r 1 ,r 2 ,…,r m};

[0052] Among them, F i represents the feature vector of candidate ontology model i, c 1 ,c 2 ,…,c n represent the core concepts in the ontology model, and r 1 ,r 2 ,…,r m represent the relationships between these concepts. Through in-depth analysis of the ontology model structure, key concepts and attribute relationships in the ontology model are extracted to form a complete feature description. Feature weights are calculated for each feature, thereby obtaining a weighted ontology feature vector set. The calculation of feature weights is based on the occurrence frequency and importance of concepts and relationships in the ontology model. For example, for core concepts that appear frequently in the model and are of great significance for describing the model, higher weights are assigned. The weighted ontology feature vector set is represented as:

[0053] W i ={w 1 ×c 1 ,w 2 ×c 2 ,…,w n ×c n ,wn+1 ×r 1 ,…,w n+m ×r m};

[0054] Among them, W i is the weighted feature vector set of the candidate ontology model i, and w j represents the weight of feature c j or r j . The weighted ontology feature vector set is matched with the corresponding domain knowledge graph. The knowledge graph contains various concepts and their association relationships in the domain. By matching the weighted feature vector with the concept vector in the knowledge graph, the semantic ontology model closest to the device protocol type is found. The similarity matching adopts the cosine similarity method, and the calculation formula is as follows:

[0055]

[0056] Among them, Similarity represents the similarity between the weighted feature vector W i and the concept vector K in the knowledge graph. The symbol · represents the dot product of two vectors. ||W i || and ||K|| represent the norms of the weighted feature vector and the knowledge graph vector respectively. Through similarity matching, the candidate ontology model with the highest similarity is selected as the most matching semantic ontology model. Based on the most matching semantic ontology model, classes, attributes, and relationship definitions are extracted to construct a semantic mapping rule set. The semantic mapping rule set is used to describe the mapping relationship between device data fields and semantic concepts, including attribute constraints and inference rules. For example, in the semantic ontology model of the Modbus protocol, "register address" is mapped to the semantic concept of "address", and "function code" is mapped to "operation type", etc. Through the semantic mapping rule set, the device data is associated with specific semantic concepts. The preliminarily processed data and the original data are parsed into key-value pair forms. According to the semantic mapping rule set, the corresponding semantic concepts and attributes are assigned to each key-value pair to generate a preliminary semantic annotation result. For example, for the temperature data collected from a Modbus device, after semantic mapping, the "temperature value" field is mapped to the semantic concept of "ambient temperature" to generate structured data containing semantic labels. Context analysis is performed on the preliminary semantic annotation result, and the association information between adjacent data items is extracted. The mutual information value between every two data items is calculated to construct a data item association matrix. The mutual information value is used to measure the correlation between data items, and the calculation formula of the mutual information value is:

[0057]

[0058] Among them, I(X; Y) represents the mutual information value between data items X and Y, p(x, y) represents the probability that X and Y take values x and y simultaneously, and p(x) and p(y) respectively represent the marginal probabilities of data items X and Y. By calculating the mutual information value, the correlation between data items is quantified, and a correlation matrix of data items is constructed. Based on the correlation matrix of data items, the vector representation of semantic concepts in the knowledge graph is calculated, and through cosine similarity calculation, the semantic concept with the highest similarity is selected as the final semantic label. According to the final semantic label, the preliminary semantic annotation result is converted into the Resource Description Framework (RDF) format. RDF is a standardized format for describing resources and their relationships, where each data item is represented as a triple of subject-predicate-object. For example, the data of a certain temperature sensor is represented as "sensor X" (subject) - "measures" (predicate) - "temperature value 30 degrees" (object). At the same time, a globally unique URI identifier is assigned to each triple to ensure that these data have unique identity recognition in a distributed system, and a data entity with semantic labels is obtained.

[0059] In one example, the sensitivity of the standardized data is calculated, and an encryption algorithm is selected according to the sensitivity to encrypt the standardized data, obtaining an encrypted security data packet and an encrypted session key, including: extracting features from the standardized data, using a pre-trained word embedding model to map data fields into vector representations to obtain a data feature vector set; inputting the data feature vector set into a sensitivity evaluation model, which is trained based on a multi-layer perceptron structure using a cross-entropy loss function, and outputs the sensitivity scores of each data field to obtain a sensitivity score set; performing clustering analysis on the sensitivity score set, dividing the data fields into different sensitivity levels to obtain a data sensitivity classification result, and according to the data sensitivity classification result, selecting the corresponding encryption algorithm from a predefined encryption algorithm library, using a lightweight encryption algorithm for low-sensitivity data and a strong encryption algorithm for high-sensitivity data to obtain an encryption algorithm selection scheme; based on the encryption algorithm selection scheme, encrypting data fields of different sensitivity levels respectively, and generating an encrypted session key at the same time, obtaining preliminary encrypted data and an encrypted session key; performing block processing on the preliminary encrypted data, adding a unique identifier and version information to each data block to construct an encrypted data packet structure, obtaining structured encrypted data, and performing integrity protection on the structured encrypted data, calculating the HMAC value and attaching it to the data packet to obtain an integrity-protected encrypted data packet; encrypting the encrypted session key using an asymmetric encryption algorithm, and combining the encrypted session key with the integrity-protected encrypted data packet to obtain an encrypted security data packet and an encrypted session key.

[0060] In this example, each field in the standardized data is represented as a semantically related feature vector. Word embedding models (such as Word2Vec, GloVe, etc.) map data fields to a vector space through a pre-trained model, such that fields with similar meanings or semantics are closer in the vector space. For example, fields such as device names, data types, and units are mapped to vectors through the word embedding model to obtain a set of data feature vectors. Through this process, each field in the standardized data is converted into a vector representation, and the vector representation is:

[0061] V i ={v 1 ,v 2 ,…,v n};

[0062] where V i represents the vector representation of the i-th data field, and v j represents the value of field i in the j-th dimension of the word embedding vector space. The set of data feature vectors is input into the sensitivity evaluation model. The sensitivity evaluation model adopts a multi-layer perceptron structure, a type of feed-forward neural network composed of multiple fully connected layers, which is used to process high-dimensional feature vectors. The sensitivity evaluation model performs sensitivity analysis on data fields and outputs the sensitivity scores of each data field. During the training process, the cross-entropy loss function is used to measure the difference between the model's output and the true labels, thereby guiding the model to update its parameters. The calculation formula of the cross-entropy loss function is:

[0063]

[0064] where L represents the cross-entropy loss, y i is the true label, is the predicted value of the model, and N represents the number of data samples. By minimizing the cross-entropy loss, the model can gradually learn how to distinguish data fields with different sensitivities. After training, the model outputs a sensitivity score for each input data field, forming a sensitivity score set. The higher the sensitivity score, the more important the data field is in terms of data security and the more stringent protection is required. Cluster analysis is performed on the sensitivity score set to divide the data fields into different sensitivity levels. Algorithms such as K-means clustering are used in cluster analysis to group data fields with similar sensitivity scores into the same category, forming classification results with different levels such as high sensitivity and low sensitivity. For example, temperature data is classified as low sensitivity, while user authentication information is classified as high sensitivity. The clustering results are used to guide the selection of data encryption strategies, thereby obtaining the data sensitivity classification results. According to the data sensitivity classification results, the corresponding encryption algorithms are selected from the predefined encryption algorithm library. For low-sensitivity data fields, lightweight encryption algorithms such as RC4 or AES-128 are selected. These algorithms have high computational efficiency and are suitable for protecting data with less strict security requirements. For high-sensitivity data fields, strong encryption algorithms such as AES-256 or RSA are selected to ensure the security of the data and prevent it from being stolen or tampered with during transmission and storage. An encryption algorithm selection scheme is formulated based on the sensitivity levels to effectively balance security and computational efficiency. Based on the encryption algorithm selection scheme, data fields with different sensitivity levels are encrypted separately, and an encryption session key is generated for each group of encryption to obtain the preliminary encrypted data and the encryption session key. The encryption session key is used to decrypt the data during data transmission to ensure that only legitimate recipients can decrypt and use the data. The preliminary encrypted data is block-processed, and a unique identifier and version information are attached to each data block to construct the encrypted data packet structure. The purpose of block-processing is to improve the flexibility and concurrency of transmission. Each data block can be transmitted independently, thereby improving the utilization rate of network resources and the transmission efficiency of the data. The identifier is used to mark the order of the data blocks in the data packet, and the version information is used to record the version of the data blocks to facilitate the recombination and management of the data at the receiving end. In this way, structured encrypted data is obtained. To ensure the integrity of the data during transmission, integrity protection is performed on the structured encrypted data. Integrity protection is achieved by calculating the HMAC (key-based message authentication code) value. The calculation formula of HMAC is:

[0065] H = Hash(K ⊕ opad ∥ Hash(K ⊕ ipad ∥ M));

[0066] Among them, H represents the calculated HMAC value, K is the encryption key, opad and ipad are the external and internal padding constants respectively, ∥ represents the string concatenation operation, and M is the message content. By appending the HMAC value, it is ensured that the receiving party can verify whether the data has been tampered with during transmission. If the data is tampered with, the calculated HMAC value will not match, thus enabling the detection of data integrity issues. The asymmetric encryption algorithm is used to encrypt the encryption session key. Asymmetric encryption algorithms such as RSA use public key encryption and private key decryption to ensure that the session key cannot be illegally intercepted and decrypted during transmission. By combining the encrypted session key with the integrity-protected encrypted data packet, an encrypted security data packet and an encrypted session key are obtained.

[0067] In one example, the current network environment of the intelligent IoT gateway is evaluated multi-dimensionally to obtain network evaluation data, and the network evaluation data is input into a deep reinforcement learning model for multi-factor transmission channel selection to obtain an optimal transmission channel combination, including: performing parallel scans on all network interfaces of the intelligent IoT gateway, collecting interface status information through the SNMP protocol to obtain a network interface list; based on the network interface list, performing network performance tests on each active interface, measuring the round-trip delay using the ICMP protocol, testing the bandwidth through the iPerf tool, measuring the packet loss rate using a UDP traffic generator, and additionally measuring the signal strength and signal-to-noise ratio for wireless interfaces to obtain an original network performance data matrix containing multi-dimensional metrics; generating a network interface evaluation vector according to the original network performance data matrix, and sorting the network interfaces in descending order according to the network interface evaluation vector, and selecting the top N interfaces as the candidate transmission channel set; performing time series fusion on the network performance data of the candidate transmission channel set and historical transmission data to construct a state space matrix, where each row represents the network state at a time point, and the columns include bandwidth utilization and delay jitter metrics, to obtain the current network state representation; inputting the current network state representation into a deep reinforcement learning model, which uses a double DQN structure, and calculating the Q value of each possible transmission channel combination through forward propagation to obtain a transmission channel evaluation matrix containing the Q values of all possible combinations; based on the transmission channel evaluation matrix, calculating the probability of each transmission channel combination being selected, and selecting the combination with the highest selection probability as the optimal transmission channel combination.

[0068] In this example, the status information of network interfaces is collected through SNMP (Simple Network Management Protocol) to obtain the availability and health status of the interfaces. SNMP is a network management protocol that performs parallel scans on each network interface of the IoT gateway device to identify which interfaces are active and the basic configuration parameters of the interfaces, such as speed, status (enabled or disabled), etc. Through this information, a list of network interfaces of the current IoT gateway is obtained. Based on the obtained list of network interfaces, network performance tests are performed on each active network interface to evaluate their actual performance. The round-trip delay (RTT) of each interface is measured using the ICMP protocol. ICMP is a commonly used network tool that sends requests to the network interface through the Ping command and measures the response time to obtain the round-trip delay. The formula for calculating the round-trip delay is:

[0069] RTT = T response -T request ;

[0070] where RTT represents the round-trip delay, T response represents the time when the response is received, and T request represents the time when the request is sent. RTT reflects the delay of the network interface when transmitting data and is an important indicator for evaluating the interface performance. The bandwidth of each network interface is tested using the iPerf tool. iPerf is a tool used to measure the maximum TCP or UDP bandwidth, which can generate continuous data streams and measure the maximum throughput capacity of the network. The bandwidth test reflects the performance of the network interface under high load and helps to determine which interface is suitable for transmitting a large amount of data. The packet loss rate is measured using a UDP traffic generator. By simulating the sending of high-frequency UDP packets and counting the number of lost packets, the packet loss rate is calculated:

[0071]

[0072] where Packet Loss Rate represents the packet loss rate, N lost represents the number of lost packets, and N sent represents the total number of packets sent. The packet loss rate is a key indicator reflecting the stability of the network interface. A low packet loss rate indicates a high reliability of the network when transmitting data under high load. For wireless interfaces, the signal strength and signal-to-noise ratio are measured. The signal strength (RSSI) represents the received power of the wireless signal, and the signal-to-noise ratio (SNR) is the ratio of the signal to the noise. Through testing, an original network performance data matrix containing multi-dimensional indicators is obtained, which is used to describe the multi-faceted performance of each network interface. Based on the original network performance data matrix, the performance data is processed to generate an evaluation vector of the network interface. The network interface evaluation vector comprehensively considers performance indicators such as RTT, bandwidth, packet loss rate, RSS, and SNR of each interface and is used to represent the overall performance level of the network interface. The evaluation vector is expressed as:

[0073] E i ={rtt i ,bw i ,plr i ,rssi i ,snr i};

[0074] Among them, E i represents the evaluation vector of the i-th interface, rtt i is the round-trip delay, bw i is the bandwidth, plr i is the packet loss rate, rssi i is the signal strength, snr i is the signal-to-noise ratio. Based on the evaluation vector, the network interfaces are sorted in descending order, and the top N interfaces are selected as the candidate transmission channel set to ensure that the selected channels have the best transmission performance under the current conditions. After determining the candidate transmission channel set, time series fusion is performed in combination with historical network performance data to construct the current network state representation. By performing time series analysis on the real-time performance data and historical performance data of the candidate transmission channel set, a state space matrix is constructed. Each row of the state space matrix represents the network state at a time point, and the columns include metrics such as bandwidth utilization, latency, and jitter. The state space matrix can be expressed as:

[0075] S t ={bu t ,rtt t ,j t};

[0076] Among them, S t represents the network state at time point t, bu t is the bandwidth utilization, rtt t is the current round-trip delay, j t is the network jitter. Through the method of time series fusion, the dynamic change characteristics of network performance over time are captured to describe the current network state. The current network state representation is input into a deep reinforcement learning model to select the optimal transmission channel combination. This deep reinforcement learning model uses a double DQN structure to reduce the overestimation problem of Q-values through two sets of independent Q-networks and improve the stability of the model. In the forward propagation process of the model, by evaluating the current state, the Q-values of each possible transmission channel combination are calculated to obtain a transmission channel evaluation matrix containing the Q-values of all possible combinations. The calculation formula of the Q-value is:

[0077]

[0078] Among them, Q(s t ,a) represents the Q-value in state st The Q-value of the selected action a, r t is the current immediate reward, γ is the discount factor, which is used to measure the importance of future rewards, and max a′ Q(s t+1 , a′) represents the maximum Q-value in the next state s t+1 In this way, the performance of each transmission channel combination in the current network state is evaluated, and a transmission channel evaluation matrix containing the Q-values of all combinations is output. Based on the transmission channel evaluation matrix, the probability of each transmission channel combination being selected is calculated. By converting the Q-value into a selection probability, the priority of each channel combination is quantified. The transmission channel combination with the highest selection probability is selected as the optimal transmission channel combination, so as to ensure that data transmission can be carried out in the most efficient and stable manner under the current network conditions.

[0079] Among them, the current network state representation is input into the deep reinforcement learning model. This deep reinforcement learning model uses a double DQN structure. By forward propagation, the Q-values of each possible transmission channel combination are calculated, and a transmission channel evaluation matrix containing the Q-values of all possible combinations is obtained, including: normalizing the current network state representation, using the Z-score normalization method to convert the data of each dimension into a standard normal distribution with a mean of 0 and a standard deviation of 1, to obtain a normalized network state vector; inputting the normalized network state vector into the main network, which is composed of a multi-layer fully connected neural network and uses the ReLU activation function for non-linear transformation to obtain the output features of the main network; inputting the output features of the main network into the advantage stream network and the value stream network, where the advantage stream network outputs the advantage value of each action, and the value stream network outputs the state value, which is realized through two independent fully connected layers, to obtain the advantage value vector and the state value scalar; based on the advantage value vector and the state value scalar, using the Q-value calculation formula of Dueling DQN, that is, Q(s, a) = V(s) + (A(s, a) - mean(A(s, a))), to calculate the Q-values of each possible transmission channel combination, and obtain the main network Q-value vector; inputting the normalized network state vector into the target network, the structure of the target network is the same as that of the main network, but the parameter update frequency is lower, and the target network Q-value vector is obtained through the same forward propagation process; using the ε-greedy strategy to select actions, with a probability of 1 - ε, select the action with the largest Q-value, and with a probability of ε, randomly select actions, where the ε value gradually decays during the training process, to obtain the selected transmission channel combination; combining the main network Q-value vector and the target network Q-value vector to construct a transmission channel evaluation matrix containing the Q-values of all possible transmission channel combinations, each row in the matrix represents a possible transmission channel combination, and each column represents the corresponding Q-value; normalizing the transmission channel evaluation matrix, using the Softmax function to convert the Q-value into a selection probability, and obtaining the final transmission channel selection probability distribution.

[0080] In one example, based on the optimal transmission channel combination, encrypted security data packets are sent to the IoT platform. The received data confirmation information is verified based on a consensus algorithm, and a data access status report is output through a data visualization interface and an AI voice assistant, including: performing fragmentation processing on the encrypted security data packets according to the optimal transmission channel combination, splitting large data packets into multiple small data packets, adding a sequence number and a checksum to each fragment to obtain a data fragment set; calculating the optimal transmission path for each fragment based on the data fragment set, allocating the fragments to different transmission channels to obtain a fragment transmission scheme; sending the data fragments to the IoT platform simultaneously through multi-threaded parallel transmission technology according to the fragment transmission scheme, and starting a timeout retransmission mechanism to record the sending status of each fragment to obtain a data transmission log; receiving the data confirmation information returned by the IoT platform, where the data confirmation information includes the sequence numbers of the successfully received data fragments and digital signatures, verifying the validity of the digital signatures using an asymmetric encryption algorithm to obtain a preliminary verification result; inputting the preliminary verification result into a consensus algorithm model based on Byzantine fault tolerance, and the consensus algorithm model based on Byzantine fault tolerance conducts multiple rounds of voting in a distributed node network. When more than two-thirds of the nodes reach an agreement, a data reception confirmation result is output; based on the data reception confirmation result, calculating the success rate, average latency, and throughput of data transmission, constructing a data access status report, generating an interactive chart through a data visualization interface, and converting the data access status report into voice output through an AI voice assistant using text-to-speech technology.

[0081] In this example, large data packets are split into multiple small data packets, enabling parallel transmission of data across different transmission channels, thereby improving the efficiency and flexibility of transmission. In the fragmentation process, each fragment is appended with a sequence number and a checksum to ensure correct data recombination at the receiving end. The sequence number is used to identify the order of the data fragments, ensuring that the fragments can be recombined in the correct order, while the checksum is used to ensure data integrity. The calculation of the checksum uses a simple modulo operation as follows:

[0082]

[0083] where C i represents the checksum of the i-th data fragment, and d ijDenote the j-th byte in data shard i, n is the number of bytes in the shard, and M is a constant used for modulo operation. By calculating the checksum, it is ensured that the data is not tampered with during transmission. After the sharding process is completed, based on the set of data shards, the optimal transmission path is calculated for each shard. The selection of the transmission path for each shard depends on the real-time state of the network, including multiple metrics such as bandwidth utilization, latency, packet loss rate, etc. By evaluating these metrics, different transmission channels are assigned to each shard to obtain a shard transmission scheme. Make full use of various transmission resources in the network, reduce the load on a single transmission channel, and improve the overall transmission efficiency and reliability of the data. According to the shard transmission scheme, the data shards are sent to the IoT platform simultaneously through multi-threaded parallel transmission technology. Multi-threaded parallel transmission is an efficient network transmission technology that enables multiple shards to be transmitted simultaneously in different channels, thereby improving the transmission speed and stability. At the same time, in order to ensure the reliable transmission of data, a timeout retransmission mechanism is started. The core of the timeout retransmission mechanism is that when the acknowledgment of a certain shard is not received within a certain time, the shard will be resent to ensure that all shards can finally reach the IoT platform successfully. The sending status of each shard, including information such as successful sending and the number of timeout retransmissions, will be recorded to generate a data transmission log. After the data shards are successfully transmitted to the IoT platform, the platform will return data acknowledgment information. This data acknowledgment information includes the sequence number of the successfully received data shards and a digital signature. The digital signature is used to verify the authenticity and integrity of the data and prevent the data from being maliciously tampered with during transmission. The system uses an asymmetric encryption algorithm (such as the RSA algorithm) to verify the digital signature to obtain a preliminary verification result. The asymmetric encryption algorithm uses the public key to decrypt the digital signature and compares the decrypted result with the calculated hash value to determine the integrity of the data. The formula for asymmetric encryption is as follows:

[0084] D = E d mod N;

[0085] Where D represents the decrypted hash value, E is the digital signature, d is the private key, and N is the modulus shared by the public key and the private key. If the decryption result matches the hash value, the data verification passes, indicating that the data has not been tampered with. The preliminary verification result is input into a Byzantine fault-tolerant consensus algorithm model for verification. The Byzantine fault-tolerant consensus algorithm is an algorithm that ensures agreement among nodes in a distributed network. Through multiple rounds of voting, even if there are some unreliable nodes in the network, the system can still reach an agreement. In IoT applications, the Byzantine fault-tolerant algorithm conducts multiple rounds of voting in a distributed node network. When more than 2 / 3 of the nodes reach an agreement on the data acknowledgment information, the final data reception acknowledgment result is output. Calculate key performance indicators such as the data transmission success rate, average latency, and throughput based on the data reception acknowledgment result. The formula for calculating the data transmission success rate is as follows:

[0086]

[0087] Among them, Success Rate represents the success rate of data transmission, N received represents the number of data shards successfully received, N sent represents the total number of data shards sent. The success rate reflects the proportion of data reaching the target platform during the transmission process. The average latency is used to measure the time required for data to be sent and confirmed received, and the throughput represents the amount of data successfully transmitted per unit time. These metrics combined can comprehensively evaluate the transmission performance of the network. Based on these key metrics, a data access status report is constructed. Through the data visualization interface, these metrics are generated into interactive charts, enabling users to intuitively view the specific performance of data transmission, such as the trend change of the success rate, the distribution of the average latency, etc. Through the AI voice assistant, the data access status report is converted into voice output using text-to-speech (TTS) technology, and users can understand the current data transmission status through voice, so as to still be able to obtain key information in a timely manner when unable to view the charts.

[0088] Further, encode the preliminary verification result into a 256-bit binary string, add a 32-bit checksum, and construct a verification message in standard format, which is broadcast to all participating nodes in the distributed node network through the P2P network protocol. After each node receives the broadcast information, it parses the verification message, extracts the preliminary verification result, and generates a 512-bit verification proposal containing a 64-bit node ID, a 64-bit nanosecond timestamp, and a 256-bit preliminary verification result; calculate the message digest of the 512-bit verification proposal using the SHA-256 algorithm to obtain a 256-bit digest value, and then use the private key of the node to sign the digest value through the Elliptic Curve Digital Signature Algorithm (ECDSA) to generate a 512-bit signature value, and append this signature value to the verification proposal to form a 1024-bit signed verification proposal; send the 1024-bit signed verification proposal to other nodes in the network through the UDP protocol, and at the same time establish a receiving buffer with a size of 10MB to receive verification proposals from other nodes. Extract the public key and signature from each received verification proposal, use the ECDSA algorithm to verify the validity of the signature, and store the verified proposals in the valid proposal list to obtain a set of valid verification proposals; based on the set of valid verification proposals, count the number of different node IDs to obtain the total number of nodes N, calculate the number of valid proposals to obtain the number of online nodes M, and determine whether M is greater than (2N + 1) / 3. If it is satisfied, the consensus condition judgment result is true, otherwise it is false; according to the consensus condition judgment result, if it is true, enter the voting stage. Each node performs a bitwise exclusive OR operation on the local verification result and the result in each received valid verification proposal. If the result is 0, it is in favor, otherwise it is against, and generates a 64-bit voting information containing a 1-bit in favor / against flag and 63-bit random padding data; use the 64-bit voting information as plaintext input to the Paillier homomorphic encryption algorithm and encrypt it using a 2048-bit public key to obtain a 2048-bit ciphertext, which is the encrypted voting information, ensuring the privacy of the vote; based on the encrypted voting information, execute a secure multi-party computation protocol. Specifically, use Shamir's Secret Sharing scheme to divide each encrypted voting information into N shares and distribute them to N nodes in the network. Each node performs a homomorphic addition operation on all the received shares locally to obtain a partial sum, and then broadcasts the partial sum to other nodes. Finally, each node collects all the partial sums and merges them to obtain a 4096-bit encrypted voting statistical result; decrypt the 4096-bit encrypted voting statistical result using a (k, n) threshold decryption scheme, where k = 2N / 3 + 1. At least k nodes need to provide their respective private key shares to complete the decryption. Each participating node uses its own private key share to perform partial decryption on the ciphertext and then broadcasts the partial decryption result. When at least k partial decryption results are collected, the complete decryption result is reconstructed through Lagrange interpolation to obtain a 64-bit plaintext voting statistical result;According to the voting statistics results of the 64-bit plaintext, extract the number of votes in favor, and determine whether it exceeds 2N / 3 + 1. If so, generate a 256-bit consensus result containing the "consensus reached" status, the current round number, and the final result. If not, increment the current round number by 1. If it does not exceed the preset maximum round number of 20, return to step 5 to start a new round of voting. Otherwise, generate a "consensus failed" consensus result. Based on the final consensus result, construct a data reception confirmation report containing a 256-bit data reception confirmation status, a 64-bit timestamp, and a variable-length (maximum 1MB) list of participating consensus nodes. Hash the report using the Merkle tree structure to obtain a 32-byte root hash value. Write this root hash value as transaction data into the blockchain network, and at the same time, send the complete data reception confirmation report to all participating nodes through a reliable multicast protocol to complete the consensus confirmation process for data reception.

[0089] Refer to Figure 2 , this embodiment provides a data access system for an intelligent IoT gateway, including:

[0090] An identification unit 1, configured to perform feature matching and protocol identification on multiple sensors and terminal devices connected to the intelligent IoT gateway using a device feature library to obtain the device protocol type;

[0091] An analysis unit 2, configured to activate a corresponding protocol analysis plugin based on the device protocol type, analyze the raw data to obtain an analysis result, and call an edge computing microservice to input the analysis result and the raw data into a semantic ontology model for data standardization processing to obtain standardized data;

[0092] An encryption unit 3, configured to calculate the sensitivity of the standardized data, and select an encryption algorithm to encrypt the standardized data according to the sensitivity to obtain an encrypted security data packet and an encrypted session key;

[0093] A selection unit 4, configured to perform a multi-dimensional evaluation on the current network environment of the intelligent IoT gateway to obtain network evaluation data, and input the network evaluation data into a deep reinforcement learning model for multi-factor transmission channel selection to obtain an optimal transmission channel combination;

[0094] An output unit 5, configured to send the encrypted security data packet to the IoT platform based on the optimal transmission channel combination, verify the received data confirmation information based on a consensus algorithm, and output a data access status report through a data visualization interface and an AI voice assistant.

[0095] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to that described in the above method embodiment, and details are not described herein again.

[0096] Refer toFigure 3 , in an embodiment of the present invention, a computer device is further provided. The computer device may be a server, and its internal structure may be as Figure 3 shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0097] Those skilled in the art can understand that Figure 3 the structure shown in

[0098] is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0099] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided by the present invention and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, etc.

[0100] It should be noted that in this article, the terms "include", "comprise", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, system, article, or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, system, article, or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, system, article, or method including that element.

[0101] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A data access method for a smart Internet of Things gateway, characterized in that: The following steps are involved: Use the device feature library to perform feature matching and protocol identification on multiple sensors and terminal devices connected to the smart IoT gateway to obtain the device protocol type; Based on the device protocol type, a corresponding protocol parsing plug-in is activated to parse the original data to obtain a parsing result, and an edge computing microservice is called to input the parsing result and the original data into a semantic ontology model for data standardization processing to obtain standardized data; Calculating the sensitivity of the standardized data, and selecting an encryption algorithm according to the sensitivity to encrypt the standardized data to obtain an encrypted security data packet and an encrypted session key; Perform a multi-dimensional evaluation on the current network environment of the smart IoT gateway to obtain network evaluation data, and input the network evaluation data into a deep reinforcement learning model to perform multi-factor transmission channel selection to obtain an optimal transmission channel combination; Based on the optimal transmission channel combination, the encrypted security data packet is sent to the IoT platform, the received data confirmation information is verified based on the consensus algorithm, and the data access status report is output through the data visualization interface and AI voice assistant.

2. The data access method of the smart Internet of Things gateway according to claim 1 is characterized in that: The device feature library is used to perform feature matching and protocol identification on multiple sensors and terminal devices connected to the smart IoT gateway to obtain the device protocol type, including: Monitor the communication interface of the smart IoT gateway in real time, identify newly connected sensors and terminal devices, and record the physical connection characteristics of the sensors and terminal devices to obtain a list of device connection information; Extracting protocol identifiers, data frame formats and communication parameters of multiple pre-stored communication protocols from the device feature library to construct a protocol feature matrix; Calculate the similarity between the physical connection features in the device connection information list and the protocol feature matrix to obtain a device-protocol similarity score, and select K candidate protocols with the highest similarity for each device based on the device-protocol similarity score to obtain a device candidate protocol set; For each communication protocol in the candidate protocol set of the device, data packet capture and protocol simulation are performed, and the protocol matching degree is calculated by sending simulated data packets to the device and analyzing the response to obtain a protocol matching score table; According to the protocol matching score table, the similarity score between the device and each protocol and the protocol matching degree are comprehensively considered, and the protocol with the highest similarity score and protocol matching degree is selected as the recognition result for each device to obtain a preliminary device-protocol mapping relationship; For the devices whose confidence in the preliminary device-protocol mapping relationship is lower than a preset threshold, adaptive protocol learning is performed and key features are extracted, the key features are compared with a known protocol library, and a temporary protocol is generated; The temporary protocol is applied to the real-time data stream of the corresponding device, a protocol parsing test is performed, and the parsing success rate and the data integrity index are calculated. If the parsing success rate and the data integrity index meet the preset conditions, the temporary protocol is added to the device feature library, and the device-protocol mapping relationship is updated to obtain the device protocol type.

3. The data access method of the smart Internet of Things gateway according to claim 2 is characterized in that: The method activates the corresponding protocol parsing plug-in based on the device protocol type, parses the original data to obtain the parsing result, and calls the edge computing microservice to input the parsing result and the original data into the semantic ontology model for data standardization processing to obtain standardized data, including: According to the device protocol type, a matching protocol parsing plug-in is retrieved from a protocol parsing plug-in library, and the protocol parsing plug-in is loaded into a parsing engine of the smart IoT gateway to obtain a protocol parsing plug-in; Inputting the original data into the protocol analysis plug-in, decomposing, extracting and converting the original data using the preset analysis rules to obtain the analysis results, and performing data integrity check on the analysis results, calculating the data checksum, and comparing it with the preset threshold to obtain the data validity mark; The parsing result and the data validity mark are transmitted to the edge computing microservice, and the edge computing task is triggered to obtain the preliminarily processed data; Extracting a semantic ontology model related to the device protocol type from a semantic ontology library, constructing a semantic mapping rule set, and semantically annotating the preliminarily processed data and the original data according to the semantic mapping rule set to generate a data entity with semantic tags; Ontological reasoning is performed on the data entities with semantic tags, and data relationships are analyzed and derived using description logic algorithms to obtain a semantic association network, and normalization processing is performed based on the semantic association network to obtain standardized data.

4. The data access method of the smart Internet of Things gateway according to claim 3 is characterized in that: The extracting of the semantic ontology model related to the device protocol type from the semantic ontology library, constructing a semantic mapping rule set, and semantically annotating the preliminarily processed data and the original data according to the semantic mapping rule set to generate a data entity with semantic tags includes: According to the device protocol type, a query statement is constructed, the query statement includes a protocol identifier and a keyword, a semantic ontology library is searched using a SPARQL query language, an ontology model related to the device protocol type is extracted, and a plurality of candidate ontology models are obtained; Perform structural analysis on each candidate ontology model, extract core concepts, attributes and relationships, construct ontology feature vectors, and calculate feature weights to obtain a weighted ontology feature vector set; Performing similarity matching between the weighted ontology feature vector set and the corresponding domain knowledge graph, and selecting the candidate ontology model with the highest similarity as the most matching semantic ontology model; Based on the semantic ontology model, extracting class, attribute and relationship definitions, and constructing a semantic mapping rule set, the semantic mapping rule set includes a mapping relationship from data fields to semantic concepts, attribute constraints and reasoning rules; Parsing the preliminarily processed data and the original data into key-value pairs, and assigning corresponding semantic concepts and attributes to each key-value pair according to the semantic mapping rule set, to generate a preliminary semantic annotation result; Performing context analysis on the preliminary semantic annotation results, extracting association information between adjacent data items, calculating mutual information values, and constructing a data item association matrix. At the same time, based on the data item association matrix, calculating the vector representation of the semantic concept in the knowledge graph, and selecting the semantic concept with the highest cosine similarity as the final semantic tag; The preliminary semantic annotation result is converted into a resource description framework format according to the final semantic tag, each data item is represented as a subject-predicate-object triple, and a globally unique URI identifier is assigned to each triple to obtain a data entity with a semantic tag.

5. The data access method of the smart Internet of Things gateway according to claim 1 is characterized in that: The calculating the sensitivity of the standardized data and selecting an encryption algorithm according to the sensitivity to encrypt the standardized data to obtain an encrypted security data packet and an encrypted session key includes: Extracting features from the standardized data, mapping the data fields into vector representations using a pre-trained word embedding model, and obtaining a data feature vector set; Inputting the data feature vector set into a sensitivity assessment model, the sensitivity assessment model is based on a multi-layer perceptron structure, trained using a cross entropy loss function, and outputting a sensitivity score for each data field to obtain a sensitivity score set; Performing cluster analysis on the sensitivity score set, dividing the data fields into different sensitivity levels, obtaining a data sensitivity classification result, and selecting a corresponding encryption algorithm from a predefined encryption algorithm library according to the data sensitivity classification result, using a lightweight encryption algorithm for low-sensitivity data and a strong encryption algorithm for high-sensitivity data, to obtain an encryption algorithm selection scheme; Based on the encryption algorithm selection scheme, data fields of different sensitivity levels are encrypted respectively, and encryption session keys are generated at the same time to obtain preliminary encrypted data and encryption session keys; Processing the preliminary encrypted data in blocks, adding a unique identifier and version information to each data block, constructing an encrypted data packet structure, obtaining structured encrypted data, performing integrity protection on the structured encrypted data, calculating an HMAC value and appending it to the data packet, obtaining an integrity-protected encrypted data packet, wherein HMAC is a key-based message authentication code; The encrypted session key is encrypted using an asymmetric encryption algorithm, and the encrypted session key is combined with the integrity-protected encrypted data packet to obtain an encrypted security data packet and an encrypted session key.

6. The data access method of the smart Internet of Things gateway according to claim 1 is characterized in that: The multi-dimensional evaluation of the current network environment of the smart IoT gateway is performed to obtain network evaluation data, and the network evaluation data is input into a deep reinforcement learning model to perform multi-factor transmission channel selection to obtain an optimal transmission channel combination, including: Perform parallel scanning on all network interfaces of the smart IoT gateway, collect interface status information through the SNMP protocol, and obtain a network interface list, wherein SNMP is a simple network management protocol; Based on the network interface list, a network performance test is performed on each active interface, the round-trip delay is measured using the ICMP protocol, the bandwidth is tested through the iPerf tool, the packet loss rate is measured using the UDP traffic generator, and the signal strength and signal-to-noise ratio are additionally measured for the wireless interface, so as to obtain an original network performance data matrix containing multi-dimensional indicators; Generate a network interface evaluation vector according to the original network performance data matrix, and arrange the network interfaces in descending order according to the network interface evaluation vector, and select the top N interfaces as a set of candidate transmission channels; The network performance data of the candidate transmission channel set is integrated with the historical transmission data in time series to construct a state space matrix, where each row represents the network state at a time point, and the columns include bandwidth utilization and delay jitter indicators, to obtain a representation of the current network state; Inputting the current network state representation into a deep reinforcement learning model, the deep reinforcement learning model uses a dual DQN structure to calculate the Q value of each possible transmission channel combination through forward propagation to obtain a transmission channel evaluation matrix containing all possible combination Q values; Based on the transmission channel evaluation matrix, the probability of each transmission channel combination being selected is calculated, and the combination with the highest probability is selected as the optimal transmission channel combination.

7. The data access method of the smart Internet of Things gateway according to claim 1 is characterized in that: Based on the optimal transmission channel combination, the encrypted security data packet is sent to the IoT platform, the received data confirmation information is verified based on the consensus algorithm, and a data access status report is output through the data visualization interface and the AI ​​voice assistant, including: According to the optimal transmission channel combination, the encrypted secure data packet is fragmented, and a large data packet is divided into a plurality of data fragments, each data fragment is attached with a unique sequence number and checksum, and a data fragment set is obtained; Based on the data shard set, calculate the optimal transmission path for each shard, allocate the shards to different transmission channels, and obtain a shard transmission plan; According to the shard transmission scheme, the data shards are sent to the IoT platform simultaneously through multi-threaded parallel transmission technology, and the timeout retransmission mechanism is started to record the sending status of each shard and obtain a data transmission log; Receive the data confirmation information returned by the IoT platform, which contains the successfully received data segment serial number and digital signature, and use the asymmetric encryption algorithm to verify the validity of the digital signature to obtain a preliminary verification result; Input the preliminary verification result into a consensus algorithm model based on Byzantine fault tolerance, and the consensus algorithm model based on Byzantine fault tolerance performs multiple rounds of voting in a distributed node network. When more than 2 / 3 of the nodes reach a consensus, the data reception confirmation result is output; Based on the data reception confirmation result, the success rate, average delay and throughput of data transmission are calculated, a data access status report is constructed, and an interactive chart is generated through a data visualization interface. The data access status report is converted into voice output through an AI voice assistant using text-to-speech technology.

8. A data access system for a smart Internet of Things gateway, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: The identification unit is used to use the device feature library to perform feature matching and protocol identification on multiple sensors and terminal devices connected to the smart IoT gateway to obtain the device protocol type; A parsing unit, configured to activate a corresponding protocol parsing plug-in based on the device protocol type, parse the original data to obtain a parsing result, and call an edge computing microservice to input the parsing result and the original data into a semantic ontology model for data standardization processing to obtain standardized data; An encryption unit, used to calculate the sensitivity of the standardized data, and select an encryption algorithm according to the sensitivity to encrypt the standardized data to obtain an encrypted security data packet and an encrypted session key; A selection unit, configured to perform a multi-dimensional evaluation on the current network environment of the smart IoT gateway to obtain network evaluation data, and input the network evaluation data into a deep reinforcement learning model to perform multi-factor transmission channel selection to obtain an optimal transmission channel combination; The output unit is used to send the encrypted security data packet to the IoT platform based on the optimal transmission channel combination, verify the received data confirmation information based on the consensus algorithm, and output the data access status report through the data visualization interface and AI voice assistant.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images