Protocol conversion method based on universal protocol conversion collector of Internet of Things data

By collecting and preprocessing data in the Internet of Things, building a deep neural network model and deploying it on edge nodes for protocol conversion, it solves the problems of difficulty in obtaining labeled samples and high consumption of computing resources, and realizes efficient and real-time protocol conversion, improving The robustness and scalability of the system.

CN118714203BActive Publication Date: 2024-11-12NANJING DEEPCTRLS TECHNOLOGIES CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411178901.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-12
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

The existing IoT data protocol conversion technology has problems such as difficulty in obtaining labeled samples, high computing resources, and neglecting real-time and robustness.

Method used

Massive IoT data is collected for preprocessing to form a sample data set, a deep neural network is used to build a feature extraction model for training, and it is deployed on edge nodes for protocol conversion, and a protocol conversion is realized through collaborative processing.

Benefits of technology

It improves the accuracy and efficiency of protocol conversion, reduces data transmission delay, enhances the scalability and robustness of the system, and reduces the computing burden of the central server.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118714203B_ABST
    Figure CN118714203B_ABST
Patent Text Reader

Abstract

The present invention belongs to the field of Internet of Things communication technology, and relates to a protocol conversion method based on a universal protocol conversion collector for Internet of Things data, which collects a large amount of data protocols in the Internet of Things for data preprocessing to form a sample data set; the sample data set is input into a feature extraction model constructed based on a deep neural network for learning and training, and after the training, the feature extraction model can adaptively extract protocol features; lightweight protocol conversion tasks and extracted protocol features are deployed on the edge nodes of the Internet of Things, and rapid conversion of data protocols is achieved through collaborative processing between edge nodes. The present invention solves the problems of difficulty in obtaining labeled samples, large consumption of computing resources, and neglect of real-time and robustness in existing Internet of Things data protocol conversion technologies, and reduces data transmission delay and improves the response speed and robustness of data protocol conversion by sinking the protocol conversion tasks to the edge of the network.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things communications, and in particular to a protocol conversion method based on an Internet of Things data universal protocol conversion collector. Background Art

[0002] With the rapid development of Internet of Things technology, the popularity of various smart devices and sensors has led to an explosive growth in data volume. These devices and sensors often use different data protocols to communicate, resulting in diverse and incompatible data formats, which brings great challenges to data collection, integration and analysis.

[0003] Traditional data protocol conversion methods mainly rely on manually designed rules and conversion logic. These methods usually require writing specific conversion code for each new data protocol, which has a long development cycle and is difficult to adapt to the ever-changing protocol format. In addition, due to the wide variety of IoT devices and the large differences between protocols, manually written conversion rules are often difficult to achieve comprehensive coverage, resulting in poor conversion results.

[0004] In recent years, with the continuous development of deep learning technology, data protocol conversion methods based on deep neural networks have gradually attracted attention. Such methods automatically mine the intrinsic connections and rules between protocols by learning a large amount of sample data of known protocols, thereby realizing automatic identification and conversion of new protocols. Compared with traditional methods, deep learning-based methods have stronger adaptability and generalization capabilities, and can significantly improve the accuracy and efficiency of data protocol conversion.

[0005] However, existing deep learning-based data protocol conversion methods still have some problems. First, these methods usually require a large number of labeled samples for training, and obtaining large-scale labeled samples is a time-consuming and labor-intensive task; second, deep learning models usually require high computing resources for training and reasoning, which is a huge challenge for resource-constrained IoT edge nodes; finally, existing methods often only focus on the accuracy of protocol conversion, but ignore the real-time and robustness requirements during the conversion process. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract of the specification and the title of the invention of this application to avoid blurring the purpose of this section, the abstract of the specification and the title of the invention, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In view of the above existing problems, the present invention is proposed.

[0008] Therefore, the technical problem solved by the present invention is that the existing Internet of Things data protocol conversion technology has the problems of difficulty in obtaining labeled samples, large consumption of computing resources, and neglect of real-time and robustness.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions: collecting massive data protocols in the Internet of Things for data preprocessing to form a sample data set;

[0010] The sample data set is input into a feature extraction model constructed based on a deep neural network for learning and training. After the training, the feature extraction model can adaptively extract protocol features.

[0011] Lightweight protocol conversion tasks and the extracted protocol features are deployed on the edge nodes of the Internet of Things, and the protocol conversion is completed through collaborative processing between edge nodes.

[0012] As a preferred solution of the protocol conversion method based on the universal protocol conversion collector for Internet of Things data described in the present invention, the types of data protocols include but are not limited to industrial protocols, home automation protocols and general Internet of Things protocols.

[0013] As a preferred solution of the protocol conversion method based on the universal protocol conversion collector for Internet of Things data described in the present invention, the data preprocessing includes:

[0014] Cleaning duplicate values, missing values, and abnormal values ​​in the data protocol;

[0015] Convert the cleaned data of the data protocol into a unified format and unify the timestamp format, wherein the unified format includes but is not limited to JSON format and CSV format;

[0016] The data protocol is then labeled with a type label, wherein the type label includes but is not limited to an industrial protocol label, a home automation protocol label, and a general Internet of Things protocol label.

[0017] As a preferred solution of the protocol conversion method based on the universal protocol conversion collector for Internet of Things data described in the present invention, the pre-processed data of the data protocol is encapsulated into a format suitable for input of the feature extraction model, and the encapsulated data is aggregated in a set to obtain the sample data set;

[0018] The formats include but are not limited to the formats required by TensorFlow and PyTorch.

[0019] As a preferred solution of the protocol conversion method based on the universal protocol conversion collector for Internet of Things data described in the present invention, the learning and training includes:

[0020] The sample data set is input into the feature extraction model through the input layer for parameter training;

[0021] Use the Adam optimization algorithm to adjust the weights of deep learning neural networks;

[0022] The training ends when the adjusted network structure meets the set requirements;

[0023] Among them, the network structure includes but is not limited to an input layer, a convolutional layer, a pooling layer, a fully connected layer and an output layer, and the setting requirements include but are not limited to the output of the feature extraction model being a non-negative real number.

[0024] As a preferred solution of the protocol conversion method based on the universal protocol conversion collector for Internet of Things data described in the present invention, the feature extraction model can be expressed by the following formula:

[0025]

[0026]

[0027] in, Represents the result function of feature extraction, whose value is a non-negative real number. represents the information filtering function, is the mean, is the standard deviation, d, c, k, and a are parameters learned through the optimization algorithm during model training, which are used to adjust the model's sensitivity to data features and response threshold. Represents the raw data points collected from IoT devices, i.e., data protocols. Is a linear rectification function, used to increase the ability to extract nonlinear features of the model. is an exponential decay function used to enhance the model’s sensitivity to protocol features. It is a logistic distribution function used to screen and optimize protocol features.

[0028] As a preferred solution of the protocol conversion method based on the universal protocol conversion collector for Internet of Things data described in the present invention, the protocol characteristics include but are not limited to protocol field characteristics, communication behavior characteristics and abnormal mode characteristics.

[0029] As a preferred solution of the protocol conversion method based on the universal protocol conversion collector for Internet of Things data described in the present invention, the collaborative processing establishes a stable message transmission mechanism between nodes through a message protocol, supports asynchronous communication and data transmission, and dynamically allocates protocol conversion tasks according to the network status of the node to complete load balancing.

[0030] As a preferred solution of the protocol conversion method based on the universal protocol conversion collector of Internet of Things data described in the present invention, the method is implemented by applying to the protocol conversion collector, which includes a multi-protocol communication module, a storage unit and an interface module, a protocol parsing module, a protocol conversion module, a data processing module and a system management module, wherein:

[0031] The multi-protocol communication module is used to support the communication protocols of MQTT, CoAP, HTTP, and LoRa;

[0032] The storage unit is used for data caching and log recording;

[0033] The interface module is used to provide a connection interface with an external device;

[0034] The protocol parsing module is responsible for receiving and parsing data of different protocols;

[0035] The protocol conversion module is used to convert the parsed data into a unified format;

[0036] The data processing module is used for data filtering, aggregation, analysis, protocol conversion and transmission;

[0037] The system management module is used to provide device configuration, status monitoring and log management.

[0038] As a preferred solution of the protocol conversion method based on the universal protocol conversion collector for Internet of Things data described in the present invention, the collector receives data from different devices, parses the data through the protocol parsing module, and then converts the data into a unified format by the protocol conversion module, and processes and transmits the data through the data processing module;

[0039] Wherein, the application program of the protocol conversion method is deployed in the protocol conversion module to realize the conversion of the data protocol.

[0040] Beneficial effects of the present invention:

[0041] 1. By collecting massive data protocols in the Internet of Things and performing data preprocessing, the unified organization and standardized processing of different protocol formats are achieved, forming a high-quality sample data set for training, providing a rich and diverse data foundation for subsequent feature learning, ensuring that the feature extraction model can learn the commonalities and characteristics of various types of protocols, thereby improving the generalization ability and adaptability of the model;

[0042] 2. Use the powerful ability of deep learning to automatically mine deep features in the data, thereby improving the accuracy and efficiency of protocol conversion;

[0043] 3. Taking advantage of edge computing, the protocol conversion task is moved to the edge of the network, thereby reducing data transmission delay, reducing the computing burden of the central server, and improving the scalability and robustness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0045] Figure 1 The present invention is a flowchart of a protocol conversion method based on a universal protocol conversion collector for Internet of Things data. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0047] Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without making any creative work should fall within the scope of protection of the present invention.

[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0049] According to an embodiment of the present invention, Figure 1 The flowchart shown is a protocol conversion method based on the universal protocol conversion collector of Internet of Things data, which specifically includes the following steps:

[0050] S1. Collect a large amount of data protocols in the Internet of Things for data preprocessing to form a sample data set. It should be noted that this step is to perform data preprocessing to obtain a sample data set, including:

[0051] Clean the duplicate values, missing values, and outliers in the data protocol;

[0052] Convert the cleaned data protocol data into a unified format and unify the timestamp format;

[0053] Label the data protocol with a type tag;

[0054] The labeled data is encapsulated into a format suitable for feature extraction model input, and the encapsulated data is aggregated in a set to obtain a sample data set.

[0055] As an example, the data is converted into a unified format, including but not limited to JSON format and CSV format.

[0056] As an example, the type tags include, but are not limited to, industrial protocol class tags, home automation protocol class tags, and general Internet of Things protocol class tags.

[0057] As an example, a format suitable for feature extraction model input includes but is not limited to the format required by TensorFlow and PyTorch.

[0058] As examples, types of data protocols include, but are not limited to, industrial protocols (such as Modbus, OPC-UA), home automation protocols (such as Zigbee, Z-Wave), and common IoT protocols (MQTT, CoAP).

[0059] It should be noted that this step realizes the unified organization and standardization of different protocol formats by collecting massive data protocols in the Internet of Things and performing data preprocessing, thus forming a high-quality sample data set for training.

[0060] Preferably, reliable input data is provided for the training of deep learning models, laying the foundation for accurate extraction of protocol features, ensuring that the feature extraction model can learn the commonalities and characteristics of various types of protocols, thereby improving the generalization ability and adaptability of the model.

[0061] S2. Input the sample data set into the feature extraction model built based on the deep neural network for learning and training. After the training, the feature extraction model can adaptively extract protocol features. It should be noted that this step includes:

[0062] The sample data set is input into the feature extraction model through the input layer for parameter training;

[0063] Use the Adam optimization algorithm to adjust the weights of deep learning neural networks;

[0064] The training ends when the adjusted network structure meets the set requirements;

[0065] The network structure includes but is not limited to an input layer, a convolutional layer, a pooling layer, a fully connected layer and an output layer, and the setting requirements include but are not limited to the output of the feature extraction model being a non-negative real number.

[0066] As an example, the feature extraction model can be expressed as follows:

[0067]

[0068]

[0069] in, Represents the result function of feature extraction, whose value is a non-negative real number. represents the information filtering function, is the mean, is the standard deviation, d, c, k, and a are parameters learned through the optimization algorithm during model training, which are used to adjust the model's sensitivity to data features and response threshold. Represents the raw data points collected from IoT devices, i.e., data protocols. Is a linear rectification function, used to increase the ability to extract nonlinear features of the model. is an exponential decay function used to enhance the model’s sensitivity to protocol features. It is a logistic distribution function used to screen and optimize protocol features.

[0070] As an example, the protocol characteristics include, but are not limited to, protocol field characteristics, communication behavior characteristics, and abnormal pattern characteristics.

[0071] It should be noted that this step realizes the automatic recognition and learning of the deep features of the IoT data protocol by inputting the sample data set into the feature extraction model built based on the deep neural network for learning and training. After the training, the feature extraction model can adaptively extract protocol features, which means that the model has the ability to extract key information from complex data and can accurately identify and convert different protocols without human intervention.

[0072] Preferably, the embodiments of the present invention utilize the powerful capabilities of deep learning to automatically mine deep features in the data, thereby improving the accuracy and efficiency of protocol conversion, greatly improving the level of automation of data protocol conversion, reducing dependence on expert knowledge, and being able to handle more complex and varied protocol formats.

[0073] S3. Deploy lightweight protocol conversion tasks and extracted protocol features on the IoT edge nodes, and complete the protocol conversion through collaborative processing between edge nodes.

[0074] In an optional embodiment, the above-mentioned collaborative processing can be achieved by establishing a stable message passing mechanism between nodes through a message protocol and dynamically allocating protocol conversion tasks according to the network status of the nodes, wherein the message passing mechanism supports asynchronous communication and data transmission.

[0075] It should be noted that this step takes advantage of edge computing and sinks the protocol conversion task to the edge of the network, thereby reducing data transmission delays, reducing the computing burden of the central server, and improving the scalability and robustness of the system.

[0076] Preferably, the embodiments of the present invention accelerate the response speed of protocol conversion, improve the overall performance of the Internet of Things system, and reduce operating costs and energy consumption.

[0077] The aforementioned collaborative processing method and edge node deployment method can be implemented using existing technical means and technologies, and will not be described in detail in this example.

[0078] It should also be noted that the method is implemented by applying to a protocol conversion collector, which includes a multi-protocol communication module, a storage unit and an interface module, a protocol parsing module, a protocol conversion module, a data processing module and a system management module, wherein:

[0079] Multi-protocol communication module, used to support MQTT, CoAP, HTTP, LoRa communication protocols;

[0080] Storage unit for data caching and logging;

[0081] An interface module is used to provide a connection interface with external devices;

[0082] The protocol parsing module is responsible for receiving and parsing data of different protocols;

[0083] The protocol conversion module is used to convert the parsed data into a unified format;

[0084] Data processing module, used for data filtering, aggregation, analysis, protocol conversion and transmission;

[0085] System management module, used to provide device configuration, status monitoring and log management.

[0086] Furthermore, the collector receives data from different devices, parses it through the protocol parsing module, and then converts the data into a unified format through the protocol conversion module, which is processed and transmitted through the data processing module;

[0087] The protocol conversion module deploys an application program of the protocol conversion method to realize the conversion of the data protocol.

[0088] It should be appreciated that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory.

[0089] The method may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes a computer to operate in a specific and predefined manner.

[0090] Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system, however, the program can be implemented in assembly or machine language if desired.

[0091] In any case, the language may be a compiled or interpreted language.

[0092] Furthermore, the program can be run on an application specific integrated circuit programmed for this purpose.

[0093] The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that can be executed by one or more processors.

[0094] Further, the method may be implemented in any type of computing platform operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device.

[0095] Various aspects of the present invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage media, RAM, ROM, etc., so that it can be read by a programmable computer, which, when the storage medium or device is read by the computer, can be used to configure and operate the computer to perform the processes described herein.

[0096] Additionally, the machine-readable code, or portions thereof, can be transmitted over a wired or wireless network.

[0097] The invention described herein includes these and other various types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor.

[0098] It should also be noted in this embodiment that the existing protocol conversion technology usually relies on the traditional data center processing method, and all data must be transmitted back to the central server for processing. Therefore, the existing technology has the following defects:

[0099] 1. High latency: Data must be transmitted to the central server over the network, which limits real-time processing capabilities;

[0100] 2. Large bandwidth consumption: large amounts of data transmission increase the burden on network bandwidth;

[0101] 3. Poor scalability: As the number of access devices increases, the processing load of the central server increases, affecting the scalability of the system.

[0102] This example further verifies the authenticity of the technical effect of the method of the present invention through experimental tests, wherein:

[0103] (1) Experimental conditions

[0104] Server: A high-performance server for data preprocessing and deep neural network training, model Dell PowerEdge R740, configured with 2 Intel Xeon Gold 6132 processors and 4 NVIDIA Tesla V100 GPUs;

[0105] Edge computing node: Raspberry Pi4 Model B with 4GB RAM is used to deploy lightweight protocol conversion tasks;

[0106] Data preprocessing: Use Python scripts to clean and standardize data and construct sample data sets;

[0107] Model training: Use the TensorFlow framework to train deep neural networks on the server. The training uses a network structure with three convolutional layers, each followed by a pooling layer and a ReLU activation function, and finally a fully connected layer to output features;

[0108] Protocol conversion deployment: Run lightweight Python applications on edge nodes to extract and convert features of real-time data protocols.

[0109] (2) Experimental process

[0110] Protocols for collecting data from multiple IoT devices (e.g., smart home devices, industrial sensors);

[0111] Run the preprocessing script on the server to clean and standardize the data protocol, and then form a sample data set;

[0112] The feature extraction model provided by the present invention is deployed to the edge computing node to perform real-time data protocol conversion, and the conversion success rate and processing time are recorded.

[0113] The experimental results are shown in Table 1:

[0114] Table 1: Data results statistics

[0115]

[0116] Referring to Table 1, this embodiment collected a total of 15.2 GB of data from 50 different IoT devices, covering various data protocols to ensure the diversity and representativeness of the samples, with an average processing time of 1.53 seconds, demonstrating efficient data processing capabilities. Through compression and optimization, the data volume was reduced from 15.2 GB to 13.5 GB, maintaining the integrity and quality of the data.

[0117] Furthermore, the model was deployed on 10 edge computing nodes with an average deployment time of 0.85 seconds. The test results showed that the success rate of protocol conversion was 98.75%, indicating that the model deployed on the edge nodes can complete the protocol conversion task efficiently and accurately.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A protocol conversion method based on a universal protocol conversion collector for Internet of Things data, characterized in that: include: Collect massive amounts of data protocols in the Internet of Things for data preprocessing to form a sample data set; The data preprocessing includes: Cleaning duplicate values, missing values, and abnormal values ​​in the data protocol; Convert the cleaned data of the data protocol into a unified format and unify the timestamp format, wherein the unified format includes JSON format and CSV format; Then, the data protocol is labeled with a type tag, wherein the type tag includes an industrial protocol tag, a home automation protocol tag, and a general Internet of Things protocol tag; Encapsulating the preprocessed data of the data protocol into a format suitable for feature extraction model input, and aggregating the encapsulated data into a set to obtain the sample data set; Wherein, the formats include those required by TensorFlow and PyTorch; The sample data set is input into a feature extraction model constructed based on a deep neural network for learning and training. After the training, the feature extraction model can adaptively extract protocol features. The learning and training includes: The sample data set is input into the feature extraction model through the input layer for parameter training; Use the Adam optimization algorithm to adjust the weights of deep learning neural networks; The training ends when the adjusted network structure meets the set requirements; The network structure includes an input layer, a convolutional layer, a pooling layer, a fully connected layer and an output layer, and the setting requirements include that the output of the feature extraction model is a non-negative real number; The feature extraction model is expressed by the following formula: in, Represents the result function of feature extraction, whose value is a non-negative real number. represents the information filtering function, is the mean, is the standard deviation, d, c, k, and a are parameters learned through the optimization algorithm during model training, which are used to adjust the model's sensitivity to data features and response threshold. Represents the raw data points collected from IoT devices, i.e., data protocols. Is a linear rectification function, used to increase the ability to extract nonlinear features of the model. is an exponential decay function used to enhance the model’s sensitivity to protocol features. It is a logistic distribution function used to screen and optimize protocol features; The protocol features include protocol field features, communication behavior features and abnormal mode features; Lightweight protocol conversion tasks and the extracted protocol features are deployed on the edge nodes of the Internet of Things, and the protocol conversion is completed through collaborative processing between edge nodes.

2. The protocol conversion method based on the universal protocol conversion collector for Internet of Things data according to claim 1 is characterized in that: The types of data protocols include industrial protocols, home automation protocols and general Internet of Things protocols.

3. The protocol conversion method based on the universal protocol conversion collector for Internet of Things data according to claim 1 is characterized in that: The collaborative processing establishes a stable message transmission mechanism between nodes through a message protocol, supports asynchronous communication and data transmission, and dynamically allocates protocol conversion tasks according to the network status of the nodes to achieve load balancing.

4. The protocol conversion method based on the universal protocol conversion collector for Internet of Things data according to claim 1 is characterized in that: The method is implemented by applying to a protocol conversion collector, which includes a multi-protocol communication module, a storage unit and an interface module, a protocol analysis module, a protocol conversion module, a data processing module and a system management module, wherein: The multi-protocol communication module is used to support the communication protocols of MQTT, CoAP, HTTP, and LoRa; The storage unit is used for data caching and log recording; The interface module is used to provide a connection interface with an external device; The protocol parsing module is responsible for receiving and parsing data of different protocols; The protocol conversion module is used to convert the parsed data into a unified format; The data processing module is used for data filtering, aggregation, analysis, protocol conversion and transmission; The system management module is used to provide device configuration, status monitoring and log management.

5. The protocol conversion method based on the universal protocol conversion collector for Internet of Things data according to claim 4 is characterized in that: The collector receives data from different devices, parses them through the protocol parsing module, converts the data into a unified format through the protocol conversion module, and processes and transmits them through the data processing module; Wherein, the application program of the protocol conversion method is deployed in the protocol conversion module to realize the conversion of the data protocol.

Citation Information

Patent Citations

  • Cloud side cooperation method based on heterogeneous decision model generation technology

    CN112286691A

  • Edge proxy gateway

    CN116055575A

  • Lightweight protocol feature extraction method based on edge computing

    CN117278453A

  • Rapid access method for protocol adaptation of Internet of Things equipment

    CN117834454A

  • Automatic tuning of heterogenous wireless infrastructure

    US20230328547A1