AI graphical programming methods and platforms for the Internet of Things

Abstract

The present invention discloses an AI graphical programming method and platform for the Internet of Things. The method includes: a graphical programming platform identifies an Internet of Things device and authenticates the identified Internet of Things device; the graphical programming platform constructs application logic by dragging and connecting programming instruction blocks, which serves as a rule engine for the Internet of Things device after authentication; the graphical programming platform interacts with the Internet of Things device based on the rule engine. The present invention solves the technical problem of the difficulty of developing Internet of Things applications in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to an AI graphical programming method and platform for the Internet of Things. Background Art

[0002] With the rapid development of Internet of Things (IoT) technology, the concept of the Internet of Everything has gradually become a reality and has been widely infiltrated into many fields such as industrial production, smart homes, and smart cities. This trend has brought huge innovation potential, but at the same time, the development of IoT applications still faces high technical barriers. Especially for non-professional developers or beginners, problems such as high programming complexity, inconsistent protocols between devices, and difficulty in system integration have seriously limited the speed of IoT innovation and application popularization.

[0003] Currently, most IoT development platforms are based on traditional text programming languages ​​(such as C, Python, etc.), which requires developers to have a certain programming foundation and professional knowledge. This not only increases the learning cost, but also limits the participation of non-technical personnel, resulting in many potential innovative ideas not being realized. In addition, the compatibility and interoperability issues between IoT devices require developers to spend a lot of time solving technical problems such as device connection and communication protocol matching during project implementation, which further reduces development efficiency.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide an AI graphical programming method and platform for the Internet of Things, so as to at least solve the technical problem that the Internet of Things application development is difficult in the prior art.

[0006] According to one aspect of an embodiment of the present invention, there is provided an AI graphical programming method for the Internet of Things, including: a graphical programming platform identifies an Internet of Things device and authenticates the identified Internet of Things device; the graphical programming platform constructs application logic by dragging and connecting programming instruction blocks, which serves as a rule engine for the Internet of Things device after authentication; the graphical programming platform interacts with the Internet of Things device based on the rule engine.

[0007] According to another aspect of an embodiment of the present invention, there is also provided an AI graphical programming platform for the Internet of Things, including: an identification module, configured to identify Internet of Things devices and authenticate the identified Internet of Things devices; a rule engine module, configured to build application logic by dragging and connecting programming instruction blocks, as a rule engine for the Internet of Things devices after authentication; and an interaction module, configured to interact with the Internet of Things devices based on the rule engine.

[0008] In the embodiment of the present invention, the graphical programming platform identifies the IoT device and authenticates the identified IoT device; the graphical programming platform builds the application logic by dragging and connecting programming instruction blocks, which serves as a rule engine for the IoT device after authentication; the graphical programming platform interacts with the IoT device based on the rule engine. The above solution solves the technical problem of the difficulty of IoT application development in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0010] Figure 1 is a flow chart of an AI graphical programming method for the Internet of Things according to an embodiment of the present invention;

[0011] Figure 2 is a flowchart of another AI graphical programming method for the Internet of Things according to an embodiment of the present invention;

[0012] Figure 3 is a flowchart of a method for building application logic according to an embodiment of the present invention;

[0013] Figure 4 is a flowchart of a method for interacting with an Internet of Things device according to an embodiment of the present invention;

[0014] Figure 5 is a flowchart of another AI graphical programming method for the Internet of Things according to an embodiment of the present invention;

[0015] Figure 6 is a flow chart of a method for data analysis and intelligent decision-making according to an embodiment of the present invention;

[0016] Figure 7 It is a structural schematic diagram of an AI graphical programming device for the Internet of Things according to an embodiment of the present invention;

[0017] Figure 8A schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] According to an embodiment of the present invention, a method embodiment of an AI graphical programming method for the Internet of Things is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0021] Figure 1 is an AI graphical programming method for the Internet of Things according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0022] Step S102: The graphical programming platform identifies the IoT device and authenticates the identified IoT device.

[0023] The graphical programming platform automatically identifies IoT devices of different manufacturers and protocols through the built-in intelligent device library, and configures the identified IoT devices to achieve plug-and-play. In this way, users can directly connect hardware devices to the platform without complicated settings and manual configuration, thereby simplifying the access process of hardware devices. In addition, the platform authenticates the identified IoT devices to ensure that only authenticated devices can access the platform's functions and data, thereby enhancing the security of the system.

[0024] In some embodiments, the graphical programming platform is provided with a cloud service interface, through which the graphical programming platform can be deployed to the cloud to achieve data storage, analysis and remote control. The design of the cloud service interface enables users to centrally manage and monitor IoT devices in real time in the cloud, improving the flexibility and scalability of the system. At the same time, cloud storage also allows users to synchronize data and application logic between multiple devices to ensure information consistency.

[0025] Step S104, the graphical programming platform constructs application logic by dragging and connecting programming instruction blocks, which serves as a rule engine for the IoT device after authentication.

[0026] The graphical programming platform builds application logic for sensor reading by dragging and connecting the programming instruction blocks; the graphical programming platform builds application logic for data processing by dragging and connecting the programming instruction blocks; the graphical programming platform builds application logic for conditional judgment by dragging and connecting the programming instruction blocks; the graphical programming platform builds application logic for cloud communication by dragging and connecting the programming instruction blocks. This "building block" programming method allows users to create complex logic in an intuitive and simple way without having to deeply understand the details of the programming language, thereby reducing the learning curve of programming and is suitable for users of different technical levels.

[0027] After dragging and connecting the programming instruction blocks, the graphical programming platform instantly checks the connection relationship between the programming instruction blocks to verify whether the program logic is correct. This instant check function can help users find and correct errors in a timely manner, improve programming efficiency and program stability. If an error is found, the platform will provide instant feedback to help users understand the cause of the error and give modification suggestions to further enhance the user experience.

[0028] Step S106: The graphical programming platform interacts with the IoT device based on the rule engine.

[0029] The graphical programming platform is provided with a security framework, through which the graphical programming platform interacts with the IoT device, wherein the security framework adopts a security mechanism including encrypted communication and access control. This security mechanism can protect the security of user data and device information, and prevent unauthorized access and potential network attacks. Through these security measures, users can safely use the graphical programming platform to manage and control IoT devices.

[0030] The AI ​​graphical programming method provided in this application can provide users with a friendly, secure and efficient IoT programming environment, making the management and application development of IoT devices more convenient and efficient, and adapting to the ever-evolving smart homes, smart cities and other application scenarios.

[0031] Figure 2 is another AI graphical programming method for the Internet of Things according to an embodiment of the present invention, such as Figure 2 As shown, the method comprises the following steps:

[0032] Step S202, identifying the IoT device and performing authentication.

[0033] The graphical programming platform first identifies the IoT devices connected to the platform through the built-in smart device library. The device library contains information about IoT devices from different manufacturers and protocols, and can automatically match and identify the type of connected devices. For example, the device identifier (such as MAC address, device ID, etc.) is compared with the information in the smart device library to achieve efficient and accurate identification.

[0034] The graphical programming platform starts the device discovery service, which sends a detection request to all available devices in the network through a broadcast protocol. The responding device will return its device type, manufacturer information, and supported communication protocols. Based on this information and the built-in smart device library, the platform quickly completes the identification and classification of the device. In some embodiments, the IoT device may also actively request access to the graphical programming platform.

[0035] After identifying the IoT device, the platform will automatically configure it to ensure that the device can communicate and exchange data with the platform smoothly. The specific process of device configuration includes automatically obtaining and setting the device's network parameters (such as IP address and port number) to ensure that the device can operate stably in the network. Users only need to connect the device to the platform without complicated settings, which significantly reduces the user's operating threshold.

[0036] Next, the graphical programming platform will authenticate the identified IoT devices. The authentication process includes device identity verification, permission check, and status confirmation. IoT devices can send authentication requests to the cloud service interface, and the platform can confirm the legitimacy of the device and ensure that only authenticated devices can access the platform's functions and data.

[0037] In some embodiments, the platform can also perform dynamic permission management based on the usage of the device and the user's operation behavior to ensure the security of the system. In this way, it not only prevents the access of unauthorized devices, but also protects the privacy and data security of users.

[0038] Step S204, constructing application logic.

[0039] After completing device authentication, the graphical programming platform builds application logic by dragging and connecting programming instruction blocks, which serves as a rule engine for IoT devices that have passed authentication. Users can use programming instruction blocks to create program logic with different functions through a graphical interface.

[0040] Taking the temperature sensor as an example, the method to build the application logic is as follows Figure 3 As shown, the following steps may be included:

[0041] Step S2042, reading sensor data.

[0042] Users can select blocks related to sensor reading from the instruction block library, drag and connect to build logic. For example, by building sensor reading logic, define the sensor reading frequency, data format, etc., read sensor data and store it in a temporary data area. For example, in a smart home application, users can select the "Read Temperature Sensor" block and set it to read temperature data every 10 seconds. The read data will be displayed in real time in the platform's monitoring interface for users to observe.

[0043] Step S2044, construct data processing logic.

[0044] By selecting data processing instruction blocks, users can customize the data processing flow, including data cleaning, filtering, aggregation and other operations. Users can connect the results of sensor readings with data processing logic through wiring to ensure smooth data flow. For example, users can pass temperature data to the "Filter" block to remove outliers, and then use the "Calculate Average" block to obtain the average temperature within a certain period of time.

[0045] Step S2046, constructing conditional judgment logic.

[0046] Users can create conditional judgment instruction blocks to achieve real-time monitoring and decision-making of sensor data. For example, users can set conditions to trigger an alarm or notification when the temperature exceeds a certain threshold. In the specific implementation, users can select the "If temperature > 30℃" conditional block and connect it to the "Send Alarm" block to set the system to send a notification to the user's mobile phone when the condition is met.

[0047] Step S2048, construct cloud communication logic.

[0048] Users can also build application logic that communicates with the cloud, connect to the cloud service interface through specific building blocks, and upload data and issue instructions. This logic can be used to upload processed data to the cloud in real time for analysis and storage. For example, users can set up logic for scheduled data uploads, uploading past sensor data to the cloud database every hour for long-term data analysis and trend prediction.

[0049] Step S2049, perform application logic verification.

[0050] After dragging and connecting, the graphical programming platform will also instantly check the connection relationship between the programming instruction blocks to verify the correctness of the program logic. This instant check function can help users find connection errors or logic loopholes in a timely manner through syntax and logic analysis algorithms, thereby improving programming efficiency and program stability.

[0051] Specifically, first, the system extracts the first feature vector of the context code of the code to be detected and the second feature vector of the current code to be detected. The feature vectors contain various information related to the code operation, such as variable declaration, function definition, and use of control structures. Then, the system upgrades the two feature vectors according to the extended rank criterion, and increases their dimensions through mathematical transformation to enhance the expression ability, thereby capturing more complex logical patterns.

[0052] Next, using a multi-channel convolution kernel, the system couples and fuses the first and second eigenvectors to generate two embedding feature matrices: the main embedding feature matrix, which reflects the main logical structure; and the auxiliary embedding feature matrix, which captures auxiliary information. After fusing the main embedding feature matrix and the auxiliary embedding feature matrix, the fused data is further expanded to form multiple sub-matrices, each of which will be processed by singular value decomposition (SVD) to extract the core subspace representation and factor matrix.

[0053] Subsequently, the system will calculate the principal component differences between the core subspace representation and the factor matrix, and identify logical errors and potential reference problems in the code, such as undefined variables, incorrect function calls, and logical inconsistencies, by analyzing the core features. Ultimately, this series of steps enables the graphical programming platform to efficiently verify code logic, ensuring that users can promptly discover and correct potential problems during the programming process, thereby improving the reliability and stability of the code.

[0054] If an error is found, the platform will provide instant feedback, pointing out the error location and explaining the cause, helping users understand and correct the problem. This user-friendly design aims to reduce the user's learning curve and make it easy for users of different technical levels to get started.

[0055] Step S206: interact with the IoT device.

[0056] After successfully building the application logic, the graphical programming platform starts interacting with IoT devices based on the rule engine. Figure 4 As shown, the interactive method includes the following steps:

[0057] Step S2062, execute the command.

[0058] After running the program logic, the platform generates control instructions to send specific operation commands to various smart home devices. For example, users can control the on / off state of smart air conditioners through the constructed logic. When the platform detects that the indoor temperature exceeds the set threshold through the temperature sensor, it automatically sends the "turn on the air conditioner" command according to the program logic to adjust the indoor temperature.

[0059] In some embodiments, the platform is equipped with a security framework to ensure data security and operational reliability during interaction with IoT devices. All data transmissions are processed using encryption algorithms to ensure the confidentiality of data during transmission and prevent theft or tampering. For example, the system uses AES (Advanced Encryption Standard) for data encryption to ensure that the content of data in transmission is not stolen by a third party. The platform manages user access rights to ensure that only authenticated users can operate specific devices and access sensitive information. Through hierarchical permission management, the system can dynamically adjust accessible functions and data based on the user's identity and role. Users with different roles can be given different operating permissions, thereby improving the security of the system.

[0060] Step S2064, monitor the device status in real time.

[0061] The platform monitors the status of the equipment in real time and displays it to the user through a graphical interface. The user can see the real-time status of each device on the interface, including switch status, working mode, current reading and other information.

[0062] The platform monitors the status of devices and abnormal situations during the interaction process in real time. If suspicious behavior or device failure is detected, the system will automatically trigger an alarm mechanism to notify the user and take corresponding measures. For example, if the system detects that a certain device frequently fails to connect, it will send an alarm to the user to indicate possible failures. In this way, users can safely use the graphical programming platform to manage and control IoT devices, avoiding risks such as data leakage and illegal intrusion.

[0063] The AI ​​graphical programming method provided by this application builds a friendly, safe and efficient IoT programming environment for users. Through the automatic identification and authentication of smart devices, intuitive programming instruction building blocks, instant error feedback mechanism and comprehensive security measures, the management of IoT devices and application development become more convenient and efficient.

[0064] Figure 5 This is another AI graphical programming method for the Internet of Things according to an embodiment of the present invention. The difference between this embodiment and the above embodiment is that this method uses the deep learning ability of the AI ​​big model to conduct in-depth analysis of the collected Internet of Things data, thereby realizing trend prediction, anomaly detection and intelligent decision support, improving users' understanding of AI, and increasing the fun of programming. Figure 5 As shown, the following steps are included:

[0065] Step S502: Identify the IoT device and perform authentication.

[0066] Same as step S202, which will not be repeated here.

[0067] Step S504: data collection and storage.

[0068] After completing device authentication, the platform starts collecting data from various sensors and devices in the smart home through the built application logic. The collected data includes environmental data (such as temperature, humidity, light, etc.), device operating status (such as power consumption, fault information, etc.) and user operation data (such as switch status, adjustment instructions, etc.). These data will be transmitted to the cloud in real time for storage and subsequent analysis.

[0069] Step S506: data analysis and intelligent decision making.

[0070] In order to achieve in-depth analysis of collected data, the graphical programming platform provides an AI big model, which is used to perform data analysis. Figure 6 As shown, the method of data analysis and intelligent decision-making includes the following steps:

[0071] Step S5062: data preprocessing.

[0072] First, data cleaning is performed. During the data cleaning stage, the platform will conduct a comprehensive check of historical data, delete invalid records and standardize the data format. Specifically, by writing data cleaning scripts, the platform automatically identifies and deletes data records with serious missing or incorrect formats. For example, if the timestamp of a record is empty or the numeric field does not conform to the expected format (such as non-numeric), the system marks the record as invalid and removes it. In addition, using regular expressions and data conversion tools, the platform ensures that all data conforms to the predetermined format. For example, the date format is unified to "YYYY-MM-DD HH:mm" to ensure that there will be no format inconsistencies in subsequent analysis. For data that cannot be retrieved, the platform will use interpolation or average method to fill in missing values ​​to reduce the impact on subsequent analysis. For example, using the interpolation method, for time series data, the average value of the previous and subsequent data can be interpolated to fill in missing values.

[0073] Step S5064, feature extraction.

[0074] The platform can decompose timestamps into components such as hours, days of the week, and months. For example, the change in indoor temperature may be different during the day and at night. By extracting the time information into hours, it can help the model identify this periodic change. In addition, based on the time period when the equipment is running, the platform can generate seasonal features for each data point, indicating which season the data point belongs to (such as spring, summer, autumn, and winter) to capture the impact of environmental factors on equipment operation.

[0075] In terms of statistical feature extraction, the platform can extract the following key features for environmental data to facilitate subsequent trend analysis: calculate the daily average temperature, humidity and other indicators to obtain the daily average value to help the model understand the overall trend; extract the daily maximum and minimum temperatures to capture extreme temperature changes, and calculate the daily temperature or humidity fluctuation range (that is, the difference between the maximum and minimum values) to help the model understand the degree of environmental change.

[0076] Taking into account the mutual influence between different sensor data, the platform can also generate interactive features. For example, temperature and humidity are combined to form new features to capture the compound effect of the environment on the device. When the humidity is high, the impact of increased temperature on the device may be different from that when the humidity is low. In addition, combining user operation data (such as switch status) with environmental data to generate interactive features can help the model better understand the impact of user behavior on the environment.

[0077] Step S5066, model training.

[0078] Use deep learning frameworks such as TensorFlow or PyTorch to train the model using large-scale historical data to ensure accuracy and generalization capabilities.

[0079] Specifically, the first step is data segmentation, which divides historical data into training set, validation set and test set to ensure the training effect of the model. Usually, the training set accounts for 70%-80% of the data set and is used for model training; the validation set accounts for 10%-15% and is used to adjust hyperparameters during training to ensure the best performance of the model; the test set also accounts for 10%-15% and is used to evaluate the final performance of the model and ensure its generalization ability.

[0080] During the model training phase, the model is trained using the training set while the hyperparameters are adjusted on the validation set to ensure that the model achieves optimal performance. Cross-validation is used during training to prevent overfitting. The specific training process includes iterative optimization and using the back-propagation algorithm to adjust the weights and biases of the model to minimize the loss function. At the same time, hyperparameters such as the learning rate, batch size, and number of network layers are adjusted based on the performance of the validation set to improve the model effect.

[0081] Finally, the trained model is evaluated using the test set to calculate indicators such as prediction accuracy, recall rate, and F1-score to comprehensively evaluate the overall performance of the model. The evaluation method includes using performance indicators such as root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) to quantitatively analyze the performance of the model on the test set.

[0082] Step S5068, trend prediction.

[0083] The deep learning model obtained through training enables the platform to predict the status of devices in the future. For example, in the temperature and humidity control of smart homes, the platform can predict environmental changes in the next few hours based on historical temperature and humidity data, thereby helping users make adjustments in advance. The specific implementation includes time series prediction and visualization.

[0084] In time series prediction, the trained model is used to predict future environmental data and output the temperature and humidity change trends in the future period. The specific steps include setting the prediction time window and predicting the next 1 hour, 3 hours or 6 hours based on the input features of the model; the model will output the predicted value and its confidence interval at each time point to help users understand the uncertainty of the prediction.

[0085] In order to help users understand environmental changes more intuitively, the platform will also display the forecast results in the form of charts. The specific method includes drawing trend charts to show the predicted temperature and humidity changes, so that users can clearly see future environmental changes. In addition, if the forecast results show that unsuitable environmental conditions are about to occur (such as excessively high temperatures), the platform will provide an alarm prompt and recommend users to take corresponding measures.

[0086] Step S508: Automatically control the IoT device based on intelligent decision making.

[0087] Based on data analysis, users can achieve automated control and decision support through intelligent programming logic built on a graphical programming platform. For example, users can create logic: when the predicted indoor temperature is higher than the set value, the air conditioner is automatically turned on in advance and set to a specific temperature; if the device fails, an alarm is immediately sent to notify the user. The implementation of this logic will greatly enhance the user's smart home experience and reduce manual operations.

[0088] This application combines AI models with IoT devices, allowing users of different technical levels to easily participate in using AI to interact with IoT devices, thereby increasing the fun of programming. In addition, the platform can dynamically adjust device operation strategies based on real-time data, improve the safety and comfort of smart homes, and enhance users' trust and reliance on graphical programming platforms.

[0089] This application also provides an AI graphical programming platform for the Internet of Things, such as Figure 7 As shown, it includes: an identification module 72, which is configured to identify IoT devices and authenticate the identified IoT devices; a rule engine module 74, which is configured to build application logic by dragging and connecting programming instruction blocks, as a rule engine for the IoT devices after authentication; and an interaction module 76, which is configured to interact with the IoT devices based on the rule engine.

[0090] It should be noted that the AI ​​graphical programming platform for the Internet of Things provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the AI ​​graphical programming platform for the Internet of Things provided in the above embodiment and the AI ​​graphical programming method embodiment for the Internet of Things belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0091] Figure 8 FIG. 1 shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present disclosure. It should be noted that: Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0092] like Figure 8As shown, the electronic device includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for system operation are also stored. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0093] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed.

[0094] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An AI graphical programming method for the Internet of Things, characterized in that: include: The graphical programming platform identifies IoT devices and authenticates the identified IoT devices; The graphical programming platform builds application logic by dragging and connecting programming instruction blocks, serving as a rule engine for the IoT device after authentication; The graphical programming platform interacts with the IoT device based on the rule engine.

2. The method according to claim 1, characterized in that: The graphical programming platform constructs application logic by dragging and connecting programming instruction blocks, including at least one of the following: The graphical programming platform constructs application logic for sensor reading by dragging and connecting the programming instruction blocks; The graphical programming platform constructs application logic for data processing by dragging and connecting the programming instruction blocks; The graphical programming platform constructs application logic for conditional judgment by dragging and connecting the programming instruction blocks; The graphical programming platform constructs application logic for cloud communication by dragging and connecting the programming instruction blocks.

3. The method according to claim 1, characterized in that The graphical programming platform identifies the Internet of Things devices, including: the graphical programming platform automatically identifies the Internet of Things devices of different manufacturers and different protocols through a built-in intelligent device library, and configures the identified Internet of Things devices to achieve plug-and-play.

4. The method according to claim 1, characterized in that: The graphical programming platform is provided with a cloud service interface, through which the graphical programming platform can be deployed to the cloud to achieve data storage, analysis and remote control.

5. The method according to claim 1, characterized in that The graphical programming platform is provided with a security framework, and the graphical programming platform interacts with the IoT device through the security framework, wherein the security framework adopts a security mechanism including encrypted communication and access control.

6. The method according to claim 1, characterized in that After constructing the application logic, the method further comprises the graphical programming platform instantly checking the connection relationship between the programming instruction building blocks to verify whether the program logic is correct.

7. An AI graphical programming platform for the Internet of Things, characterized in that: include: An identification module, configured to identify IoT devices and authenticate the identified IoT devices; A rule engine module is configured to construct application logic by dragging and connecting programming instruction blocks, serving as a rule engine for the IoT device after authentication; The interaction module is configured to interact with the Internet of Things device based on the rule engine.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 6.

9. A computer device, characterized in that: include: Memory and processor, The memory stores a computer program; The processor is used to execute the computer program stored in the memory, and when the computer program is run, the processor is enabled to execute the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images