Visual configuration method and system based on modular AI gateway

Abstract

The invention relates to a visual configuration method and system based on a modular AI gateway, and relates to the technical field of electric power Internet of Things. The visual configuration method comprises the following steps: identifying and analyzing a gateway module to obtain a unique identifier of the module, and packaging the unique identifier into structured data; according to the structured data, retrieving and loading a corresponding initialization drive program in a preset drive library; generating a graphical parameter configuration guide according to the initialization driving program in combination with a module type code in the structured data; in the operation process of the graphical parameter configuration guide, collecting and displaying a working state oscillogram of the gateway module, and verifying a configuration result; through automatic linkage of hardware plugging and pulling and a visual configuration process, a driver does not need to be manually installed or a configuration document does not need to be manually searched, the configuration time is shortened, the deployment efficiency is improved, and the project implementation cost is remarkably reduced; the module state is fed back in real time in the configuration process, the effectiveness of parameter adjustment is ensured, and the repeated debugging frequency is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power Internet of Things, and in particular to a visual configuration method and system based on a modular AI gateway. Background Art

[0002] In the field of edge computing devices, modular gateways are widely used in scenarios such as power grids and industrial control due to their scalability. However, existing technologies have significant drawbacks: when users insert new functional modules (such as LoRa communication modules or 4G communication modules), they must manually locate and install the corresponding drivers and configure parameters (such as frequency band and transmit power) through professional documentation. This process is not only time-consuming and labor-intensive (traditional configuration can take over two hours), but also requires operators to possess specialized technical knowledge, resulting in inefficient deployment and a high risk of device failure due to configuration errors. Furthermore, existing modular devices lack a mechanism to link hardware with a visual interface, preventing automated "plug-and-play" configuration. This seriously conflicts with the existing requirement for modular products to be universally applicable, and has become a technical bottleneck hindering the rapid adoption of gateway products.

[0003] Application number CN202310112448.1 discloses a visually configured soft gateway system and its implementation method. The system mainly includes a gateway configuration module to obtain gateway configuration information and save the gateway configuration information on the deployment server; a connection module to establish a connection relationship with the Internet of Things gateway platform based on the gateway configuration information; a first configuration module to determine the communication protocol parameters of the device to be connected based on the connection relationship, and configure the connector according to the communication protocol parameters; a second configuration module to configure the converter corresponding to the connector and establish a corresponding relationship between the converter and the device to be connected; an information configuration module to configure the overall information of the device to be connected with the corresponding converter and connector. The above invention greatly shortens the development cycle and maintenance cost of the Internet of Things gateway.

[0004] The above-mentioned existing technical solutions have the following defects: 1. The operators' professional and technical knowledge does not meet the requirements, resulting in low deployment efficiency and easy equipment failure due to configuration errors; 2. The existing modular gateway lacks a linkage mechanism between hardware and visual interface, and cannot achieve plug-and-play automated configuration. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the purpose of the present invention is to provide a visual configuration method and system based on a modular AI gateway. Through the hardware-software-visualization trinity linkage configuration architecture, the hardware plug-in and unplugging are automatically linked with the visual configuration process. There is no need to manually install drivers or search for configuration documents, which shortens configuration time, improves deployment efficiency, and significantly reduces project implementation costs.

[0006] The purpose of the present invention is achieved through the following technical solutions: A visual configuration method based on a modular AI gateway, comprising: Identify and parse the gateway module, obtain the module's unique identifier, and encapsulate it into structured data; According to the structured data, the corresponding initialization driver in the preset driver library is retrieved and loaded; Generate a graphical parameter configuration wizard according to the initialization driver and the module type code in the structured data; During the operation of the graphical parameter configuration wizard, collecting and displaying the working status waveform of the gateway module and verifying the configuration results; Dynamically verify all working parameters according to a preset pre-check verification mechanism combined with the configuration results to generate parameter verification results; Based on the parameter verification results, digital twins of different gateway modules are constructed, and combined with preset parameter adjustment strategies, module performance under extreme scenarios is calculated; According to the module performance and the environmental sensor network, a physical environment digital model is constructed and a corresponding anti-interference configuration table is generated.

[0007] By adopting the above technical solution, the driver is automatically loaded through module identifier resolution and structured packaging (such as reading EEPROM data through the I2C / SPI bus). Combined with the graphical wizard to guide parameter configuration (such as LoRa frequency band setting), the working status waveform is collected in real time (WebGL renders RSSI dynamic graph) and connectivity is verified. Further, based on the AI ​​pre-check algorithm (such as decision tree parameter conflict detection), the parameters are dynamically verified, and the digital twin (using a multi-physics field simulation engine) is driven to simulate extreme scenario performance. Finally, the environmental sensor network (temperature and humidity / electromagnetic interference data) is integrated to build a physical environment model and generate an anti-interference configuration table (such as dynamic power adjustment strategy). This realizes full life cycle intelligent configuration from hardware identification to environmental adaptation, significantly improving the deployment efficiency and reliability of each gateway module.

[0008] The present invention is further configured as follows: the specific steps of identifying and parsing the gateway module, obtaining the module unique identifier, and encapsulating it into structured data include: Monitor the external interface slot for loading, obtain fluctuation signals, and identify the gateway module; Initializing the communication bus according to the fluctuation signal to establish a data transmission channel; Address the gateway module according to a preset storage mapping table and send a parsing read instruction; Extract data from the gateway module according to the parsing and reading instruction in combination with the data transmission channel to obtain a unique module identifier; Verifying the module unique identifier, and if the verification fails, sending a retransmission request to the gateway module; Otherwise, the module unique identifier is encapsulated to obtain structured data.

[0009] By adopting the above technical solution, the electrical fluctuation signal of the external interface slot is monitored in real time (using the FFT spectrum feature matching algorithm), the communication bus is dynamically initialized and a dedicated transmission channel is established. After locating the gateway module based on the storage mapping table (pre-loaded with the physical address-logical address mapping relationship), a parsing instruction is sent. The integrity of the module's unique identifier is guaranteed by the CRC-16 cyclic redundancy check, and finally it is encapsulated into structured data, realizing hardware plug-in and unplug identification and automatic module registration with zero manual intervention, significantly improving the deployment efficiency and anti-interference reliability of industrial field gateways.

[0010] The present invention is further configured as follows: the specific steps of retrieving and loading the corresponding initialization driver program in the preset driver library according to the structured data include: The structured data is extracted according to the preset interpretation and extraction mechanism to obtain a complete identifier, which is then decrypted into the hardware version number and manufacturer code identifier; Matching the complete identifier according to a preset driver mapping table, and if the match is successful, obtaining the corresponding driver file path in combination with the hardware version number; Otherwise, all driver file paths of the same series are obtained according to the manufacturer code identifier combined with the wildcard rule; Performing a driver search on a preset driver library according to all the driver file paths to obtain all initialized driver programs; Extract information from all the initialization drivers to obtain compatible version ranges and program version information; the program version information includes a major version number, a minor version number, and a patch level; Calculating the matching degree of the complete identifiers and arranging them in descending order according to the program version information, and combining them with the compatible version interval to obtain the corresponding initialization driver program; Calling the initialization driver according to the built-in initialization entry function and registering the operation interface; The operating parameters are transmitted to the initialization driver according to the operation interface, and the driver boot instance is preloaded in combination with the digital signature; the operating parameters include operating frequency band, transmission power and air rate.

[0011] By adopting the above technical solution, the complete identifier is extracted and decrypted from the structured data into the hardware version number and manufacturer code identifier through a preset interpretation and extraction mechanism (such as regular expression parsing) and decryption algorithm (such as AES). The driver mapping table is used for hash matching (if the match is successful, the precise driver path is obtained in combination with the hardware version number; otherwise, the wildcard rule is applied based on the manufacturer code identifier to obtain all paths of the same series). After searching the driver library to obtain all initialized drivers, the compatible version range and program version information (major / minor / patch level) are extracted. The version similarity algorithm (such as cosine distance) is used to calculate the matching degree and sort in descending order (such as quick sort) in combination with the compatible range to select the optimal driver. The built-in initialization entry function is called to register the operation interface, the working parameters (working frequency band, transmission power, air rate) are transmitted, and the digital signature (such as RSA) is verified to pre-load the driver boot instance, thereby realizing automatic, highly compatible, safe and reliable dynamic driver loading, significantly improving the system initialization efficiency and anti-interference capability.

[0012] The present invention is further configured as follows: the specific steps of generating a graphical parameter configuration wizard according to the initialization driver and the module type code in the structured data include: Search the driver mapping table according to the structured data to obtain the module type code; Extracting data from the initialization driver according to the module type code to obtain a configuration description file; Mapping the configuration description file according to a preset metadata parser combined with parameter types to obtain a graphic parameter control and a parameter linkage skeleton; Filling the blank page according to the functional domain and the graphic parameter control to generate several configuration guide pages; According to the parameter linkage skeleton combined with the drive guide instance, all the configuration guide pages are associated and integrated to generate a graphical parameter configuration wizard.

[0013] By adopting the above technical solution, the module type code is determined by searching the driver mapping table through structured data, and the initialization driver is extracted based on this code to generate a configuration description file. The description file is mapped into a graphical parameter control and a parameter linkage skeleton using a metadata parser combined with parameter types. Based on the functional domain, the control is filled into a blank page to form a configuration guide page. Finally, the parameter linkage skeleton is used to associate the driver guidance instance, achieving dynamic fusion and logical connection of multiple pages, and automatically generating a graphical parameter configuration wizard. Through data-driven and meta-model parsing, zero-code visualization of the configuration process is achieved, significantly reducing development complexity. At the same time, the parameter linkage skeleton ensures the consistency and real-time performance of the cross-page control logic, significantly improving the efficiency and accuracy of parameter configuration for embedded devices or industrial software.

[0014] The present invention is further configured as follows: the specific steps of mapping the configuration description file according to a preset metadata parser in combination with the parameter type to obtain the graphic parameter control and the parameter linkage skeleton include: Parse the configuration description file using the preset metadata parser to extract working parameters and dependency expressions; Analyze all the working parameters according to the dependency condition expression and construct a parameter relationship diagram; Perform control mapping on all the working parameters according to parameter types to generate an initial graphic control; Compile the dependency condition expression according to the preset relationship parser to obtain the linkage execution logic and establish a parameter monitoring network; According to the parameter relationship diagram and the parameter modification event, the parameter monitoring network is monitored and updated to obtain a parameter network skeleton; Fitting the parameter network skeleton according to the linkage execution logic to obtain a parameter linkage skeleton; The initial graphic control is optimized according to the screen size to obtain a graphic parameter control.

[0015] By employing this technical solution, a metadata parser extracts configuration parameters and dependency expressions, constructs a parameter relationship graph, and maps them to initial controls. A relationship parser compiles dependency expressions into linkage execution logic, establishing a parameter monitoring network. When parameter modification events are triggered, the network is dynamically updated to generate a parameter network skeleton, which is then fitted using linkage logic. Finally, the control layout is optimized based on screen size. By integrating graph modeling (parameter relationship graph), event-driven monitoring (parameter monitoring network), and dynamic compilation (dependency expression compilation), automated linkage between parameter dependencies and adaptive rendering of visual controls are achieved, significantly improving the maintainability and interface responsiveness of complex configuration systems.

[0016] The present invention is further configured as follows: during the operation of the graphical parameter configuration wizard, the specific steps of collecting and displaying the working status waveform of the gateway module and verifying the configuration result include: When the graphical parameter configuration wizard is running, different gateway modules are parsed according to the preset protocol parser to obtain several customized decoding interfaces; Sampling the operation data of the gateway module according to a preset parameter sampling strategy to obtain module status metadata; Classifying the module status metadata according to data sources to obtain several types of indicator metadata; Performing waveform conversion on the indicator metadata according to the time series to obtain a working status waveform diagram; Verify the gateway module according to the preset detection logic, record the feedback mode of the graphic parameter control, and compare it with the corresponding standard feedback state; If the feedback mode is consistent with the standard feedback state, it indicates that the parameter network skeleton is correct, and the gateway module is subjected to instantaneous load testing, boundary value scanning and regression comparison according to a preset automated test sequence to calculate the module power consumption; If the power consumption of the module is greater than the power consumption limit threshold, the associated parameters are located according to the parameter network skeleton, and the corresponding associated parameters are corrected to generate a three-dimensional configuration verification table; the three-dimensional configuration verification table includes pass items, warning items, failure items, abnormal waveforms, performance comparisons and log fragments.

[0017] By adopting the above technical solution, a graphical wizard drives the protocol parser to generate a customized decoding interface. Based on the parameter sampling strategy, the gateway module operation data is collected and classified into indicator metadata, and then converted into a time series waveform to form a status monitoring diagram. The preset detection logic is used to verify the consistency of the graphic control feedback mode with the standard state. If a match is found, the automated test sequence (including instantaneous load, boundary value scanning and regression comparison) is started to calculate the module power consumption. If the limit is exceeded, the associated parameters are located and corrected through the parameter network skeleton. Finally, a three-dimensional configuration verification table (including pass / warning / fail items, abnormal waveforms, performance comparison and log fragments) is output, realizing closed-loop visual verification of the gateway configuration and intelligent parameter tuning, significantly improving the deployment efficiency and reliability of complex systems.

[0018] In a second aspect, the present invention also provides a visual configuration system based on a modular AI gateway, which adopts the following technical solutions: A modular AI gateway-based visualization configuration method, used in the modular AI gateway-based visualization configuration system, comprising: The hardware layer is used to detect the insertion signals of different gateway modules, transmit hardware information to the main control board, and integrate sensors and standardized interfaces in modular slots; The software layer is used to build a driver library and a configuration engine; the driver library is used to pre-store the drivers of all the gateway modules, and the configuration engine is used to generate corresponding parameter configuration logic according to the module type; The visualization layer is used to graphically display the guidance process of the parameter configuration logic through an interactive interface including a module status display area, a parameter configuration wizard area and a real-time waveform feedback area; The monitoring layer is used to monitor the boot process of the parameter configuration logic, extract abnormal configuration points, and generate corresponding abnormal processing logs in combination with the physical environment digital model.

[0019] By adopting the above technical solution, the modular slots and sensors of the hardware layer detect the insertion signal of the gateway module and transmit hardware information in real time. The software layer calls the pre-stored driver library based on the dynamic loading algorithm. At the same time, the configuration engine uses the rule matching algorithm to automatically generate parameter configuration logic suitable for different module types; the visualization layer uses a graphics rendering algorithm to dynamically display the configuration wizard process (including status display, parameter configuration guidance and real-time waveform feedback) in three dimensions in the interactive interface. The monitoring layer relies on the anomaly detection algorithm to analyze the configuration process in real time, combines the digital model of the physical environment for digital twin comparison, automatically locates the anomaly points and generates structured processing logs. Through algorithm collaboration, intelligent management of the entire life cycle of modules with plug-and-play, zero configuration coding and self-diagnosis of anomalies is realized.

[0020] In a third aspect, the present invention further provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods described in the above solutions.

[0021] In a fourth aspect, the present invention also provides a storage medium, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement a visual configuration method based on a modular AI gateway as in the above-mentioned scheme.

[0022] In summary, the beneficial technical effects of the present invention are: Automated hardware plugging and unplugging is linked to the visual configuration process, eliminating the need to manually install drivers or search for configuration documents. This shortens configuration time, improves deployment efficiency, and significantly reduces project implementation costs. Visual wizard guidance avoids parameter omissions or errors, reducing configuration error rates; Real-time feedback of the modular AI gateway status during the configuration process ensures the effectiveness of parameter adjustments and reduces the number of repeated debugging cycles. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flowchart of a visualization configuration method according to one embodiment of the present invention.

[0024] Figure 2 It is a flowchart of a visualization configuration method according to one embodiment of the present invention.

[0025] Figure 3 It is a flowchart of a visualization configuration method according to one embodiment of the present invention.

[0026] Figure 4 It is a structural diagram of a visualization configuration system according to one embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described in detail below with reference to the accompanying drawings. Example

[0028] Reference Figure 1 , a visualization configuration method based on a modular AI gateway disclosed in the present invention, comprising: S1: Identify and parse the gateway module, obtain the module's unique identifier, and encapsulate it into structured data; S2: Retrieve and load the corresponding initialization driver from the preset driver library according to the structured data; S3: Generate a graphical parameter configuration wizard according to the initialization driver and the module type code in the structured data; S4: During the running of the graphical parameter configuration wizard, collecting and displaying the working status waveform of the gateway module and verifying the configuration result; S5: Dynamically verify all working parameters according to a preset pre-check verification mechanism and the configuration result, and generate a parameter verification result; S6: Based on the parameter verification results, construct digital twins of different gateway modules, and calculate the module performance under extreme scenarios in combination with preset parameter adjustment strategies; S7: Based on the module performance and the environmental sensor network, a physical environment digital model is constructed, and a corresponding anti-interference configuration table is generated.

[0029] The implementation principle of this embodiment is as follows: first, the unique identifier of the gateway module (such as device_id) is securely identified through a dynamic token authentication mechanism (access_token) and encapsulated into structured data; based on this data, the matching initialization program in the preset driver library (supporting SQL Server, MySQL, HTTP, MQTT and other protocols) is loaded, and a graphical configuration wizard is generated in combination with the module type code; while the wizard is running, the module working status waveform is collected and visualized through the real-time stream processing engine, and the data of heterogeneous devices such as PLCs is dynamically parsed using the multi-protocol adaptation layer; after the configuration results are dynamically verified by the pre-check mechanism (including boundary value / conflict detection), a digital twin is constructed to simulate the performance of extreme scenarios (such as high load and electromagnetic interference); finally, the environmental sensor network data is integrated to construct a digital model of the physical environment, and the parameter adjustment strategy engine is used to generate an anti-interference configuration table (such as communication retry threshold and power consumption optimization plan), and a configuration version rollback mechanism is introduced to ensure fault tolerance, ultimately achieving a secure, compatible, and real-time gateway intelligent configuration closed loop. Example

[0030] The step S1 comprises: Performing load monitoring on the external interface slot to obtain a fluctuation signal and identify a gateway module; Initializing a communication bus according to the fluctuation signal to establish a data transmission channel; Positioning the address of the gateway module according to a preset storage mapping table and sending an analysis reading instruction; Extracting data from the gateway module according to the analysis reading instruction in combination with the data transmission channel to obtain a module unique identifier; Checking the module unique identifier, and if the check fails, sending a retransmission request to the gateway module; Otherwise, encapsulating the module unique identifier to obtain structured data.

[0031] The implementation principle of the embodiment is: through real-time high-precision load monitoring on the external interface slot, the system captures a fluctuation signal to identify a gateway module, and initializes a communication bus based on the signal to establish an encrypted data transmission channel, integrating a dynamic token authentication mechanism to prevent unauthorized access; subsequently, address positioning is performed using a preset storage mapping table, supporting multiple industrial protocols such as Modbus, CAN, and MQTT, ensuring protocol compatibility, and sending an analysis reading instruction; the module unique identifier is efficiently extracted through the channel, while CRC check and data integrity verification are performed to prevent data damage; if the check fails, the system automatically triggers a retransmission request, combining timeout control and abnormal log recording to realize fault-tolerant processing and avoid system crashes; after successful check, the unique identifier is encapsulated as structured data, millisecond-level response is achieved through optimized signal processing algorithms, and environmental sensor network data is fused to dynamically adjust monitoring parameters to cope with physical disturbances such as temperature and humidity, ultimately completing a reliable and adaptive module identification and data encapsulation process to ensure efficient operation of the system in complex industrial environments. Embodiment

[0032] The step S2 comprises: Extracting the structured data according to a preset interpretation extraction mechanism to obtain a complete identifier, and decrypting it into a hardware version number and a manufacturer code identifier; Matching the complete identifier according to a preset driver mapping table, and if the matching is successful, obtaining the corresponding driver file path in combination with the hardware version number; Otherwise, obtaining all driver file paths of the same series according to the manufacturer code identifier in combination with the wildcard rule; Performing driver search on a preset driver library according to all the driver file paths to obtain all initialization drivers; Extract information from all the initialization drivers to obtain compatible version ranges and program version information; the program version information includes a major version number, a minor version number, and a patch level; Calculating the matching degree of the complete identifiers and arranging them in descending order according to the program version information, and combining them with the compatible version interval to obtain the corresponding initialization driver program; Calling the initialization driver according to the built-in initialization entry function and registering the operation interface; The operating parameters are transmitted to the initialization driver according to the operation interface, and the driver boot instance is preloaded in combination with the digital signature; the operating parameters include operating frequency band, transmission power and air rate.

[0033] The implementation principles of this embodiment are as follows: a complete identifier is extracted from structured data through a preset interpretation and extraction mechanism and decrypted into a hardware version number and vendor code identifier, with enhanced digital signature verification ensuring data integrity. Subsequently, a match is performed based on a driver mapping table. Upon success, the driver file path is obtained in combination with the hardware version number. Upon failure, the vendor code identifier and wildcard rules are used to obtain all paths in the same series. Automatic retry and timeout control are also integrated to handle exceptions. All initialized drivers are then retrieved from a preset driver library, performance is optimized through a caching mechanism, and compatible version ranges and program version information (including major version number, minor version number, and patch level) are extracted. The version matching degree is calculated and sorted in descending order. The optimal driver is selected based on the compatible range, and dynamic updates are supported to adapt to new devices. After calling a built-in initialization entry function to register an operation interface, operating parameters (such as operating frequency band, transmit power, and air data rate) are transmitted through the interface. These parameters are dynamically adjusted based on environmental sensor data. The digital signature is verified to preload the driver boot instance, ultimately achieving a secure, efficient, and adaptive driver initialization and operation process. Example

[0034] Reference Figure 2 , the step S3 comprises: S31: Search the driver mapping table according to the structured data to obtain the module type code; S32: extracting data from the initialization driver according to the module type code to obtain a configuration description file; S33: Mapping the configuration description file according to a preset metadata parser combined with parameter types to obtain a graphic parameter control and a parameter linkage skeleton; S34: Filling the blank page according to the functional domain and the graphic parameter control to generate several configuration guide pages; S35: According to the parameter linkage skeleton and the driving guide instance, all the configuration guide pages are associated and integrated to generate a graphical parameter configuration wizard.

[0035] The implementation principle of this embodiment is as follows: based on structured data retrieval, the driver mapping table is used to obtain the module type code. After ensuring the security of the data source through digital signature verification, the configuration description file is extracted from the initialization driver according to the module type code. Subsequently, the preset metadata parser maps the description file into graphic parameter controls (such as sliders, drop-down menus) and parameter linkage skeletons (defining the logical dependencies between controls) in combination with parameter types (such as enumeration values ​​and numerical ranges), and embeds real-time verification rules to enhance the legitimacy of the parameters. Next, the graphic parameter controls are dynamically filled into blank pages according to the functional domain to generate several configuration guide pages, using a responsive layout to adapt to different terminals and optimizing performance through lazy loading technology. Finally, the parameter linkage skeleton is combined with the driver guidance instance to associate and merge all pages to generate a unified graphical parameter configuration wizard. The user status is automatically saved during the process and abnormal rollback is supported, ensuring the efficiency and robustness of the configuration process, and ultimately achieving safe, intuitive and adaptive hardware driver parameter configuration. Example

[0036] Reference Figure 3 , the step S33 includes: S331: Parsing the configuration description file using a preset metadata parser to extract working parameters and dependency condition expressions; S332: Analyze all the working parameters according to the dependency condition expression and construct a parameter relationship diagram; S333: Perform control mapping on all the working parameters according to parameter types to generate an initial graphic control; S334: Compile the dependency condition expression according to a preset relationship parser to obtain linkage execution logic and establish a parameter monitoring network; S335: Monitoring and updating the parameter monitoring network according to the parameter relationship diagram and the parameter modification event to obtain a parameter network skeleton; S336: Fitting the parameter network skeleton according to the linkage execution logic to obtain a parameter linkage skeleton; S337: Optimize the initial graphic control according to the screen size to obtain a graphic parameter control.

[0037] The implementation principle of the embodiment is: after the configuration description file is safely checked by the preset metadata parser, the working parameters and dependent condition expressions are extracted, and the logic legality is ensured through syntax checking; then the parameter relationship graph with loop detection is constructed by analyzing the expressions, and the initial graphical control is generated according to the parameter type mapping; at the same time, the relationship parser compiles the expressions into linkage execution logic in real time, and establishes a parameter monitoring network based on event throttling and dependent pruning; when the user triggers the parameter modification event, the parameter relationship graph is dynamically updated and the parameter network skeleton is generated, and then the parameter linkage skeleton is formed through the fitting of the linkage logic and the skeleton; finally, the initial control is optimized for touch hot area and responds to the reorganization according to the screen size, pixel density and direction, to generate a cross-terminal adaptive graphical parameter control, supporting log tracking and abnormal rollback throughout the process, and realizing high-robustness hardware parameter dynamic configuration. Embodiment

[0038] The step S4 comprises: When the graphical parameter configuration wizard is running, different gateway modules are parsed according to the preset protocol parser to obtain a plurality of customized decoding interfaces; According to the preset parameter sampling strategy, the running data of the gateway module is sampled to obtain module state metadata; According to the data source, the module state metadata is classified to obtain a plurality of class index metadata; According to the time sequence, the index metadata is waveform converted to obtain a working state waveform graph; According to the preset detection logic, the gateway module is verified, the feedback mode of the graphical parameter control is recorded, and compared with the corresponding standard feedback state; If the feedback mode is consistent with the standard feedback state, it indicates that the parameter network skeleton is correct, and the gateway module is tested for instantaneous load, boundary value scanning and regression comparison according to the preset automatic test sequence, and the module power consumption is calculated; If the module power consumption is greater than the power consumption limit threshold, the associated parameters are located according to the parameter network skeleton, and the corresponding associated parameters are corrected to generate a three-dimensional configuration verification table; the three-dimensional configuration verification table includes pass items, warning items, failure items, abnormal waveforms, performance comparisons and log segments.

[0039] The implementation principle of this embodiment is as follows: the gateway customized protocol is loaded through the dynamic adaptation layer of the protocol parser, a decoding interface is generated, and the sampling strategy is dynamically adjusted according to the working condition perception engine to obtain classified indicator metadata; then, the waveform conversion and fault annotation of the time series data are performed in combination with the abnormal waveform feature library to generate a working status waveform diagram; at the same time, the detection logic quantifies the interactive feedback of the graphic control into latency / accuracy indicators, and verifies the correctness of the parameter network skeleton through multi-dimensional similarity comparison with the standard state; if the verification passes, the automated test sequence is started to perform load scanning and regression comparison. When the module power consumption exceeds the limit, the parameter-power consumption mapping model is called to locate the associated parameters and generate an optimized solution. Finally, a three-dimensional configuration verification table containing abnormal waveform annotations, performance comparisons and AI optimization logs is output to realize closed-loop intelligent parameter adjustment of the gateway module.

[0040] In this embodiment, a 2U standard rack-mounted body is adopted, with the domestically produced Xinwei RX3588 as the core, and it has extremely rich interface types. It adopts a highly modular design, and deploys POE network, storage, serial port, low current sampling, input and output signal control, 4G / 5G communication, LORA, WIFI, Bluetooth and other interfaces on different functional modules, which enhances the scalability of the product, facilitates users to choose different functional combinations, and greatly improves the maintainability of the product; a unified interface specification (such as Linux udev rules) is used to manage all module drivers to ensure compatibility when new modules are connected; configuration wizard templates are preset for different types of modules (communication, sampling, and control), and the corresponding templates are called through the module type code; the WebSocket protocol is used to achieve millisecond-level data transmission between the main control board and the visual interface to ensure that there is no delay in waveform feedback. Example

[0041] Reference Figure 4 , a visual configuration system based on a modular AI gateway, applied to the fault detection method, comprising: The hardware layer is used to detect the insertion signals of different gateway modules, transmit hardware information to the main control board, and integrate sensors and standardized interfaces in modular slots; The software layer is used to build a driver library and a configuration engine; the driver library is used to pre-store the drivers of all the gateway modules, and the configuration engine is used to generate corresponding parameter configuration logic according to the module type; The visualization layer is used to graphically display the guidance process of the parameter configuration logic through an interactive interface including a module status display area, a parameter configuration wizard area and a real-time waveform feedback area; The monitoring layer is used to monitor the boot process of the parameter configuration logic, extract abnormal configuration points, and generate corresponding abnormal processing logs in combination with the physical environment digital model.

[0042] The implementation principle of this embodiment is as follows: the hardware layer pre-processes the insertion signal and operation data of the gateway module in real time through integrated sensors and edge computing units, and transmits them to the main control board through a standardized interface; the software layer calls the driver library to match the module type, and the configuration engine combines the knowledge graph to generate anti-interference parameter configuration logic, and dynamically projects the configuration path on the modular slot through the AR guidance technology of the visualization layer; the monitoring layer synchronously collects configuration process data, uses the digital model of the physical environment to compare abnormal configuration points and generate diagnostic logs, and at the same time feeds back to the knowledge graph to optimize the prediction rules, finally forming a closed-loop configuration verification system of "signal perception-intelligent guidance-abnormal self-healing-model iteration", realizing zero-contact adjustment and predictive maintenance of the gateway module. Example

[0043] An electronic device, comprising: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods described in the above solutions. Example

[0044] A storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement a visual configuration method based on a modular AI gateway as described above. The embodiments of this specific implementation method are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A visual configuration method based on a modular AI gateway, characterized in that: include: Identify and parse the gateway module, obtain the module's unique identifier, and encapsulate it into structured data; According to the structured data, the corresponding initialization driver in the preset driver library is retrieved and loaded; Generate a graphical parameter configuration wizard according to the initialization driver and the module type code in the structured data; During the operation of the graphical parameter configuration wizard, the working status waveform of the gateway module is collected and displayed, and the configuration result is verified.

2. The visualization configuration method based on modular AI gateway according to claim 1 is characterized in that: The specific steps of identifying and parsing the gateway module, obtaining the module unique identifier, and encapsulating it into structured data include: Monitor the external interface slot for loading, obtain fluctuation signals, and identify the gateway module; Initializing the communication bus according to the fluctuation signal to establish a data transmission channel; Address the gateway module according to a preset storage mapping table and send a parsing read instruction; Extract data from the gateway module according to the parsing and reading instruction in combination with the data transmission channel to obtain a unique module identifier; Verifying the module unique identifier, and if the verification fails, sending a retransmission request to the gateway module; Otherwise, the module unique identifier is encapsulated to obtain structured data.

3. The visualization configuration method based on modular AI gateway according to claim 1 is characterized in that: The specific steps of retrieving and loading the corresponding initialization driver program in the preset driver library according to the structured data include: The structured data is extracted according to the preset interpretation and extraction mechanism to obtain a complete identifier, which is then decrypted into the hardware version number and manufacturer code identifier; Matching the complete identifier according to a preset driver mapping table, and if the match is successful, obtaining the corresponding driver file path in combination with the hardware version number; Otherwise, all driver file paths of the same series are obtained according to the manufacturer code identifier combined with the wildcard rule; Performing a driver search on a preset driver library according to all the driver file paths to obtain all initialized driver programs; Extract information from all the initialization drivers to obtain compatible version ranges and program version information; the program version information includes a major version number, a minor version number, and a patch level; Calculating the matching degree of the complete identifiers and arranging them in descending order according to the program version information, and combining them with the compatible version interval to obtain the corresponding initialization driver program; Calling the initialization driver according to the built-in initialization entry function and registering the operation interface; The operating parameters are transmitted to the initialization driver according to the operation interface, and the driver boot instance is preloaded in combination with the digital signature; the operating parameters include operating frequency band, transmission power and air rate.

4. The visualization configuration method based on modular AI gateway according to claim 1 is characterized in that: The specific steps of generating a graphical parameter configuration wizard based on the initialization driver and the module type code in the structured data include: Search the driver mapping table according to the structured data to obtain the module type code; Extracting data from the initialization driver according to the module type code to obtain a configuration description file; Mapping the configuration description file according to a preset metadata parser combined with parameter types to obtain a graphic parameter control and a parameter linkage skeleton; Filling the blank page according to the functional domain and the graphic parameter control to generate several configuration guide pages; According to the parameter linkage skeleton combined with the drive guide instance, all the configuration guide pages are associated and integrated to generate a graphical parameter configuration wizard.

5. The method for visual configuration based on modular AI gateway according to claim 4, characterized in that: The specific steps of mapping the configuration description file according to the preset metadata parser and the parameter type to obtain the graphic parameter control and the parameter linkage skeleton include: Parse the configuration description file using the preset metadata parser to extract working parameters and dependency expressions; Analyze all the working parameters according to the dependency condition expression and construct a parameter relationship diagram; Perform control mapping on all the working parameters according to parameter types to generate an initial graphic control; Compile the dependency condition expression according to the preset relationship parser to obtain the linkage execution logic and establish a parameter monitoring network; According to the parameter relationship diagram and the parameter modification event, the parameter monitoring network is monitored and updated to obtain a parameter network skeleton; Fitting the parameter network skeleton according to the linkage execution logic to obtain a parameter linkage skeleton; The initial graphic control is optimized according to the screen size to obtain a graphic parameter control.

6. The method for visual configuration based on modular AI gateway according to claim 1, characterized in that: The specific steps of collecting and displaying the working status waveform of the gateway module and verifying the configuration results during the operation of the graphical parameter configuration wizard include: When the graphical parameter configuration wizard is running, different gateway modules are parsed according to the preset protocol parser to obtain several customized decoding interfaces; Sampling the operation data of the gateway module according to a preset parameter sampling strategy to obtain module status metadata; Classifying the module status metadata according to data sources to obtain several types of indicator metadata; Performing waveform conversion on the indicator metadata according to the time series to obtain a working status waveform diagram; Verify the gateway module according to the preset detection logic, record the feedback mode of the graphic parameter control, and compare it with the corresponding standard feedback state; If the feedback mode is consistent with the standard feedback state, it indicates that the parameter network skeleton is correct, and the gateway module is subjected to instantaneous load testing, boundary value scanning and regression comparison according to a preset automated test sequence to calculate the module power consumption; If the power consumption of the module is greater than the power consumption limit threshold, the associated parameters are located according to the parameter network skeleton, and the corresponding associated parameters are corrected to generate a three-dimensional configuration verification table; the three-dimensional configuration verification table includes pass items, warning items, failure items, abnormal waveforms, performance comparisons and log fragments.

7. The visualization configuration method based on modular AI gateway according to claim 1 is characterized in that: The visualization configuration method further includes: Dynamically verify all working parameters based on the preset pre-check mechanism and configuration results to generate parameter verification results; Based on the parameter verification results, digital twins of different gateway modules are constructed, and combined with preset parameter adjustment strategies, module performance under extreme scenarios is calculated; According to the module performance and the environmental sensor network, a physical environment digital model is constructed and a corresponding anti-interference configuration table is generated.

8. A visual configuration system based on modular AI gateway, characterized in that: include: The hardware layer is used to detect the insertion signals of different gateway modules, transmit hardware information to the main control board, and integrate sensors and standardized interfaces in modular slots; The software layer is used to build a driver library and a configuration engine; the driver library is used to pre-store the drivers of all the gateway modules, and the configuration engine is used to generate corresponding parameter configuration logic according to the module type; The visualization layer is used to graphically display the guidance process of the parameter configuration logic through an interactive interface including a module status display area, a parameter configuration wizard area and a real-time waveform feedback area; The monitoring layer is used to monitor the boot process of the parameter configuration logic, extract abnormal configuration points, and generate corresponding abnormal processing logs in combination with the physical environment digital model.

9. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A storage medium storing at least one instruction, at least one program, a code set, or an instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the visualization configuration method based on the modular AI gateway as described in claims 1 to 7.

Images