Waterproof socket remote control system and method based on Internet of Things

Abstract

The invention relates to the technical field of waterproof sockets, and discloses a waterproof socket remote control system and method based on the Internet of Things, and the system comprises a data collection module, a signal detection module, a software detection module, a firmware detection module, an environment detection module and a signal feedback module. The system realizes comprehensive monitoring, intelligent optimization and anomaly detection of equipment, and compared with traditional Internet of Things socket equipment, the system not only has the functions of real-time monitoring and intelligent adjustment, but also can automatically adjust the running state of the equipment through an accurate data analysis and feedback mechanism, so that the safety of the equipment is improved. The safety, the stability and the environmental adaptability of the socket are remarkably improved, meanwhile, the fault occurrence possibility is reduced through the high automation and optimization capability of the system, the maintenance cost is reduced, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of waterproof sockets, and in particular to a remote control system and method for waterproof sockets based on the Internet of Things. Background Art

[0002] With the rapid development of IoT technology, intelligent management has become a future trend across various industries. As a crucial component of information technology, the IoT connects sensors and devices to the internet, enabling real-time data collection, analysis, and feedback. It is widely used in smart homes, environmental monitoring, smart grids, and other fields. In these applications, IoT intelligent hardware is gradually replacing traditional devices, enhancing product intelligence and user experience. Specifically, in the field of IoT waterproof sockets, IoT combines traditional socket equipment with sensing and data processing technologies, enabling remote control and real-time monitoring via the internet, thereby improving device reliability and intelligence. The application of IoT technology, especially in complex environments, enables more flexible and precise management of waterproof sockets.

[0003] While existing IoT waterproof socket systems have made initial progress in remote control and monitoring, they still have some significant shortcomings. First, over the long term, waterproof socket devices are subject to a variety of external environmental factors, such as humidity fluctuations, water immersion, UV radiation, and electromagnetic interference. These factors can cause device performance degradation or even malfunction. While existing IoT waterproof socket systems offer data collection and remote control capabilities, they lack anomaly detection and optimization capabilities, hindering real-time, accurate monitoring of device status. In particular, when dealing with the impact of multiple environmental factors, existing systems struggle to effectively perform dynamic optimization based on real-time data.

[0004] Therefore, we propose a waterproof socket remote control system based on the Internet of Things to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a waterproof socket remote control system and method based on the Internet of Things to solve the problems raised by the above background technology.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solutions: a remote control system for waterproof sockets based on the Internet of Things, comprising a data acquisition module, a signal detection module, a software detection module, a firmware detection module, an environment detection module, and a signal feedback module;

[0007] The data acquisition module is used to detect and extract data from the waterproof socket, and pre-process and reorganize the extracted multiple parameters to generate a first data group, a second data group, and a third data group;

[0008] The signal detection module is used to analyze the first data group, the second data group and the third data group to determine whether the socket is abnormal;

[0009] The software detection module is used to perform data analysis on the first data group, determine whether the software has abnormalities based on the analysis results, and optimize the software;

[0010] The firmware detection module is used to perform data analysis on the second data group, determine whether the current firmware has an abnormality based on the analysis result, and optimize it;

[0011] The environment detection module is used to perform data analysis on the third data group, determine whether there is an abnormality in the current environment based on the analysis results, and perform optimization;

[0012] The signal feedback module is used to provide feedback on multiple optimization results.

[0013] Preferably, the data acquisition module includes a data acquisition unit and a data preprocessing unit;

[0014] The data acquisition unit is used to detect and advance data on the waterproof socket and the environment, including software execution time, memory usage, packet loss rate, code coverage, log recording frequency, current load, voltage fluctuation, relay contact resistance, temperature change rate, battery current, humidity change rate, water immersion conductivity, external temperature change rate, ultraviolet radiation intensity and electromagnetic interference intensity;

[0015] The data preprocessing unit is used to preprocess the acquired multiple data and perform dimensionless conversion, and organize the processed multiple parameters into a first data group, a second data group, and a third data group;

[0016] The first data set includes software execution time A, memory usage B, packet loss rate C, code coverage D, and log recording frequency E;

[0017] The second data set includes current load F, voltage fluctuation G, relay contact resistance H, temperature change rate I, and battery current J;

[0018] The third data set includes humidity change rate K, water immersion conductivity L, external temperature change rate M, ultraviolet radiation intensity N, and electromagnetic interference intensity O.

[0019] Preferably, the signal detection module includes a signal data calculation unit and a signal data analysis unit;

[0020] The signal data calculation unit is used to extract data from the first data group, the second data group, and the third data group, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the signal anomaly coefficient SAI. The specific calculation formula is as follows:

[0021]

[0022] Where: A is the software execution time, B is the memory usage, C is the packet loss rate, D is the code coverage, E is the logging frequency, F is the current load, G is the voltage fluctuation, H is the relay contact resistance, I is the temperature change rate, J is the battery current, K is the humidity change rate, L is the water immersion conductivity, M is the external temperature change rate, N is the ultraviolet radiation intensity, and O is the electromagnetic interference intensity;

[0023] The signal data analysis unit is used to perform data analysis on the signal anomaly coefficient SAI obtained by calculation, and the specific steps are as follows:

[0024] When SAI < 0.56, it means that there is no abnormality in the current waterproof socket;

[0025] When SZI ≥ 0.56, it means that the current waterproof socket is abnormal and the analysis program is started.

[0026] Preferably, the software detection module includes a software data calculation unit and a software data analysis unit;

[0027] The software data calculation unit is used to extract data from the first data group, including software execution time A, memory usage B, packet loss rate C, code coverage D, and log recording frequency E, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the software reference coefficient RYC. The specific calculation formula is as follows;

[0028]

[0029] Where: A is the software execution time, B is the memory usage, C is the packet loss rate, D is the code coverage, and E is the logging frequency;

[0030] The software data analysis unit is used to perform data analysis on the calculated software reference coefficient RYC, and determine whether the current software needs to be optimized based on the analysis results. The specific steps are as follows:

[0031] When RYC<0.45, it means that there is no abnormality in the current software;

[0032] When RYC ≥ 0.45, it means that when an exception occurs in the software, the parameter curves within 10 seconds before and after the exception are extracted from the system log. The inflection point is observed using visualization tools, the log level is adjusted to DEBUG, all function entries and exits are recorded, module-level memory snapshots are activated, and queues are used to maintain data from the past 5 minutes. The threshold is updated in real time. Before the system load is too high or a resource bottleneck occurs, the system behavior is automatically adjusted to ensure the stable operation of the core functions and reduce the probability of exception triggering. A software optimization data set is generated, including optimization of software execution time YA, optimization of memory usage YB, optimization of packet loss rate YC, optimization of code coverage YD, and optimization of logging frequency YE.

[0033] Preferably, the software detection module further includes a software optimization calculation unit and a software optimization analysis unit;

[0034] The software data analysis unit is used to extract data from the software optimization data group, including optimizing software execution time YA, optimizing memory usage YB, optimizing data packet loss rate YC, optimizing code coverage YD, and optimizing log recording frequency YE, and input the extracted multiple data into the pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the optimized software reference coefficient YRY. The specific calculation formula is as follows:

[0035]

[0036] Where: optimize software execution time YA, optimize memory usage YB, optimize packet loss rate YC, optimize code coverage YD and optimize logging frequency YE;

[0037] The software optimization analysis unit is used to perform data analysis on the calculated optimization software reference coefficient YRY, and judge whether the software optimization is effective according to the analysis results, specifically in the following manner:

[0038] When RYC ≥ 0.33, it means that the current software optimization is effective;

[0039] When RYC < 0.56, it means that the software optimization is invalid and a feedback warning is sent.

[0040] Preferably, the firmware detection module includes a firmware data calculation unit and a firmware data analysis unit;

[0041] The firmware data calculation unit is used to extract data from the second data group, including current load F, voltage fluctuation G, relay contact resistance H, temperature change rate I, and battery current J, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the firmware reference coefficient GJC. The specific calculation formula is as follows:

[0042]

[0043] Where: F is the current load, G is the voltage fluctuation, H is the relay contact resistance, I is the temperature change rate, and J is the battery current

[0044] The firmware data analysis unit is used to perform data analysis on the calculated firmware reference coefficient GJC, and determine whether the current firmware is abnormal based on the analysis result, in the following specific manner;

[0045] When GJC≤0.55, it means that there is no abnormality in the current firmware;

[0046] When GJC>0.55, it means that the current firmware is abnormal and needs to be optimized. A firmware optimization data set is generated including current load YF, voltage fluctuation YG, relay contact resistance YH, temperature change rate YI and battery current YJ.

[0047] Preferably, the firmware detection module further includes a firmware optimization calculation unit and a firmware optimization analysis unit;

[0048] The firmware optimization calculation unit is used to extract data from the firmware optimization data group, including inputting the extracted multiple data into a pre-trained deep learning framework, performing feature fusion through a multi-layer neural network, and then calculating the optimized firmware reference coefficient YGJ. The specific formula is as follows:

[0049]

[0050] Where: YF is the current load, YG is the voltage fluctuation, YH is the relay contact resistance, YI is the temperature change rate, and YJ is the battery current;

[0051] The firmware optimization analysis unit is used to perform data analysis on the calculated optimized firmware reference coefficient YGJ, and judge whether the current firmware optimization is effective according to the analysis result. The specific steps are as follows:

[0052] When YGJ<0.33, it means that the current firmware optimization is effective;

[0053] When YGJ ≥ 0.33, it means that the firmware optimization is invalid and a feedback warning is sent.

[0054] Preferably, the environmental detection module includes an environmental data calculation unit and an environmental data analysis unit. The environmental data calculation unit is used to extract data from the third data group, including humidity change rate K, water immersion conductivity L, external temperature change rate M, ultraviolet radiation intensity N, and electromagnetic interference intensity O, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the environmental reference coefficient HJC. The specific calculation formula is as follows:

[0055]

[0056] Where: K is the humidity change rate, L is the water immersion conductivity, M is the external temperature change rate, N is the ultraviolet radiation intensity, and O is the electromagnetic interference intensity;

[0057] The environmental data analysis unit is used to analyze the data obtained by calculation and determine whether the current environment is abnormal based on the analysis results. The specific steps are as follows:

[0058] When HJC≤0.65, it means that there is no abnormality in the current environment;

[0059] When HJC>0.65, it means that the current environment is abnormal and needs to be optimized. An environmental optimization data set is generated, including the optimized humidity change rate YK, optimized water immersion conductivity YL, optimized external temperature change rate YM, optimized ultraviolet radiation intensity YN, and optimized electromagnetic interference intensity YO.

[0060] Preferably, the environment detection module further includes an environment optimization calculation unit and an environment optimization analysis unit;

[0061] The environmental optimization calculation unit is used to extract data from the environmental optimization data set, including optimizing the humidity change rate YK, optimizing the water immersion conductivity YL, optimizing the external temperature change rate YM, optimizing the ultraviolet radiation intensity YN, and optimizing the electromagnetic interference intensity YO. The extracted multiple data are input into the pre-trained deep learning framework, and feature fusion is performed through a multi-layer neural network to calculate the optimized environmental reference coefficient YHJ. The specific formula is as follows:

[0062]

[0063] Where: YK is the optimized humidity change rate, YL is the optimized water immersion conductivity, YM is the optimized external temperature change rate, YN is the optimized ultraviolet radiation intensity, and YO is the optimized electromagnetic interference intensity;

[0064] The environmental optimization analysis unit is used to perform data analysis on the calculated optimized environmental reference coefficient YHJ and determine whether the environmental optimization is effective based on the analysis results. The specific steps are as follows:

[0065] When YHJ<0.33, it means that the current environment optimization is effective;

[0066] When YHJ ≥ 0.33, it means that the environment optimization is invalid and a feedback warning is sent.

[0067] This application also includes a remote control method for a waterproof socket based on the Internet of Things, the specific steps are as follows:

[0068] S1. Detecting and extracting data from the waterproof socket using the data acquisition module, and preprocessing and reorganizing the extracted parameters to generate a first data group, a second data group, and a third data group;

[0069] S2. Analyze the first data group, the second data group, and the third data group by the signal detection module to determine whether the socket is abnormal;

[0070] S3, performing data analysis on the first data group using the software detection module, determining whether the software has an abnormality based on the analysis results, and optimizing the software;

[0071] S4. Analyze the second data set by the firmware detection module, determine whether the current firmware has an abnormality based on the analysis result, and optimize the firmware;

[0072] S5. Analyze the third data set using the environment detection module, determine whether the current environment is abnormal based on the analysis results, and perform optimization.

[0073] S6. Feedback of multiple optimization results is performed through the signal feedback module.

[0074] Compared with the prior art, the present invention has the following beneficial effects:

[0075] 1. By introducing multiple modules, the system enables comprehensive device monitoring, intelligent optimization, and anomaly detection. Compared to traditional IoT sockets, this system not only features real-time monitoring and intelligent adjustment, but also automatically adjusts the device's operating status through precise data analysis and feedback mechanisms, significantly improving the socket's safety, stability, and environmental adaptability. Furthermore, the system's high degree of automation and optimization capabilities reduce the likelihood of failures, lower maintenance costs, and enhance the user experience.

[0076] 2. By categorizing and organizing different types of data, such as software-related data, current load, and electromagnetic interference, into distinct primary, secondary, and tertiary data groups, the system can conduct refined analysis targeting different aspects of the problem. For example, software-related data such as execution time and memory usage and hardware performance data such as current load and temperature fluctuations are processed separately. This allows each module to focus on optimizing specific areas, avoiding overly complex comprehensive analysis and improving the overall efficiency of the system. By combining and preprocessing multiple parameters, data acquisition module 1 provides a solid data foundation for modules such as signal detection, software detection, and firmware detection. This enables the system to dynamically adjust device operating status based on real-time data, promptly identifying potential issues and optimizing them. By comprehensively monitoring environmental factors such as humidity changes and electromagnetic interference, as well as device performance data such as current load and temperature fluctuations, the system can provide stable operation support under various environmental conditions, enhancing the adaptability and safety of waterproof sockets. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a system flow chart of the present invention.

[0078] Figure 2 A diagram showing the steps of the method of the present invention.

[0079] In the figure: 1. Data acquisition module; 11. Data acquisition unit; 12. Data preprocessing unit; 2. Signal detection module; 21. Signal data calculation unit; 22. Signal data analysis unit; 3. Software detection module; 31. Software data calculation unit; 32. Software data analysis unit; 33. Software optimization calculation unit; 34. Software optimization analysis unit; 4. Firmware detection module; 41. Firmware data calculation unit; 42. Firmware data analysis unit; 43. Firmware optimization calculation unit; 44. Firmware optimization analysis unit; 5. Environment detection module; 51. Environment data calculation unit; 52. Environment data analysis unit; 53. Environment optimization calculation unit; 54. Environment optimization analysis unit; 6. Signal feedback module. DETAILED DESCRIPTION

[0080] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0081] Example 1: Please refer to Figure 1, a waterproof socket remote control system based on the Internet of Things, including a data acquisition module 1, a signal detection module 2, a software detection module 3, a firmware detection module 4, an environment detection module 5 and a signal feedback module 6;

[0082] The data acquisition module 1 is used to detect and extract data from the waterproof socket, and pre-process and reorganize the extracted multiple parameters to generate a first data group, a second data group, and a third data group;

[0083] The signal detection module 2 is used to analyze the first data group, the second data group and the third data group to determine whether the socket has any abnormality;

[0084] The software detection module 3 is used to perform data analysis on the first data group, determine whether there is any abnormality in the software based on the analysis results, and optimize the software;

[0085] The firmware detection module 4 is used to perform data analysis on the second data group, determine whether the current firmware has an abnormality based on the analysis result, and optimize it;

[0086] The environment detection module 5 is used to perform data analysis on the third data group, determine whether there is an abnormality in the current environment based on the analysis results, and perform optimization;

[0087] The signal feedback module 6 is used to provide feedback on multiple optimization results.

[0088] In this embodiment, Data Acquisition Module 1 is responsible for real-time detection and extraction of various operating parameters of the waterproof outlet. This module preprocesses and categorizes the collected data, generating first, second, and third data sets, and producing structured data output. By comprehensively monitoring multiple key parameters of the outlet, such as current load, voltage fluctuations, temperature changes, and humidity, the Data Acquisition Module provides accurate data support for subsequent analysis and optimization. This module effectively improves data accuracy and reliability, ensuring that subsequent modules can make analyses and decisions based on accurate data, thereby ensuring device safety and performance stability.

[0089] Signal Detection Module 2 analyzes the first, second, and third data sets output by Data Acquisition Module 1 to identify any abnormalities in the waterproof socket. Through in-depth analysis of multiple parameters, this module accurately determines whether the socket's operating status is within normal range and promptly detects any potential abnormalities. For example, if the current load exceeds a safe range or the temperature fluctuates abnormally, the module will react quickly, issuing an alarm and initiating a repair process. By accurately monitoring abnormalities, Signal Detection Module 2 improves the system's response to potential faults and ensures the socket's stable operation in various operating environments.

[0090] Software Detection Module 3 specifically analyzes the first data set, focusing on key software-related metrics such as software execution time, memory usage, and packet loss rate. By processing and analyzing this data, the module can determine whether the software has any anomalies and promptly optimize it. In particular, when software performance bottlenecks or anomalies are discovered, the system can automatically adjust relevant parameters or optimize the code, thereby improving the software's operational efficiency. By enhancing the software's stability and fault tolerance, Software Detection Module 3 effectively prevents system crashes or performance degradation caused by software failures, thereby improving the overall reliability of the system.

[0091] Firmware Detection Module 4 analyzes the data in the second data set, assessing the current firmware operating status and identifying any anomalies. By analyzing firmware-related parameters such as current load, voltage fluctuation, and relay contact resistance, Firmware Detection Module 4 can initiate a firmware optimization process upon detecting a firmware anomaly, promptly adjusting firmware settings or updating the firmware version to ensure proper hardware operation. This module's optimization measures effectively improve the long-term stability and anti-interference capabilities of the waterproof socket, thereby extending the device's service life and reducing the incidence of failures caused by firmware issues.

[0092] Environmental Detection Module 5 is responsible for analyzing data related to environmental factors in the third data set, including humidity changes, water immersion conductivity, and ultraviolet radiation intensity. By monitoring and analyzing environmental data, the module can determine in real time whether any environmental anomalies are occurring and perform corresponding optimization based on the analysis results. For example, if humidity is too high or water immersion conductivity is abnormal, the system will take preventative measures and automatically adjust the device's operating state to prevent operation in unsuitable environmental conditions. Environmental Detection Module 5 effectively improves the waterproof socket's adaptability in complex or harsh environments, ensuring its stability and safety.

[0093] Signal Feedback Module 6 provides comprehensive feedback on the optimization results of each of the aforementioned modules, ensuring that all optimization measures are promptly reflected in the actual operation of the device. By providing feedback on optimization results, the system can dynamically adjust the device's operating parameters to ensure that the socket is always in optimal working condition. Signal Feedback Module 6 enables the system to self-regulate and automatically repair, significantly improving the device's automation level and operating efficiency. The introduction of this module significantly enhances the system's adaptive capabilities, reduces manual intervention, and improves device reliability.

[0094] By integrating multiple modules, the system enables comprehensive device monitoring, intelligent optimization, and anomaly detection. Compared to traditional IoT sockets, this system not only features real-time monitoring and intelligent adjustment, but also automatically adjusts the device's operating status through precise data analysis and feedback mechanisms, significantly improving the socket's safety, stability, and environmental adaptability. Furthermore, the system's high degree of automation and optimization capabilities reduce the likelihood of failures, lower maintenance costs, and enhance the user experience.

[0095] Example 2: Please refer to Figure 1 , the data acquisition module 1 includes a data acquisition unit 11 and a data preprocessing unit 12;

[0096] The data acquisition unit 11 is used to detect and monitor the waterproof socket and its environment, including software execution time, memory usage, packet loss rate, code coverage, log recording frequency, current load, voltage fluctuation, relay contact resistance, temperature change rate, battery current, humidity change rate, water immersion conductivity, external temperature change rate, ultraviolet radiation intensity, and electromagnetic interference intensity.

[0097] The data preprocessing unit 12 is used to preprocess the acquired multiple data and perform dimensionless conversion, and organize the processed multiple parameters into a first data group, a second data group, and a third data group;

[0098] The first data set includes software execution time A, memory usage B, packet loss rate C, code coverage D, and log recording frequency E;

[0099] The second data set includes current load F, voltage fluctuation G, relay contact resistance H, temperature change rate I, and battery current J;

[0100] The third data set includes humidity change rate K, water immersion conductivity L, external temperature change rate M, ultraviolet radiation intensity N, and electromagnetic interference intensity O.

[0101] In this embodiment, the data acquisition unit 11 can monitor and collect multiple important parameters of the waterproof socket and its environment in real time, including software execution time, memory usage, packet loss rate, current load, and more. This comprehensive data coverage provides a deep understanding of the device's performance and external environmental changes, providing accurate data for subsequent analysis. This multi-dimensional monitoring approach ensures that the device can be fully evaluated under various operating conditions.

[0102] The data preprocessing unit 12 is responsible for preprocessing and dimensionlessizing the collected data, resolving discrepancies between different data units and dimensions and ensuring data uniformity and comparability. The data is organized into first, second, and third data groups, providing standardized input for subsequent analysis and decision-making, reducing data noise and inconsistencies, and improving the accuracy of subsequent anomaly detection and optimization processing.

[0103] By categorizing and organizing different types of data, such as software-related data, current load, and electromagnetic interference, into distinct primary, secondary, and tertiary data groups, the system can conduct refined analysis targeting different aspects of the problem. For example, software-related data such as execution time and memory usage and hardware performance data such as current load and temperature fluctuations are processed separately, allowing each module to focus on optimizing specific areas, avoiding overly complex comprehensive analysis and improving the overall efficiency of the system. By combining and preprocessing multiple parameters, data acquisition module 1 provides a solid data foundation for modules such as signal detection, software detection, and firmware detection. This enables the system to dynamically adjust device operating status based on real-time data, promptly identifying potential issues and optimizing them. By comprehensively monitoring environmental factors such as humidity changes and electromagnetic interference, as well as device performance data such as current load and temperature fluctuations, the system can provide stable operation support under various environmental conditions, enhancing the adaptability and safety of waterproof sockets.

[0104] Example 3: Please refer to Figure 1 , the signal detection module 2 includes a signal data calculation unit 21 and a signal data analysis unit 22;

[0105] The signal data calculation unit 21 is used to extract data from the first data group, the second data group, and the third data group, and input the extracted multiple data into the pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the signal anomaly coefficient SAI. The specific calculation formula is as follows:

[0106]

[0107] Where: A is the software execution time, B is the memory usage, C is the packet loss rate, D is the code coverage, E is the logging frequency, F is the current load, G is the voltage fluctuation, H is the relay contact resistance, I is the temperature change rate, J is the battery current, K is the humidity change rate, L is the water immersion conductivity, M is the external temperature change rate, N is the ultraviolet radiation intensity, and O is the electromagnetic interference intensity;

[0108] The signal data analysis unit 22 is used to perform data analysis on the calculated signal anomaly coefficient SAI, and the specific steps are as follows:

[0109] When SAI < 0.56, it means that there is no abnormality in the current waterproof socket;

[0110] When SZI ≥ 0.56, it means that the current waterproof socket is abnormal and the analysis program is started.

[0111] In this embodiment, the signal data calculation unit 21 significantly enhances the intelligence of anomaly detection by inputting data into a pretrained deep learning framework and utilizing a multi-layer neural network for feature fusion. Compared to traditional rule-based methods, the deep learning framework automatically extracts underlying patterns from large amounts of historical data without the need for manual rule setting, thereby improving the system's adaptability and accuracy. This method not only identifies complex nonlinear relationships but also enables more accurate predictions of potential equipment issues, effectively enhancing the intelligence and automation of anomaly detection.

[0112] By calculating the Signal Anomaly Index (SAI), the system can comprehensively quantify the impact of various data types and perform multi-dimensional analysis using formulas. Specifically, the SAI calculation formula incorporates several key parameters, such as software execution time, memory usage, current load, and voltage fluctuation. These parameters are weighted to reflect the device's status under different environments and operating conditions. When the SAI value exceeds a set threshold, such as 0.56, the system deems the device anomaly and promptly initiates analysis to diagnose the problem. This quantitative assessment method effectively avoids errors caused by human judgment and improves the reliability and accuracy of anomaly detection.

[0113] The signal data calculation unit 21 leverages the correlations between different data types by integrating multiple data sets, such as software, hardware, and environmental data. This multi-dimensional data integration enables the system to comprehensively assess the socket's operating status by taking into account various operational factors, avoiding potential misjudgments or omissions caused by a single data source. This approach significantly improves the comprehensiveness and accuracy of anomaly detection, ensuring the system's efficient operation in complex environments.

[0114] The signal data analysis unit 22 performs real-time analysis of the calculated SAI and automatically determines whether the device is experiencing an anomaly based on the results. When the SAI value is below the threshold, the device is operating normally; when the SAI exceeds the threshold, the system immediately initiates further analysis. This automated process significantly reduces manual intervention and improves response speed, enabling the device to react quickly to anomalies and avoiding potential damage or failures caused by delayed processing.

[0115] Signal Detection Module 2 significantly enhances the intelligent monitoring capabilities of the waterproof socket system through deep learning technology and a quantitative anomaly detection mechanism. Compared to traditional methods, this module not only automatically processes and analyzes multi-dimensional data but also provides a more accurate and efficient solution for anomaly detection by calculating the SAI signal anomaly coefficient. This advanced technology enables the system to demonstrate greater accuracy and responsiveness in real-time monitoring and early warning, ensuring the reliability and stability of the waterproof sockets in various environments, significantly improving the overall security of the device and the user experience.

[0116] Example 4: Please refer to Figure 1 , the software detection module 3 includes a software data calculation unit 31 and a software data analysis unit 32;

[0117] The software data calculation unit 31 is used to extract data from the first data group, including software execution time A, memory usage B, packet loss rate C, code coverage D, and log recording frequency E, and input the extracted data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the software reference coefficient RYC. The specific calculation formula is as follows:

[0118]

[0119] Where: A is the software execution time, B is the memory usage, C is the packet loss rate, D is the code coverage, and E is the logging frequency;

[0120] The software data analysis unit 32 is used to perform data analysis on the calculated software reference coefficient RYC and, based on the analysis results, determine whether the current software needs to be optimized. The specific steps are as follows:

[0121] When RYC<0.45, it means that there is no abnormality in the current software;

[0122] When RYC ≥ 0.45, it means that when an exception occurs in the software, the parameter curves within 10 seconds before and after the exception are extracted from the system log. The inflection point is observed using visualization tools, the log level is adjusted to DEBUG, all function entries and exits are recorded, module-level memory snapshots are activated, and queues are used to maintain data from the past 5 minutes. The threshold is updated in real time. Before the system load is too high or a resource bottleneck occurs, the system behavior is automatically adjusted to ensure the stable operation of the core functions and reduce the probability of exception triggering. A software optimization data set is generated, including optimization of software execution time YA, optimization of memory usage YB, optimization of packet loss rate YC, optimization of code coverage YD, and optimization of logging frequency YE.

[0123] In this embodiment, the software data calculation unit 31 utilizes a deep learning framework and multi-layer neural networks to perform feature fusion on multiple parameters, including software execution time, memory usage, packet loss rate, code coverage, and logging frequency. This advanced technology automatically extracts key features from large amounts of historical data, enabling in-depth analysis of potential bottlenecks and issues in software operation. This avoids the limitations of manually defined rules and significantly enhances the system's ability to identify software anomalies. Compared to traditional rule-based approaches, the deep learning framework offers greater adaptability and accuracy, enabling real-time adaptation to diverse operating environments and usage scenarios.

[0124] By calculating the software reference coefficient (RYC), the system quantifies the overall performance of the software and uses a formula to comprehensively evaluate various key indicators. When the RYC value exceeds a preset threshold, such as 0.45, it indicates that the software may be experiencing performance anomalies or bottlenecks. This quantitative evaluation method makes the software optimization process more systematic, avoiding the subjective errors of manual judgment. Through this automated evaluation mechanism, the system can efficiently and accurately identify software issues and promptly initiate optimization processes to ensure that the software always maintains optimal performance.

[0125] After analyzing the software reference coefficient RYC, the software data analysis unit 32 can determine whether the software needs optimization based on the real-time data analysis results. If the RYC value exceeds 0.45, the system automatically extracts the parameter curves within 10 seconds before and after the anomaly and uses visualization tools to draw an inflection point graph. This visualization method helps developers intuitively identify anomalies in software operation. In addition, by adjusting log levels, activating memory snapshots, and updating thresholds in real time, the system can effectively record and adjust software behavior, ensuring the stable operation of core functions and avoiding excessive system load or resource bottlenecks.

[0126] When software requires optimization, the system automatically generates optimization data sets, including key metrics such as execution time, memory usage, and packet loss rate. These optimization measures effectively improve software efficiency, reduce resource consumption, and mitigate the risk of system crashes or performance degradation caused by software anomalies. Through continuous optimization and adjustment, the system achieves dynamic optimization, ensuring the software remains efficient and stable over the long term.

[0127] Component Detection Module 3, through deep learning and automated optimization mechanisms, has brought significant technological advancements to the IoT waterproof socket system. Compared to traditional manual inspection and manual optimization methods, the deep learning framework and quantitative evaluation of the software reference coefficient (RYC) improve the accuracy and efficiency of software anomaly detection. Furthermore, through visualization tools, memory snapshots, logging, and other technical means, the system can efficiently and in real time adjust software behavior to ensure the stability of core functions. The introduction of this module enables the system to self-optimize and dynamically adjust, improving the overall stability and performance of the device, reducing the probability of failure, and providing users with a more reliable smart device experience.

[0128] Example 5: Please refer to Figure 1 , the software detection module 3 also includes a software optimization calculation unit 33 and a software optimization analysis unit 34;

[0129] The software data analysis unit 32 is used to extract data from the software optimization data group, including optimizing software execution time YA, optimizing memory usage YB, optimizing packet loss rate YC, optimizing code coverage YD, and optimizing log recording frequency YE, and input the extracted multiple data into the pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the optimized software reference coefficient YRY. The specific calculation formula is as follows:

[0130]

[0131] Where: optimize software execution time YA, optimize memory usage YB, optimize packet loss rate YC, optimize code coverage YD and optimize logging frequency YE;

[0132] The software optimization analysis unit 34 is used to perform data analysis on the calculated optimization software reference coefficient YRY and determine whether the software optimization is effective based on the analysis results. The specific method is as follows:

[0133] When RYC ≥ 0.33, it means that the current software optimization is effective;

[0134] When RYC < 0.56, it means that the software optimization is invalid and a feedback warning is sent.

[0135] In this embodiment, the software optimization calculation unit 33 significantly enhances the intelligence and accuracy of the optimization process by inputting optimization data into a pre-trained deep learning framework and utilizing a multi-layer neural network for feature fusion. This technical approach automatically extracts and integrates multiple optimization data points, such as optimized software execution time and memory usage, through deep learning, enabling more accurate assessment of software performance under different operating conditions. Compared to traditional rule-based optimization methods, deep learning frameworks can dynamically learn and adapt to changing system states and environmental conditions, providing a more efficient and flexible solution for software optimization.

[0136] By calculating the optimization software reference coefficient YRY, the system can quantitatively evaluate the optimization effect. Specifically, the optimization software reference coefficient combines multiple optimization parameters such as optimization execution time, memory usage, and packet loss rate, providing a clear digital indicator for improving software performance. The weighting method in the calculation formula reasonably reflects the impact of different optimization indicators on software performance, ensuring that the system can effectively adjust according to the most important parameters. Compared with traditional optimization methods, quantitative evaluation criteria make the software optimization process more scientific and transparent, avoiding the limitations of relying solely on experience and subjective judgment.

[0137] The software optimization analysis unit 34 performs real-time analysis of the optimization software reference coefficient YRY and, based on the results, determines the effectiveness of the optimization measures. When the YRY value is above 0.33, it indicates that the optimization has achieved the desired effect. Conversely, when the YRY value falls below 0.56, the system issues a feedback warning and initiates further optimization or adjustment measures. This automated evaluation and feedback mechanism not only improves the efficiency of software optimization but also ensures the system's ability to self-adjust and continuously improve, thereby reducing the need for human intervention and enhancing the overall intelligence level of the device.

[0138] This module dynamically adapts to varying system loads and operating conditions by calculating and optimizing the software's reference coefficient, YRY, in real time, continuously optimizing and adjusting. When software performance falls short of expectations, the system automatically issues a warning and adjusts the optimization strategy based on this feedback. This adaptive optimization capability enables the system to maintain efficient and stable operation in a constantly changing environment and promptly address emerging performance bottlenecks and issues, thereby enhancing the long-term reliability of the waterproof socket system.

[0139] Through the automated optimization mechanism comprised of the software optimization calculation unit 33 and the software optimization analysis unit 34, the system independently completes the entire process from data extraction, optimization calculation, to effect evaluation, significantly enhancing the automated management capabilities of the equipment. Furthermore, by providing timely feedback on optimization results, the system is able to self-heal and continuously optimize, reducing manual intervention, lowering operation and maintenance costs, and improving system stability and reliability.

[0140] Software Detection Module 3, by introducing a deep learning framework and quantitative evaluation mechanism, provides significant technological advancements in the optimization and adaptive adjustment of waterproof socket systems. Compared to traditional manual optimization methods, the application of deep learning and multi-layer neural networks improves the intelligence, accuracy, and automation of the optimization process.

[0141] By optimizing the calculation of the software reference coefficient YRY, the system can quantify the optimization effect and automatically adjust the strategy when necessary, thereby ensuring continuous improvement in software performance and efficient and stable system operation. These improvements enable the device to maintain stability and efficiency in a dynamically changing environment, improving the long-term reliability of the device and user experience.

[0142] Example 6: Please refer to Figure 1 , the firmware detection module 4 includes a firmware data calculation unit 41 and a firmware data analysis unit 42;

[0143] The firmware data calculation unit 41 is used to extract data from the second data group, including current load F, voltage fluctuation G, relay contact resistance H, temperature change rate I, and battery current J, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the firmware reference coefficient GJC. The specific calculation formula is as follows:

[0144]

[0145] Where: F is the current load, G is the voltage fluctuation, H is the relay contact resistance, I is the temperature change rate, and J is the battery current;

[0146] The firmware data analysis unit 42 is used to perform data analysis on the calculated firmware reference coefficient GJC and determine whether the current firmware is abnormal based on the analysis results. The specific method is as follows:

[0147] When GJC≤0.55, it means that there is no abnormality in the current firmware;

[0148] When GJC>0.55, it means that the current firmware is abnormal and needs to be optimized. A firmware optimization data set is generated including current load YF, voltage fluctuation YG, relay contact resistance YH, temperature change rate YI and battery current YJ.

[0149] In this embodiment, the firmware data calculation unit 41 utilizes a deep learning framework to perform feature fusion on multiple data points, including current load, voltage fluctuation, relay contact resistance, temperature change rate, and battery current, through a multi-layer neural network. Compared to traditional rule-based analysis methods, the deep learning framework can automatically learn and extract potential nonlinear relationships from complex data, further improving the accuracy and adaptability of firmware anomaly detection. This approach eliminates the need for pre-set manual rules and can adjust the analysis model in real time based on the device's historical operating data and current status, making firmware detection more intelligent and efficient.

[0150] By calculating the firmware reference coefficient (GJC), the system quantifies the firmware's health and performs a comprehensive assessment based on key indicators such as current load, voltage fluctuation, relay contact resistance, temperature change rate, and battery current. This calculation formula weights each parameter to accurately reflect their impact on firmware performance, providing an accurate and quantifiable evaluation standard for firmware status. Compared to traditional qualitative analysis methods, this quantitative evaluation approach makes firmware anomaly detection more objective and transparent, and provides clearer optimization directions.

[0151] The firmware data analysis unit 42 analyzes the firmware reference coefficient (GJC) and determines whether there are any firmware anomalies based on the calculated results. When the GJC value exceeds 0.55, indicating a firmware anomaly, the system automatically initiates an optimization process, generating a firmware optimization data set containing optimized values ​​for current load, voltage fluctuation, relay contact resistance, temperature change rate, and battery current. This automated detection and optimization mechanism ensures that the firmware responds quickly to anomalies and automatically adjusts relevant parameters to improve firmware performance and stability.

[0152] Firmware Detection Module 4 significantly reduces the need for manual intervention through automated firmware anomaly detection and optimization feedback. Traditional methods typically rely on manual analysis of the causes of device failures or performance degradation. The introduction of this module enables the system to automatically diagnose firmware issues and implement optimization measures. This automated processing enables the system to respond more quickly and accurately, reducing errors caused by human error and improving overall system reliability and efficiency.

[0153] Example 7: Please refer to Figure 1 , the firmware detection module 4 also includes a firmware optimization calculation unit 43 and a firmware optimization analysis unit 44;

[0154] The firmware optimization calculation unit 43 is used to extract data from the firmware optimization data group, including inputting the extracted multiple data into a pre-trained deep learning framework, performing feature fusion through a multi-layer neural network, and then calculating the optimized firmware reference coefficient YGJ. The specific formula is as follows:

[0155]

[0156] Where: YF is the current load, YG is the voltage fluctuation, YH is the relay contact resistance, YI is the temperature change rate, and YJ is the battery current;

[0157] The firmware optimization analysis unit 44 is used to perform data analysis on the calculated optimized firmware reference coefficient YGJ and determine whether the current firmware optimization is effective based on the analysis results. The specific steps are as follows:

[0158] When YGJ<0.33, it means that the current firmware optimization is effective;

[0159] When YGJ ≥ 0.33, it means that the firmware optimization is invalid and a feedback warning is sent.

[0160] In this embodiment, the firmware optimization calculation unit 43 utilizes a deep learning framework, combined with a multi-layer neural network, to process the firmware optimization data set and calculate the optimized firmware reference coefficient YGJ through feature fusion. This approach offers significant advantages over traditional rule-based optimization methods. The deep learning framework can automatically extract deep features from large amounts of data and, through learning optimization patterns, flexibly adapt to different firmware and environmental changes. Compared to manually set rules, the deep learning framework can dynamically adjust the optimization strategy, making firmware optimization more precise and intelligent.

[0161] By calculating the optimized firmware reference coefficient YGJ, the system quantifies the effectiveness of firmware optimization and conducts a comprehensive evaluation based on parameters such as current load, voltage fluctuation, relay contact resistance, temperature change rate, and battery current. This calculation formula weights each optimization parameter to effectively reflect the impact of different optimization measures on firmware performance, thereby providing a clear quantitative indicator of the firmware optimization effect. This quantitative evaluation method ensures the accuracy of firmware optimization and avoids the limitations of previous reliance on experience and manual judgment, thereby enhancing the scientific nature and transparency of firmware optimization.

[0162] The firmware optimization analysis unit 44 automatically determines the effectiveness of firmware optimization by analyzing the optimized firmware reference coefficient YGJ in real time. When YGJ is less than 0.33, the firmware optimization is effective, and the system will continue with the current optimization strategy. When YGJ is greater than or equal to 0.33, the system automatically triggers a feedback warning, indicating that the current optimization is ineffective, and initiates further optimization measures. This automated mechanism reduces manual intervention, improves system response speed and processing efficiency, and ensures that firmware optimization is quickly and accurately reflected in device performance.

[0163] This optimization module not only monitors the effectiveness of firmware optimization but also adaptively adjusts the optimization strategy based on feedback. If it detects that an optimization measure isn't achieving the expected results, the system automatically adjusts the strategy and re-executes the optimization calculation. This flexibility enables the system to continuously optimize under changing operating environments and varying load conditions, ensuring optimal performance over the long term.

[0164] The firmware optimization calculation unit 43 and the firmware optimization analysis unit 44 together form a self-healing optimization mechanism, enabling the system to automatically optimize based on the device's actual operating status and performance requirements. This not only improves the device's adaptability but also reduces reliance on manual intervention and lowers maintenance costs. Through this intelligent firmware optimization, the system can automatically identify and take action when performance issues arise, improving the device's stability and long-term reliability.

[0165] Firmware Optimization Module 4 significantly enhances the firmware optimization capabilities of the waterproof socket system by introducing a deep learning framework and quantitative evaluation mechanism. Compared with traditional firmware optimization methods, deep learning technology can provide more accurate and intelligent optimization solutions, enabling the system to dynamically adjust optimization strategies based on real-time data to ensure that the firmware is always in optimal operating condition. By optimizing the quantitative evaluation of the firmware reference coefficient YGJ, the system can objectively and scientifically judge the optimization effect and automatically trigger optimization measures, thereby improving the stability, performance, and reliability of the firmware. This module not only enhances the device's adaptive and self-healing capabilities, but also improves the system's degree of automation and overall intelligence, providing users with a more efficient and reliable device experience.

[0166] Example 8: Please refer to Figure 1 The environment detection module 5 includes an environment data calculation unit 51 and an environment data analysis unit 52. The environment data calculation unit 51 is used to extract data from the third data group, including the humidity change rate K, water immersion conductivity L, external temperature change rate M, ultraviolet radiation intensity N, and electromagnetic interference intensity O, and input the extracted multiple data into the pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the environmental reference coefficient HJC. The specific calculation formula is as follows:

[0167]

[0168] Where: K is the humidity change rate, L is the water immersion conductivity, M is the external temperature change rate, N is the ultraviolet radiation intensity, and O is the electromagnetic interference intensity;

[0169] The environmental data analysis unit 52 is used to analyze the data obtained by calculation and determine whether the current environment is abnormal based on the analysis results. The specific steps are as follows:

[0170] When HJC≤0.65, it means that there is no abnormality in the current environment;

[0171] When HJC>0.65, it means that the current environment is abnormal and needs to be optimized. An environmental optimization data set is generated, including the optimized humidity change rate YK, optimized water immersion conductivity YL, optimized external temperature change rate YM, optimized ultraviolet radiation intensity YN, and optimized electromagnetic interference intensity YO.

[0172] In this embodiment, the environmental data calculation unit 51 improves the intelligence and accuracy of environmental detection by inputting multiple environmental data items, such as humidity change rate, water immersion conductivity, and external temperature change rate, into a pre-trained deep learning framework and performing feature fusion via a multi-layer neural network. Traditional environmental detection methods rely on fixed rules and thresholds and are difficult to cope with the dynamic changes in complex environments. However, the deep learning framework can dynamically adapt to various environmental changes by learning the underlying relationships in environmental data, improving the system's responsiveness to complex environmental factors. This method is more intelligent than traditional experience-based rule processing and can automatically identify and process a variety of changing factors in the environment.

[0173] By calculating the environmental reference coefficient (HJC), the system quantifies the impact of various environmental factors on device performance, integrating data such as humidity change rate, water conductivity, external temperature change rate, UV radiation intensity, and electromagnetic interference intensity. This quantitative assessment method enables the system to clearly and objectively determine whether the environment is outside the normal range, avoiding the misjudgment caused by the complex and changing environmental factors used in traditional methods. The HJC calculation formula combines the weights of different environmental factors, allowing the system to accurately assess the combined impact of multiple environmental factors on the device, further improving the accuracy of environmental monitoring.

[0174] The environmental data analysis unit 52 performs real-time analysis of the calculated environmental reference coefficient (HJC) to determine whether any environmental anomalies are present. When the HJC value exceeds a set threshold, such as 0.65, the system automatically identifies the environmental anomaly and generates an environmental optimization data set, including optimization data such as humidity change rate, water immersion conductivity, and external temperature change rate. This automated environmental anomaly detection and optimization feedback mechanism ensures that the device can respond promptly to harsh environmental conditions, adjusting its operating status and avoiding failures caused by environmental factors that excessively impact device operation. This mechanism enables the system to react quickly based on real-time monitoring, ensuring the device's stable operation to the greatest extent possible.

[0175] By introducing the environmental reference coefficient (HJC) and an optimization feedback mechanism, the system achieves enhanced environmental adaptability. When environmental conditions change, the system automatically analyzes environmental data and takes appropriate optimization measures. For example, in environments with high humidity or strong UV radiation, the system automatically adjusts the device's operating state to mitigate the negative impact of the environment. This ensures stable operation of the device in a variety of environments, significantly improving its reliability and adaptability.

[0176] By precisely monitoring and optimizing environmental factors, the system effectively mitigates the negative impact of the environment on equipment and reduces the risk of equipment failure in harsh environments. For example, in situations of extreme humidity or drastic temperature fluctuations, the system can promptly adjust equipment status to prevent malfunction or damage caused by these environmental factors. This not only reduces equipment failure rates but also extends equipment life, improving the overall economic benefits of operations.

[0177] Example 9: Please refer to Figure 1 , the environment detection module 5 also includes an environment optimization calculation unit 53 and an environment optimization analysis unit 54;

[0178] The environmental optimization calculation unit 53 is used to extract data from the environmental optimization data set, including optimizing the humidity change rate YK, optimizing the water immersion conductivity YL, optimizing the external temperature change rate YM, optimizing the ultraviolet radiation intensity YN, and optimizing the electromagnetic interference intensity YO. The extracted multiple data are input into the pre-trained deep learning framework, and feature fusion is performed through a multi-layer neural network to calculate the optimized environmental reference coefficient YHJ. The specific formula is as follows:

[0179]

[0180] Where: YK is the optimized humidity change rate, YL is the optimized water immersion conductivity, YM is the optimized external temperature change rate, YN is the optimized ultraviolet radiation intensity, and YO is the optimized electromagnetic interference intensity;

[0181] The environmental optimization analysis unit 54 is used to perform data analysis on the calculated optimized environmental reference coefficient YHJ and determine whether the environmental optimization is effective based on the analysis results. The specific steps are as follows:

[0182] When YHJ<0.33, it means that the current environment optimization is effective;

[0183] When YHJ ≥ 0.33, it means that the environment optimization is invalid and a feedback warning is sent.

[0184] In this embodiment, the environmental optimization calculation unit 53 significantly enhances the intelligence and accuracy of environmental optimization by inputting the optimized environmental data into a pretrained deep learning framework and performing feature fusion via a multi-layer neural network. Compared to traditional environmental optimization methods, the deep learning framework can automatically identify and learn the complex relationships between environmental parameters, adapting to changing environmental conditions in real time. This approach eliminates the need for manually setting complex rules or thresholds, enabling flexible adjustment of optimization strategies, further improving the system's adaptability and responsiveness to varying environmental conditions.

[0185] By calculating the optimized environmental reference coefficient (YHJ), the system can quantify the optimization effects of various environmental factors, such as humidity, water conductivity, and temperature fluctuations. This formula combines multiple optimized environmental parameters to reflect the contribution of each factor to the overall environmental optimization effect. Compared with traditional environmental optimization methods, this quantitative assessment approach makes the environmental optimization process more precise and easier to monitor, avoiding the limitations of relying on manually set rules and ensuring the scientific and controllable optimization results.

[0186] The environmental optimization analysis unit 54 performs real-time analysis of the optimized environmental reference coefficient YHJ and, based on the results, determines whether the optimization is effective. When YHJ is less than 0.33, the system deems the optimization effective and maintains the current optimization state. When YHJ is greater than or equal to 0.33, the system triggers a feedback warning, indicating that the current optimization effect is ineffective and initiating further optimization measures. This automated feedback mechanism reduces manual intervention and ensures that the system can promptly identify and adjust ineffective optimization strategies, thereby improving the efficiency and accuracy of the overall optimization effect.

[0187] This module monitors and analyzes real-time environmental data, enabling the system to dynamically adjust optimization measures based on current environmental conditions. By continuously optimizing environmental factors such as humidity, water conductivity, and UV radiation intensity, the system ensures stable device operation in changing environments. For example, in environments with extreme humidity or high UV radiation, the system automatically adjusts environmental conditions to protect the device from external environmental influences, ensuring optimal operation at all times.

[0188] By automatically optimizing environmental parameters and adjusting equipment operating conditions in real time, the system significantly reduces the risk of equipment failures caused by environmental factors. For example, in the event of excessive electromagnetic interference or severe temperature fluctuations, the system can quickly respond and adjust equipment parameters to prevent failures. This effectively improves equipment stability and reduces failure rates, thereby extending equipment life and reducing maintenance costs.

[0189] Environmental Optimization Module 5 utilizes a deep learning framework and quantitative evaluation mechanism to achieve intelligent optimization and dynamic adjustment of environmental factors. Compared to traditional manual optimization methods, this system can automatically identify and optimize a variety of environmental factors, such as humidity, temperature fluctuations, and electromagnetic interference, improving the stability and reliability of the device in various environments. By optimizing the environmental reference coefficient YHJ and adjusting the optimization strategy through an automatic feedback mechanism, the system maintains efficient and stable operation, avoiding ineffective optimization and the shortcomings of manual intervention. Furthermore, continuous environmental optimization significantly reduces equipment failure rates and improves long-term operational reliability, providing users with a more intelligent and efficient device management solution.

[0190] This application also includes a remote control method for waterproof sockets based on the Internet of Things, see Figure 2 , the specific steps are as follows:

[0191] S1. Detecting and extracting data from the waterproof socket through the data acquisition module 1, and preprocessing and reorganizing the extracted multiple parameters to generate a first data group, a second data group, and a third data group;

[0192] S2. Analyze the first data group, the second data group, and the third data group through the signal detection module 2 to determine whether the socket is abnormal;

[0193] S3, performing data analysis on the first data group by the software detection module 3, determining whether the software has an abnormality based on the analysis results and optimizing the software;

[0194] S4, performing data analysis on the second data group by the firmware detection module 4, determining whether the current firmware has an abnormality based on the analysis result and optimizing it;

[0195] S5, performing data analysis on the third data group through the environment detection module 5, judging whether there is an abnormality in the current environment based on the analysis results and performing optimization;

[0196] S6. Feedback of multiple optimization results is performed through the signal feedback module 6.

[0197] The contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0198] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A waterproof socket remote control system based on the Internet of Things, characterized by: It includes a data acquisition module (1), a signal detection module (2), a software detection module (3), a firmware detection module (4), an environment detection module (5) and a signal feedback module (6); The data acquisition module (1) is used to detect and extract data from the waterproof socket, and pre-process and reorganize the extracted multiple parameters to generate a first data group, a second data group, and a third data group; The signal detection module (2) is used to analyze the first data group, the second data group and the third data group to determine whether the socket has an abnormality; The software detection module (3) is used to perform data analysis on the first data group, determine whether the software has an abnormality based on the analysis result, and optimize the software; The firmware detection module (4) is used to perform data analysis on the second data group, determine whether the current firmware has an abnormality based on the analysis result, and optimize it; The environment detection module (5) is used to perform data analysis on the third data group, determine whether the current environment is abnormal based on the analysis results, and perform optimization; The signal feedback module (6) is used to provide feedback on multiple optimization results.

2. The remote control system for waterproof sockets based on the Internet of Things according to claim 1, characterized in that: The data acquisition module (1) includes a data acquisition unit (11) and a data preprocessing unit (12); The data acquisition unit (11) is used to detect and pre-process data of the waterproof socket and the environment, including software execution time, memory usage, packet loss rate, code coverage, log recording frequency, current load, voltage fluctuation, relay contact resistance, temperature change rate, battery current, humidity change rate, water immersion conductivity, external temperature change rate, ultraviolet radiation intensity, and electromagnetic interference intensity; The data preprocessing unit (12) is used to preprocess the acquired multiple data and perform dimensionless conversion, and organize the processed multiple parameters into a first data group, a second data group, and a third data group; The first data set includes software execution time A, memory usage B, packet loss rate C, code coverage D, and log record frequency E; The second data set includes current load F, voltage fluctuation G, relay contact resistance H, temperature change rate I, and battery current J; The third data set includes humidity change rate K, water immersion conductivity L, external temperature change rate M, ultraviolet radiation intensity N, and electromagnetic interference intensity O.

3. The remote control system for waterproof sockets based on the Internet of Things according to claim 2, characterized in that: The signal detection module (2) includes a signal data calculation unit (21) and a signal data analysis unit (22); The signal data calculation unit (21) is used to extract data from the first data group, the second data group, and the third data group, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the signal anomaly coefficient SAI. The specific calculation formula is as follows: Where: A is the software execution time, B is the memory usage, C is the packet loss rate, D is the code coverage, E is the logging frequency, F is the current load, G is the voltage fluctuation, H is the relay contact resistance, I is the temperature change rate, J is the battery current, K is the humidity change rate, L is the water immersion conductivity, M is the external temperature change rate, N is the ultraviolet radiation intensity, and O is the electromagnetic interference intensity; The signal data analysis unit (22) is used to perform data analysis on the signal anomaly coefficient SAI obtained by calculation, and the specific steps are as follows: When SAI < 0.56, it means that there is no abnormality in the current waterproof socket; When SZI ≥ 0.56, it means that the current waterproof socket is abnormal and the analysis program is started.

4. The remote control system for waterproof sockets based on the Internet of Things according to claim 3, characterized in that: The software detection module (3) includes a software data calculation unit (31) and a software data analysis unit (32); The software data calculation unit (31) is used to extract data from the first data group, including software execution time A, memory usage B, packet loss rate C, code coverage D, and log recording frequency E, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the software reference coefficient RYC. The specific calculation formula is as follows: Where: A is the software execution time, B is the memory usage, C is the packet loss rate, D is the code coverage, and E is the logging frequency; The software data analysis unit (32) is used to perform data analysis on the calculated software reference coefficient RYC, and to determine whether the current software needs to be optimized based on the analysis results. The specific steps are as follows: When RYC<0.45, it means that there is no abnormality in the current software; When RYC ≥ 0.45, it means that when an exception occurs in the software, the parameter curves within 10 seconds before and after the exception are extracted from the system log. The inflection point is observed using visualization tools, the log level is adjusted to DEBUG, all function entries and exits are recorded, module-level memory snapshots are activated, and queues are used to maintain data from the past 5 minutes. The threshold is updated in real time. Before the system load is too high or a resource bottleneck occurs, the system behavior is automatically adjusted to ensure the stable operation of the core functions and reduce the probability of exception triggering. A software optimization data set is generated, including optimization of software execution time YA, optimization of memory usage YB, optimization of packet loss rate YC, optimization of code coverage YD, and optimization of logging frequency YE.

5. The remote control system for waterproof sockets based on the Internet of Things according to claim 4, characterized in that: The software detection module (3) further includes a software optimization calculation unit (33) and a software optimization analysis unit (34); The software data analysis unit (32) is used to extract data from the software optimization data group, including optimizing software execution time YA, optimizing memory usage YB, optimizing data packet loss rate YC, optimizing code coverage YD and optimizing log recording frequency YE, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the optimized software reference coefficient YRY. The specific calculation formula is as follows: Where: optimize software execution time YA, optimize memory usage YB, optimize packet loss rate YC, optimize code coverage YD and optimize logging frequency YE; The software optimization analysis unit (34) is used to perform data analysis on the optimized software reference coefficient YRY obtained by calculation, and judge whether the software optimization is effective according to the analysis result, in the following specific manner: When RYC ≥ 0.33, it means that the current software optimization is effective; When RYC < 0.56, it means that the software optimization is invalid and a feedback warning is sent.

6. The remote control system for waterproof sockets based on the Internet of Things according to claim 5, characterized in that: The firmware detection module (4) includes a firmware data calculation unit (41) and a firmware data analysis unit (42); The firmware data calculation unit (41) is used to extract data from the second data group, including current load F, voltage fluctuation G, relay contact resistance H, temperature change rate I and battery current J, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the firmware reference coefficient GJC. The specific calculation formula is as follows: Where: F is the current load, G is the voltage fluctuation, H is the relay contact resistance, I is the temperature change rate, and J is the battery current; The firmware data analysis unit (42) is used to perform data analysis on the firmware reference coefficient GJC obtained by calculation, and judge whether the current firmware is abnormal based on the analysis result, in the following specific manner; When GJC≤0.55, it means that there is no abnormality in the current firmware; When GJC>0.55, it means that the current firmware is abnormal and needs to be optimized. A firmware optimization data set is generated including current load YF, voltage fluctuation YG, relay contact resistance YH, temperature change rate YI and battery current YJ.

7. The Internet of Things-based waterproof socket remote control system according to claim 6, characterized in that: The firmware detection module (4) further includes a firmware optimization calculation unit (43) and a firmware optimization analysis unit (44); The firmware optimization calculation unit (43) is used to extract data from the firmware optimization data group, including inputting the extracted multiple data into a pre-trained deep learning framework, performing feature fusion through a multi-layer neural network, and then calculating and obtaining the optimized firmware reference coefficient YGJ. The specific formula is as follows: Where: YF is the current load, YG is the voltage fluctuation, YH is the relay contact resistance, YI is the temperature change rate, and YJ is the battery current; The firmware optimization analysis unit (44) is used to perform data analysis on the calculated optimized firmware reference coefficient YGJ, and judge whether the current firmware optimization is effective according to the analysis result. The specific steps are as follows: When YGJ<0.33, it means that the current firmware optimization is effective; When YGJ ≥ 0.33, it means that the firmware optimization is invalid and a feedback warning is sent.

8. The Internet of Things-based waterproof socket remote control system according to claim 7, characterized in that: The environmental detection module (5) includes an environmental data calculation unit (51) and an environmental data analysis unit (52). The environmental data calculation unit (51) is used to extract data from the third data group, including humidity change rate K, water immersion conductivity L, external temperature change rate M, ultraviolet radiation intensity N, and electromagnetic interference intensity O, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the environmental reference coefficient HJC. The specific calculation formula is as follows: Where: K is the humidity change rate, L is the water immersion conductivity, M is the external temperature change rate, N is the ultraviolet radiation intensity, and O is the electromagnetic interference intensity; The environmental data analysis unit (52) is used to analyze the data obtained by calculation and determine whether the current environment is abnormal based on the analysis results. The specific steps are as follows: When HJC≤0.65, it means that there is no abnormality in the current environment; When HJC>0.65, it means that the current environment is abnormal and needs to be optimized. An environmental optimization data set is generated, including the optimized humidity change rate YK, optimized water immersion conductivity YL, optimized external temperature change rate YM, optimized ultraviolet radiation intensity YN, and optimized electromagnetic interference intensity YO.

9. The remote control system for waterproof sockets based on the Internet of Things according to claim 8, characterized in that: The environment detection module (5) further includes an environment optimization calculation unit (53) and an environment optimization analysis unit (54); The environmental optimization calculation unit (53) is used to extract data from the environmental optimization data group, including optimizing the humidity change rate YK, optimizing the water immersion conductivity YL, optimizing the external temperature change rate YM, optimizing the ultraviolet radiation intensity YN and optimizing the electromagnetic interference intensity YO, and input the extracted multiple data into the pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the optimized environmental reference coefficient YHJ. The specific formula is as follows: Where: YK is the optimized humidity change rate, YL is the optimized water immersion conductivity, YM is the optimized external temperature change rate, YN is the optimized ultraviolet radiation intensity, and YO is the optimized electromagnetic interference intensity; The environmental optimization analysis unit (54) is used to perform data analysis on the calculated optimized environmental reference coefficient YHJ, and judge whether the environmental optimization is effective according to the analysis result. The specific steps are as follows: When YHJ<0.33, it means that the current environment optimization is effective; When YHJ ≥ 0.33, it means that the environment optimization is invalid and a feedback warning is sent.

10. A remote control method for a waterproof socket based on the Internet of Things, characterized by: The method for remotely controlling a waterproof socket based on the Internet of Things is performed by the remote control system for waterproof socket based on the Internet of Things according to any one of claims 1 to 9, and the specific steps are as follows: S1, detecting and extracting data from the waterproof socket through the data acquisition module (1), and pre-processing and reorganizing the extracted multiple parameters to generate a first data group, a second data group, and a third data group; S2, analyzing the first data group, the second data group, and the third data group by the signal detection module (2) to determine whether the socket has an abnormality; S3, performing data analysis on the first data group through the software detection module (3), determining whether the software has an abnormality based on the analysis result and optimizing the software; S4, performing data analysis on the second data group by the firmware detection module (4), determining whether the current firmware has an abnormality based on the analysis result and optimizing the firmware; S5, performing data analysis on the third data group through the environment detection module (5), judging whether the current environment is abnormal based on the analysis results and performing optimization; S6. Feedback of multiple optimization results is performed through the signal feedback module (6).

Images