A control method for PLC controller based on hidden interface

Abstract

The present invention proposes a control method for a PLC controller based on a hidden interface. Belonging to the technical field of PLC controllers, the method includes: obtaining user identity information; in response to a user interface selection request, the control system checks the user identity information and interface status, and if the user has the corresponding authority and the interface is in an idle state, automatically unlocks and enables the selected interface; in response to a signal indicating that the external device has completed the connection with the unlocked interface, programming and configuration are performed through the operation interface; the operating status and interface usage of the device are monitored in real time; and the operating status and interface usage are recorded in a log file. Through multimodal authentication and a deep learning-driven risk assessment model, accurate verification of user identity and efficient monitoring of abnormal behavior are achieved, effectively preventing unauthorized access and potential malicious attacks. Adaptive security policies and intelligent unlocking mechanisms ensure the security of interface access and reduce security vulnerabilities.

Description

Technical Field

[0001] The invention proposes a control method for a PLC controller based on a hidden interface, belonging to the technical field of PLC controllers. Background Art

[0002] With the continuous development of industrial automation technology, programmable logic controllers (PLCs) have become core control devices in the field. Due to their high reliability, flexibility, and ease of use, PLC controllers are widely used in various industrial environments, such as production line automation, robotic control, and building automation. However, with the increasing complexity of industrial automation systems, the control methods and safety requirements of PLC controllers are becoming increasingly stringent.

[0003] Traditional PLC controller control methods typically rely on fixed interfaces and explicit programming methods, which to some extent limits the flexibility and scalability of the system. Furthermore, traditional control methods also have certain security risks. For example, unauthorized users may be able to access and manipulate the PLC controller, causing system crashes or data leaks.

[0004] To address these issues, researchers and industry are exploring PLC controller control methods based on hidden interfaces. These interfaces are invisible or inaccessible under normal circumstances and are accessible only to users with specific authentication or permissions. This interface design effectively prevents unauthorized users from accessing and operating the system, thereby improving system security and reliability.

[0005] However, current PLC controller control methods based on hidden interfaces still face several challenges. First, effectively managing and controlling access rights to hidden interfaces is a key issue. Second, ensuring that external devices can connect, program, and configure smoothly after the interfaces are unlocked and enabled is another issue that needs to be addressed. Finally, real-time monitoring of device operating status and interface usage, as well as timely recording and reporting of abnormalities, is crucial for ensuring stable system operation and troubleshooting. Summary of the Invention

[0006] The present invention provides a control method for a PLC controller based on a hidden interface to solve the problems mentioned in the above background technology:

[0007] The present invention proposes a control method for a PLC controller based on a hidden interface, the method comprising:

[0008] S1. Obtain user identity information;

[0009] S2. In response to the user interface selection request, the control system checks the user identity information and the interface status. If the user has the corresponding authority and the interface is in an idle state, the selected interface is automatically unlocked and enabled.

[0010] S3, in response to a signal indicating that the external device is connected to the unlocked interface, programming and configuration are performed through the operation interface;

[0011] S4. Monitor the operating status and interface usage of the device in real time; and record the operating status and interface usage in a log file.

[0012] Furthermore, the S1 includes:

[0013] S11. The user authenticates his / her identity through a multimodal authentication mechanism.

[0014] S12. The control system analyzes the user's multimodal identity data and historical behavior data through a built-in deep learning model to construct a user identity feature map;

[0015] S13: Real-time monitoring of the user's current behavior to see if it is consistent with the graph. If abnormal behavior is detected, the control system uses a built-in risk assessment model to assess the user's risk level based on multiple factors.

[0016] S14. Based on the risk assessment results, the control system dynamically adjusts the user's permissions and access restrictions.

[0017] Furthermore, the S12 includes:

[0018] Collect user's multimodal identity data; pre-process the collected data;

[0019] Based on the built-in deep learning model, it extracts and encodes the user's multimodal identity data, combines the extracted features with historical behavior data, and constructs a multi-dimensional user identity feature map;

[0020] Visualize and interact with the graph, and regularly update the user identity feature graph;

[0021] Implement anomaly detection mechanisms to trigger alerts and notify administrators when user behavior is significantly different from the graph.

[0022] Furthermore, the S13 includes:

[0023] Through multi-source information, it captures and records user operations and interaction details in real time, and performs preliminary classification and filtering of user behaviors to exclude irrelevant or redundant information.

[0024] Compare user behavior captured in real time with the behavior patterns in the established user identity feature map, and use anomaly detection algorithms to detect abnormal behaviors that deviate significantly from normal behavior patterns;

[0025] Score and categorize detected abnormal behaviors, distinguish different degrees of abnormality and possible risks, and collect multi-factor data related to users;

[0026] Through feature engineering, key features and indicators are extracted from multi-factor data, abnormal behavior scores are combined with multi-factor features, and comprehensive risk assessment is performed through integrated learning algorithms.

[0027] Furthermore, the S2 includes:

[0028] S21: The user issues a request to access the hidden interface, and the control system determines whether to allow access based on the user's permissions, risk assessment results, and adaptive security policy;

[0029] S22. If access is allowed, the control system activates the intelligent unlocking mechanism, predicts the unlocking timing and method based on the machine learning algorithm, and monitors the physical status of the interface through the network sensor.

[0030] S23. After the interface is unlocked, the control system dynamically allocates the permissions and configurations of the interface according to the real-time needs and operating habits;

[0031] S24. During the use of the interface, the control monitors the user's interaction behavior with the interface in real time through a multimodal perception algorithm. If abnormal behavior or operation error is detected, the security response mechanism is triggered.

[0032] Furthermore, the S23 includes:

[0033] The control system collects real-time demand information from users and predicts their needs through machine learning algorithms and data analysis algorithms;

[0034] Based on the prediction results, the control system pre-allocates possible interface permissions and resources for the user, and based on the user's operating habits, the control system performs personalized adaptation of the interface configuration;

[0035] After the interface is unlocked, the control system dynamically allocates interface permissions based on the user's real-time needs and operating habits; the control system monitors user usage in real time and dynamically adjusts interface permissions and configurations based on the user's actual behavior and feedback;

[0036] The control system sets upper and lower limits for permissions, and sets conditions and thresholds for triggering permission adjustments. If it determines that the user's behavior exceeds the limit, the control system automatically adjusts the permissions or triggers a security response mechanism.

[0037] Furthermore, the S24 includes:

[0038] The control system monitors the user's interaction with the interface in real time through a multimodal perception algorithm, and collects data related to each interaction method;

[0039] Use machine learning algorithms to process and analyze the collected multimodal interaction data and detect abnormal behaviors. For detected abnormal behaviors, the control system further identifies and classifies them.

[0040] For detected operational errors, the control system automatically corrects them. If automatic correction is not feasible or the user rejects the automatic correction, the control system will display an error message to the user through the user interface;

[0041] For any detected serious abnormal behavior or high-risk operations, the control system triggers a security response mechanism.

[0042] Furthermore, the S3 includes:

[0043] S31. When an external device is connected, the control system identifies device information using a multimodal perception algorithm, where the device information includes device type, specifications, and performance parameters.

[0044] S32. Based on device information, the control system predicts the user's programming and configuration requirements through a built-in deep learning model and generates an adaptive programming framework and configuration template;

[0045] S33. Users fine-tune or customize the programming framework and configuration templates through the operation interface, and the control system updates the model in real time based on user feedback.

[0046] Furthermore, the S4 includes:

[0047] S41. The control system monitors the operating status of the equipment and the usage of the interfaces in real time based on multiple monitoring methods, and collects multi-modal monitoring data;

[0048] S42. Record the collected monitoring data in real time into a distributed log system, and perform multimodal log analysis using a deep learning algorithm to obtain analysis results.

[0049] S43. The obtained analysis results are displayed to the user through a visual interface, and predictive maintenance suggestions and optimization solutions based on machine learning are provided to the user.

[0050] Furthermore, the S42 includes:

[0051] Preprocess the collected multimodal monitoring data and classify and label the multimodal data according to data type and source;

[0052] The pre-processed multimodal monitoring data is recorded in real time into a distributed log system through a streaming processing framework.

[0053] Select a deep learning model based on the data type and analysis objectives; train the deep learning model using historical data and known problems and failure modes;

[0054] Fuse the outputs of deep learning models from different modalities and fine-tune or retrain the deep learning models based on preliminary analysis results;

[0055] Use an independent test data set to verify the accuracy of the analysis results by comparing them with the actual device status; if the verification results are not ideal, return to further optimization;

[0056] The optimized and verified analysis results are stored in the distributed log system and the analysis results are visualized.

[0057] The present invention offers the following benefits: Through multimodal authentication and a deep learning-driven risk assessment model, it enables accurate verification of user identities and efficient monitoring of abnormal behavior, effectively preventing unauthorized access and potential malicious attacks. Adaptive security policies and intelligent unlocking mechanisms ensure secure interface access and reduce security vulnerabilities. Dynamically adjusting permissions based on user behavior, real-time needs, and risk assessments not only improves system flexibility but also ensures efficient resource utilization and operational compliance. Personalized interface configuration improves the user experience while ensuring the stable operation of the system; deep learning is used to predict users' programming and configuration needs, and adaptive programming frameworks and configuration templates are generated, which greatly simplifies the user's workflow, reduces error rates, and improves programming and configuration efficiency; combining the Internet of Things, big data, and cloud computing technologies, it achieves all-round, multi-dimensional monitoring of equipment operating status and interface usage, and uses deep learning to perform log analysis to provide predictive maintenance recommendations, which helps prevent failures and reduce downtime and maintenance costs; the use of multimodal perception algorithms and machine learning models enables the system to quickly identify and respond to various abnormal behaviors, including misoperation and malicious attacks, and protects system security and stability through measures such as immediate correction, alarm notifications, and security locks; through in-depth analysis and visual display of monitoring data, it provides users with a clear overview of system status and optimization recommendations, which helps managers make more accurate decisions and improve overall operational efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a step diagram of the method of the present invention. DETAILED DESCRIPTION

[0059] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein may be combined with each other.

[0060] The following description sets forth numerous specific details to facilitate a thorough understanding of the present invention. The embodiments described are merely a portion of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0062] One embodiment of the present invention, as Figure 1 As shown, a control method of a PLC controller based on a hidden interface, the method comprising:

[0063] S1. Obtain user identity information;

[0064] S2. In response to the user interface selection request, the control system checks the user identity information and the interface status. If the user has the corresponding authority and the interface is in an idle state, the selected interface is automatically unlocked and enabled.

[0065] S3, in response to a signal indicating that the external device is connected to the unlocked interface, programming and configuration are performed through the operation interface;

[0066] S4. Monitor the operating status and interface usage of the device in real time; and record the operating status and interface usage in a log file.

[0067] The working principle of the above technical solution is as follows: when a user wishes to access a PLC controller, the system first obtains the user's identity information, perhaps through logging in or other authentication methods. After the user requests an interface, the system checks the user's identity information and the interface status. If the user has the corresponding permissions and the selected interface is available, the system automatically unlocks and enables the selected interface. Once the interface is unlocked and enabled, external devices can connect to it. The system responds with a connection completion signal and provides an operation interface for user programming and configuration. The system monitors the device's operating status and interface usage in real time. This information is recorded in a log file for future query and analysis.

[0068] The effects of the above technical solution are as follows: by requiring users to provide identity information and checking their permissions, the system can ensure that only authorized users can access and operate the PLC controller, thereby enhancing system security; the system can automatically check the status of the interface and automatically unlock and enable the selected interface when the conditions are met, reducing the need for manual intervention and improving the system's automation and management efficiency; once the interface is unlocked and enabled, external devices can be easily connected to the PLC controller and programmed and configured through the operation interface, making operation more convenient and intuitive; the system can monitor the operating status of the device and the usage of the interface in real time and record the relevant information in a log file. This helps to promptly detect problems and abnormal situations, improving the reliability and stability of the system.

[0069] In one embodiment of the present invention, the S1 includes:

[0070] S11. Users authenticate themselves through a multimodal authentication mechanism, including static passwords, dynamic verification codes, and biometric information (e.g., fingerprints, iris scans);

[0071] S12. The control system analyzes the user's multimodal identity data and historical behavior data through a built-in deep learning model to construct a user identity feature map, and compares it with the map during each verification.

[0072] S13. Real-time monitoring of the user's current behavior to see if it is consistent with the profile. If abnormal behavior is detected, the control system uses a built-in risk assessment model to assess the user's risk level based on multiple factors, including historical records, behavioral patterns, and the current environment.

[0073] S14. Based on the risk assessment results, the control system dynamically adjusts the user's permissions and access restrictions.

[0074] The working principle of the above technical solution is as follows: users authenticate their identities through a variety of authentication methods, including static passwords, dynamic verification codes, and biometric information (such as fingerprints and iris scans). Such diversity improves the accuracy and security of identity authentication; the control system analyzes the user's multimodal identity data and historical behavior data through a built-in deep learning model to construct a user identity feature map. This map can comprehensively reflect the user's identity characteristics and behavior patterns; the system monitors in real time whether the user's current behavior is consistent with the map. If abnormal behavior is detected, the system will use the built-in risk assessment model to evaluate the user's risk level based on multiple factors. These factors include the user's historical records, behavior patterns, and current environment; based on the risk assessment results, the system can dynamically adjust the user's permissions and access restrictions. For example, for users with higher risks, the system can restrict their access to specific interfaces, or require additional security measures such as secondary verification.

[0075] The above technical solution significantly improves system security and prevents unauthorized access through a multimodal authentication mechanism, including static passwords, dynamic verification codes, and biometric information. The control system uses a built-in deep learning model to analyze a user's multimodal identity data and historical behavior data to construct a user identity profile. This enables more accurate identity authentication and reduces misidentification and impersonation. The system monitors user behavior in real time to see if it aligns with the profile and uses a built-in risk assessment model to assess the user's risk level. This allows for timely detection of abnormal behavior and assessment of its risk level, providing a basis for subsequent action. Based on the risk assessment results, the control system can dynamically adjust user permissions and access restrictions. For higher-risk users, the system can restrict access to specific interfaces or require secondary verification, further enhancing system security. By integrating multiple factors, including historical records, behavioral patterns, and the current environment, the system can more comprehensively manage and assess user security risks, thereby ensuring stable system operation and data security.

[0076] In one embodiment of the present invention, the step S12 includes:

[0077] Collecting multimodal identity data of users, including hash values ​​of static passwords, records of dynamic verification codes, and biometric information (such as fingerprints and iris scan images or data); preprocessing the collected data, including cleaning and standardization to remove noise and inconsistent data;

[0078] Based on the built-in deep learning model, the user's multimodal identity data is extracted and encoded, and the extracted features are combined with historical behavior data to construct a multi-dimensional user identity feature map; the map can include the user's basic identity features, behavioral habits, preferences and other information.

[0079] Visualize and interact with the graph so that the control system can intuitively display and analyze the user's identity characteristics and behavior patterns, and regularly update the user's identity characteristic graph;

[0080] Implement anomaly detection mechanisms to trigger alerts and notify administrators when user behavior is significantly different from the graph.

[0081] The working principle of the above technical solution is as follows: First, the system collects the user's multimodal identity data, including hash values ​​of static passwords, records of dynamic verification codes, and biometric information. The collected data is then preprocessed, including cleaning and standardization to remove noise and inconsistencies to ensure data accuracy and consistency. Next, the system uses a built-in deep learning model to extract and encode features from the user's multimodal identity data. These extracted features are combined with the user's historical behavioral data to construct a multidimensional user identity feature map. This map can include basic identity characteristics, behavioral habits, preferences, and other information, providing data support for subsequent analysis and judgment. The system uses visualization and interactive design to enable the control system to intuitively display and analyze user identity characteristics and behavioral patterns. Furthermore, the system regularly updates the user identity feature map to ensure it remains consistent with actual changes in user behavior. The system implements an anomaly detection mechanism. When a user's behavior deviates significantly from the map, the system triggers an alarm and notifies the administrator. This allows for timely identification of potential security risks and abnormal behavior, allowing appropriate measures to be taken to address and prevent them.

[0082] The effects of the above technical solution are as follows: by collecting users' multimodal identity data, including static passwords, dynamic verification codes and biometric information, the system can achieve more comprehensive and reliable identity authentication, improving the security and credibility of the system; by preprocessing, cleaning and standardizing the data, the system can improve the quality of the data, remove noise and inconsistent data, and ensure the accuracy and reliability of subsequent analysis and modeling; by extracting and encoding features of users' multimodal identity data based on a built-in deep learning model and combining it with historical behavioral data, the system can build a personalized user identity feature map, including basic identity features, behavioral habits, preferences and other information, providing a basis for subsequent personalized services and analysis; by visualizing and interactively designing the map, the system can intuitively display and analyze users' identity features and behavior patterns, helping administrators better understand user behavior and promptly detect abnormal behavior; the system implements an anomaly detection mechanism. When a significant difference is detected between user behavior and the map, an alarm will be triggered and the administrator will be notified, helping to promptly identify potential security risks and abnormal behavior, take appropriate measures to deal with and prevent them, and improve the security and stability of the system.

[0083] In one embodiment of the present invention, the step S13 includes:

[0084] Through multi-source information, it captures and records user operations and interaction details in real time, and performs preliminary classification and filtering of user behaviors to exclude irrelevant or redundant information.

[0085] Compare user behavior captured in real time with the behavior patterns in the constructed user identity feature map, and use anomaly detection algorithms (such as Isolation Forest and One-Class SVM) to detect abnormal behaviors that deviate significantly from normal behavior patterns;

[0086] Score and classify detected abnormal behaviors, distinguish different degrees of abnormality and possible risks, and collect multi-factor data related to users.

[0087] Through feature engineering, key features and indicators are extracted from multi-factor data, abnormal behavior scores are combined with multi-factor features, and comprehensive risk assessment is performed through integrated learning algorithms (such as random forests and gradient boosting machines).

[0088] The above technical solution works as follows: The system captures and records user operations and interaction details in real time using multiple sources, including system logs, network traffic monitoring, and sensor data. It then performs preliminary classification and filtering of user behavior to eliminate irrelevant or redundant information and ensure the accuracy of subsequent analysis. The captured user behavior is then compared with behavioral patterns in a constructed user identity profile. This allows for the identification of abnormal behavior by comparing real-time behavior with historical behavior patterns. The system utilizes anomaly detection algorithms (such as Isolation Forest and One-Class Support Vector Machine) to detect abnormal behavior that significantly deviates from normal behavior patterns. Detected abnormal behavior is scored and classified to distinguish between different levels of abnormality and potential risk. The system collects multi-factor data related to users, including historical records, behavioral patterns, and current environmental information (such as IP address, geographic location, and device information). Through feature engineering, key features and indicators are extracted from this multi-factor data to prepare for a comprehensive risk assessment. The abnormal behavior score is combined with the multi-factor features, and the system uses ensemble learning algorithms (such as Random Forest and Gradient Boosting Machine) to perform a comprehensive risk assessment to determine the severity of the abnormal behavior and the potential risk level.

[0089] The effects of the above technical solutions are as follows: the system can capture and record user operation behaviors and interaction details in real time, realize real-time monitoring and detection of user behaviors through multi-source information, and promptly discover potential abnormal behaviors; by comparing with user identity feature maps and anomaly detection algorithms, the system can accurately identify abnormal behaviors that deviate significantly from normal behavior patterns, effectively reducing false alarms and missed reports; the system adopts multi-factor data collection and feature engineering, comprehensively considers factors such as historical records, behavior patterns, and current environmental information, and combines integrated learning algorithms for comprehensive risk assessment, thereby improving the accuracy and reliability of risks that may be caused by abnormal behaviors; after timely discovering abnormal behaviors, the system can score and classify them, distinguish different degrees of abnormality and possible risks, and take targeted rapid response and disposal measures to effectively reduce the impact of potential risks; through real-time monitoring, precise identification and comprehensive evaluation, the system can improve the security and reliability of the system, and ensure the safe and stable operation of user data and system resources.

[0090] In one embodiment of the present invention, the S2 includes:

[0091] S21: The user issues a request to access the hidden interface, and the control system determines whether to allow access based on the user's permissions, risk assessment results, and adaptive security policy;

[0092] S22. If access is allowed, the control system activates the intelligent unlocking mechanism, predicts the unlocking timing and method based on a machine learning algorithm, and monitors the physical status of the interface through network sensors;

[0093] S23. After the interface is unlocked, the control system dynamically allocates the permissions and configurations of the interface according to the real-time needs and operating habits;

[0094] S24. During the use of the interface, the control monitors the user's interaction behavior with the interface in real time through a multimodal perception algorithm. If abnormal behavior or operation error is detected, the security response mechanism is triggered.

[0095] The working principle of the above technical solution is as follows: when a user requests access to a hidden interface, the control system determines whether to allow access based on the user's permissions, risk assessment results, and adaptive security policies. If access is allowed, the control system activates the intelligent unlocking mechanism. This mechanism uses machine learning algorithms to predict the timing and method of unlocking, while also monitoring the physical state of the interface through network sensors to ensure a safe and reliable unlocking process. After the interface is unlocked, the control system dynamically allocates permissions and configurations based on real-time needs and user operating habits to ensure that users can access the required functions and resources on demand. During interface use, the control system monitors the user's interaction with the interface in real time through a multimodal perception algorithm. If abnormal behavior or operational errors are detected, a security response mechanism is triggered, which may include alarms, restricted operating permissions, or forced exits to ensure system and data security.

[0096] The effects of the above technical solution are: by comprehensively considering user permissions, risk assessment results and adaptive security strategies, the control system can effectively prevent unauthorized users from accessing hidden interfaces, thereby improving the overall security of the system; starting the intelligent unlocking mechanism can predict the unlocking timing and method based on the machine learning algorithm, and combine the network sensor to monitor the physical state of the interface to ensure the security and reliability of the unlocking process, avoiding the disadvantages of traditional passwords or keys, and improving the security of the system; dynamically allocating the permissions and configurations of the interface according to real-time needs and operating habits can ensure that users can obtain the required functions and resources on demand, while preventing unnecessary permission leakage or abuse, thereby improving the flexibility and security of the system; through the multimodal perception algorithm, real-time monitoring of the user's interaction behavior with the interface can promptly detect abnormal behavior or operation errors, and trigger corresponding security response mechanisms, such as alarms, restricted operating permissions or forced exits, etc., effectively preventing the occurrence or expansion of security incidents, and improving the security and reliability of the system.

[0097] In one embodiment of the present invention, the step S23 includes:

[0098] The control system collects real-time demand information from users and predicts their needs through machine learning algorithms and data analysis algorithms;

[0099] Based on the prediction results, the control system pre-allocates possible interface permissions and resources for the user, and based on the user's operating habits, the control system performs personalized adaptation of the interface configuration;

[0100] After the interface is unlocked, the control system dynamically allocates interface permissions based on the user's real-time needs and operating habits; the control system monitors the user's usage in real time and dynamically adjusts the interface permissions and configuration based on the user's actual behavior and feedback.

[0101] The control system sets upper and lower limits for permissions, and sets conditions and thresholds for triggering permission adjustments. If it determines that the user's behavior exceeds the limit, the control system automatically adjusts the permissions or triggers a security response mechanism.

[0102] The working principle of the above technical solution is as follows: the control system collects real-time user demand information through various channels, including explicit requests, historical usage records, and interaction data with other systems. This information is input into machine learning and data analysis algorithms for processing to predict the interface functions that users may need within a certain period of time. For example, time series analysis can predict user usage preferences and demand trends over different time periods. Based on the prediction results, the control system pre-assigns possible interface permissions and resources to the user and performs personalized adaptation based on the user's operating habits. This includes adjusting the interface display and operation shortcuts to improve the user experience and efficiency. After the interface is unlocked, the control system dynamically assigns interface permissions based on the user's real-time needs and operating habits. The system monitors user usage in real time, including the interface functions accessed, data range, and operation duration, and dynamically adjusts interface permissions and configuration based on user behavior and feedback. For example, if a user frequently accesses a function, the permission level of that function may be temporarily increased. The control system sets upper and lower limits for permissions and sets the conditions and thresholds that trigger permission adjustments. If it is determined that the user's behavior exceeds the limit, the system will automatically adjust the permissions or trigger a security response mechanism, such as an alert, restricting operating permissions, or forced exit, to protect the security and stability of the system.

[0103] The effects of the above technical solution are as follows: the control system dynamically allocates interface permissions and configurations based on the user's real-time needs and operating habits, thereby providing a personalized user experience, enabling users to access the required interface functions more quickly and conveniently, and improving user satisfaction and usage efficiency; predicting user needs through machine learning algorithms and data analysis algorithms, and pre-allocating and personalizing interface permissions based on the prediction results, so that the control system has a certain intelligent capability and can actively respond to changes in user needs, thereby improving the intelligence level of the system; the control system sets upper and lower limits for permissions, and sets conditions and thresholds for triggering permission adjustments. When the user's behavior exceeds the limit, the system will automatically adjust the permissions or trigger a security response mechanism to protect the security and stability of the system and effectively prevent malicious operations and security threats; the control system dynamically adjusts the interface permissions and configuration based on the user's actual behavior and feedback, enabling users to access the required interface functions more efficiently, reducing unnecessary operating steps and time consumption, and improving the overall efficiency and performance of the system.

[0104] In one embodiment of the present invention, the control system sets upper and lower limits for permissions, and sets conditions and thresholds for triggering permission adjustments. If it determines that the user's behavior exceeds the limit, the control system automatically adjusts the permissions or triggers a security response mechanism, including:

[0105] The control system divides interface permissions into multiple levels based on user roles, responsibilities, and business needs, and sets clear permission scope and operation content for each level;

[0106] Based on the user's historical behavior data, business needs, and system security policies, the control system dynamically adjusts the upper and lower limits of permissions;

[0107] The control system analyzes the user's behavior patterns to establish a baseline of normal behavior. When the user's behavior deviates from the baseline, the system identifies abnormal behavior;

[0108] Set a threshold for triggering permission adjustment for each abnormal behavior, and the system dynamically adjusts the threshold based on real-time data;

[0109] When the system detects that the user's behavior is close to or exceeds the set threshold, the control system will automatically reduce the user's authority level;

[0110] During critical operations or high-risk behaviors, the system requires users to perform multiple verifications, such as SMS verification codes and fingerprint recognition;

[0111] The system monitors user behavior in real time and assesses potential security risks in real time. When the assessment result exceeds the set risk threshold, the system automatically blocks the user's operation.

[0112] The working principle of the above technical solution is as follows: The control system first divides interface permissions into multiple levels based on user roles, responsibilities, and business requirements, and defines clear permission scopes and operations for each level. This ensures that users with different roles can only access functions relevant to their responsibilities. Based on historical user behavior data, business requirements, and system security policies, the control system dynamically adjusts the upper and lower limits of permissions. This means that as user behavior and business requirements change, user permission levels will be adjusted accordingly to adapt to current work scenarios. The control system analyzes user behavior patterns to establish a baseline of normal behavior. When user behavior deviates from this baseline, the system identifies abnormal behavior and triggers further permission adjustments or security response mechanisms. Triggering thresholds for permission adjustments are set for each abnormal behavior, such as access frequency and operation duration. The control system dynamically adjusts these thresholds based on real-time data to improve the accuracy of abnormal behavior detection. When the system detects that user behavior approaches or exceeds the set threshold, the control system automatically reduces the user's permission level to reduce potential security risks. Users are immediately notified of any permission adjustments and the reason for the adjustment is explained. The system also provides user feedback channels for users to raise objections or make suggestions regarding the adjustments. For critical operations or high-risk behaviors, the system requires users to undergo multiple authentication steps, such as SMS verification codes and fingerprint recognition. This increases operational complexity and security while reducing the risk of unauthorized access. The control system monitors user behavior in real time and assesses potential security risks. If the assessment exceeds the set risk threshold, the system automatically blocks the user's operation to prevent further escalation of the risk. The control system records user operations and security incidents in detail for subsequent auditing and tracing. The system also provides data analysis tools to help administrators analyze the causes and trends of security incidents, providing a basis for formulating more effective security policies.

[0113] The above technical solution achieves fine-grained permission control by classifying permissions based on user roles, responsibilities, and business needs, and setting clear permission scopes and operations. This effectively avoids security risks and work efficiency issues caused by excessive or insufficient permissions. The control system dynamically adjusts the upper and lower limits of permissions based on historical user behavior data, business needs, and system security policies. This dynamic adjustment mechanism ensures that users can complete tasks efficiently without exceeding their permissions, improving work efficiency and security. The control system analyzes user behavior patterns to establish a baseline of normal behavior and identifies abnormal behavior that deviates from this baseline. This abnormal behavior detection mechanism promptly identifies potential security risks and triggers appropriate permission adjustments or security response mechanisms, reducing the probability of security incidents. The control system sets thresholds for triggering permission adjustments for each abnormal behavior, such as access frequency and operation duration. Furthermore, the system dynamically adjusts these thresholds based on real-time data, improving the accuracy and flexibility of abnormal behavior detection. When the system detects that user behavior approaches or exceeds a set threshold, the control system automatically reduces the user's permission level to reduce potential security risks. Users are immediately notified of any permission adjustments and are provided with an explanation of the reasons for the adjustment. This transparent permission adjustment mechanism enhances user confidence in system security. For critical operations or high-risk behaviors, the system requires users to perform multiple verification steps, such as SMS verification codes and fingerprint recognition. This multi-verification mechanism improves operational security and reduces the risk of unauthorized access. The control system monitors user behavior in real time and assesses potential security risks. When the assessment result exceeds the set risk threshold, the system automatically blocks the user's operation to prevent further escalation of the risk. This real-time risk assessment and blocking mechanism enables rapid response to security threats and protects system security. The control system records user operations and security incidents in detail, supporting post-audit and tracing. Furthermore, the system provides data analysis tools to help administrators analyze the causes and trends of security incidents, providing a basis for formulating more effective security policies. This security logging and auditing mechanism provides comprehensive protection for system security.

[0114] In one embodiment of the present invention, the step S24 includes:

[0115] The control system uses a multimodal perception algorithm to monitor user interactions with the interface in real time. This includes keyboard input, mouse movement, touch operations, voice commands, and other interaction methods. The control system collects data related to each interaction method, such as keystroke frequency, mouse movement trajectory, touch point location, and the semantics of voice commands.

[0116] Use machine learning algorithms to process and analyze the collected multimodal interaction data and detect abnormal behaviors. For detected abnormal behaviors, the control system further identifies and classifies them.

[0117] For detected operational errors, the control system automatically corrects them. If automatic correction is not feasible or the user rejects the automatic correction, the control system will display an error message to the user through the user interface;

[0118] For any detected serious abnormal behavior or high-risk operations, the control system triggers a security response mechanism.

[0119] The working principle of the above technical solution is as follows: The control system monitors user interaction with the interface in real time through multiple sensing methods, including keyboard input, mouse movement, touch operation, and voice commands. For each interaction method, the system collects relevant data, such as keystroke frequency, mouse movement trajectory, touch point location, and voice command semantics. This collected multimodal interaction data is fed into a machine learning algorithm for processing and analysis. The system uses this data to train a model to identify normal and abnormal behavior patterns. The machine learning algorithm detects abnormal behavior and identifies and classifies it. The system can distinguish between incorrect operations, malicious attacks, or other types of abnormal behavior and determine their severity and risk level. For detected operational errors, the control system attempts to automatically correct them. If automatic correction is not possible or the user refuses automatic correction, the system displays an error message through the user interface, notifying the user of the error and providing corrective action suggestions or help documentation. For detected serious abnormal behavior or high-risk operations, the control system triggers security response mechanisms. This may include recording detailed information about the abnormal behavior, sending alerts to administrators or security teams, and temporarily locking the interface to prevent further operation.

[0120] The effects of the above technical solution are as follows: by monitoring the user's interaction with the interface in real time, the system can more comprehensively perceive user operations, including multiple interaction methods such as keyboard, mouse, touch, and voice, thereby improving its ability to perceive user behavior; by using machine learning algorithms to process and analyze the collected multimodal interaction data, the system can effectively detect abnormal behavior and identify and classify it. This helps to promptly discover and respond to various abnormal situations, including misoperation and malicious attacks; for detected operational errors, the system can automatically correct them, improving the accuracy and efficiency of user operations. If automatic correction is not feasible or the user refuses automatic correction, the system can promptly display an error prompt to the user and provide corrective operation suggestions or help documentation, enhancing the user experience; in response to the detection of serious abnormal behavior or high-risk operations, the system can trigger a security response mechanism and take necessary security measures in a timely manner, including recording the abnormal behavior, sending alerts to notify administrators or security teams, and temporarily locking the interface, thereby ensuring the security and stability of the system.

[0121] In one embodiment of the present invention, S3 includes:

[0122] S31. When an external device is connected, the control system identifies device information using a multimodal perception algorithm, where the device information includes device type, specifications, and performance parameters.

[0123] S32. Based on device information, the control system predicts the user's programming and configuration requirements through a built-in deep learning model and generates an adaptive programming framework and configuration template;

[0124] S33. Users fine-tune or customize the programming framework and configuration templates through the operation interface, and the control system updates the model in real time based on user feedback.

[0125] The working principle of the above technical solution is as follows: When an external device is connected, the control system uses a multimodal perception algorithm to sense and identify the device, obtaining device information, including device type, specifications, and performance parameters. Based on this acquired device information, the control system uses a built-in deep learning model to predict the user's possible programming and configuration needs. These needs may involve programming frameworks and configuration templates for specific devices. Based on the prediction results of the deep learning model, the control system generates adaptive programming frameworks and configuration templates to meet the user's needs. These frameworks and templates can be optimized for different types of devices, thereby improving the efficiency and accuracy of programming and configuration. Users can fine-tune or customize the generated programming frameworks and configuration templates through the user interface to meet specific needs and preferences. The control system updates the model in real time based on user feedback, continuously optimizing and adjusting the prediction results to provide more personalized and accurate programming and configuration solutions.

[0126] The effects of the above technical solution are: by identifying external device information through multimodal perception algorithms, the system can intelligently manage various types of external devices, including device types, specifications and performance parameters, thereby improving the convenience and efficiency of device connection; based on device information and built-in deep learning models, the system can accurately predict users' programming and configuration needs, and generate adaptive programming frameworks and configuration templates to provide users with personalized programming and configuration solutions; adaptive programming frameworks and configuration templates can effectively reduce users' time and energy consumption in the programming and configuration process, and improve production efficiency and work efficiency; users can fine-tune or customize the generated programming frameworks and configuration templates through the operation interface to meet personalized needs and preferences, enhancing user experience and satisfaction; the control system can update the model in real time based on user feedback, continuously optimize the prediction results and programming framework, and maintain the intelligence and adaptability of the system.

[0127] In one embodiment of the present invention, the S4 includes:

[0128] S41. The control system monitors the operating status of the equipment and interface usage in real time based on multiple monitoring methods, including the Internet of Things, big data, and cloud computing technologies, and collects multimodal monitoring data (such as performance parameters, video images, audio data, etc.);

[0129] S42. Record the collected monitoring data in real time into a distributed log system, and perform multimodal log analysis using a deep learning algorithm to obtain analysis results; the analysis results include potential problems, failure modes, and safety hazards;

[0130] S43. The obtained analysis results are displayed to the user through a visual interface, and predictive maintenance suggestions and optimization solutions based on machine learning are provided to the user.

[0131] The working principle of the above technical solution is as follows: the control system uses various monitoring methods (such as the Internet of Things, big data, and cloud computing technologies) to monitor the operating status of equipment and interface usage in real time. These monitoring methods can collect multimodal monitoring data, including performance parameters, video images, audio data, etc. The collected monitoring data is recorded in real time in a distributed logging system for subsequent analysis and processing. This ensures the reliability and durability of the monitoring data. The control system uses deep learning algorithms to analyze the multimodal monitoring data recorded in the distributed logging system. Through deep learning processing of monitoring data, the system can identify potential problems, failure modes, and safety hazards. The control system displays the analysis results to the user through a visual interface, allowing users to intuitively understand the equipment status and problem situations. At the same time, the system also provides users with predictive maintenance recommendations and optimization solutions based on machine learning to help users promptly identify and resolve problems, thereby improving the reliability and stability of the equipment.

[0132] The effects of the above technical solution are: real-time monitoring of device status and interface usage through various monitoring methods, while simultaneously collecting multimodal monitoring data, including performance parameters, video images, audio data, and so on. This provides a comprehensive understanding of the device's operating status, helping to promptly identify problems and anomalies; the collected monitoring data is recorded in real time in a distributed log system, and multimodal log analysis is performed using deep learning algorithms. This analysis method can efficiently identify potential problems, failure modes, and safety hazards, improving the accuracy and efficiency of fault diagnosis; the analysis results are presented to the user through a visual interface, allowing the user to intuitively understand the device status and problem situation. This interactive method allows users to quickly locate problems and take appropriate measures; predictive maintenance recommendations and optimization solutions based on machine learning can help users prevent failures and optimize equipment performance in advance, thereby reducing maintenance costs, extending equipment life, and improving production efficiency.

[0133] In one embodiment of the present invention, the step S42 includes:

[0134] Preprocess the collected multimodal monitoring data and classify and label the multimodal data according to data type and source;

[0135] The pre-processed multimodal monitoring data is recorded in real time into a distributed log system through a streaming processing framework.

[0136] Select a deep learning model based on the data type and analysis objectives; train the deep learning model using historical data and known problems and failure modes;

[0137] Fuse the outputs of deep learning models from different modalities and fine-tune or retrain the deep learning models based on preliminary analysis results;

[0138] Use an independent test data set to verify the accuracy of the analysis results by comparing them with the actual device status; if the verification results are not ideal, return to further optimization;

[0139] The optimized and verified analysis results are stored in the distributed log system and the analysis results are visualized.

[0140] The working principle of the above technical solution is as follows: First, the collected multimodal monitoring data is preprocessed, including data cleaning and feature extraction. Then, it is classified and labeled according to data type and source. For example, performance parameter data can be labeled as "system performance," video image data can be labeled as "physical environment monitoring," and audio data can be labeled as "device sound monitoring" to facilitate subsequent analysis and processing. After preprocessing and classification, the multimodal monitoring data is recorded in real time into a distributed logging system through a streaming processing framework for subsequent analysis and storage. Based on the data type and analysis objectives, an appropriate deep learning model is selected for analysis. For example, recurrent neural networks (RNN) or long short-term memory networks (LSTM) can be used for time series data, and convolutional neural networks (CNN) can be used for image and audio data. During the training process, unsupervised learning can be introduced to automatically discover potential patterns in the data, or semi-supervised learning can be used to train with a small amount of labeled data to improve the performance and generalization ability of the model. The outputs of deep learning models from different modalities can be integrated to obtain more comprehensive analysis results and improve the accuracy and reliability of the analysis. The analysis results are verified using independent test data sets, and the accuracy is evaluated by comparing the analysis results with the actual device status. If the verification results are not ideal, the deep learning model can be fine-tuned or retrained to optimize the model performance. The optimized and verified analysis results are stored in a distributed log system and displayed to the user through a visual interface, so that the user can intuitively understand the device status and problem situation, and it is convenient for the user to quickly take appropriate measures.

[0141] The effects of the above technical solutions are as follows: by preprocessing, classifying and labeling multimodal monitoring data, and selecting appropriate deep learning models for analysis, comprehensive monitoring and analysis of equipment status is achieved, including performance parameters, images and audio data, etc.; the preprocessed multimodal monitoring data is recorded in real time into the distributed log system through the streaming processing framework, which can timely capture changes and abnormal conditions in equipment status so that corresponding measures can be taken in time; using deep learning models to analyze multimodal monitoring data can better capture patterns and laws in the data, thereby improving the ability to identify and predict equipment status; introducing unsupervised learning and semi-supervised learning Learning technology can automatically discover potential patterns in data and use a small amount of labeled data for training, thereby improving the performance and generalization ability of the model; fusing the outputs of deep learning models from different modalities can obtain more comprehensive analysis results and improve the accuracy and reliability of the analysis; using independent test data sets to verify the analysis results and further optimize them based on the verification results can improve the accuracy and reliability of the analysis results; storing the optimized and verified analysis results in a distributed log system and displaying them to users through a visual interface, so that users can intuitively understand the device status and problem conditions, and facilitate users to quickly take corresponding measures.

[0142] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A control method for a PLC controller based on a hidden interface, characterized in that: The method comprises: S1. Obtain user identity information; S2. In response to the user interface selection request, the control system checks the user identity information and the interface status. If the user has the corresponding authority and the interface is in an idle state, the selected interface is automatically unlocked and enabled. S3, in response to a signal indicating that the external device is connected to the unlocked interface, programming and configuration are performed through the operation interface; S4. Monitor the device's operating status and interface usage in real time; and record the operating status and interface usage in a log file; Said S2 comprises: S21: The user issues a request to access the hidden interface, and the control system determines whether to allow access based on the user's permissions, risk assessment results, and adaptive security policy; S22. If access is allowed, the control system activates the intelligent unlocking mechanism, predicts the unlocking timing and method based on a machine learning algorithm, and monitors the physical status of the interface through network sensors; S23. After the interface is unlocked, the control system dynamically allocates the permissions and configurations of the interface according to the real-time needs and operating habits; S24. During the use of the interface, the controller monitors the user's interaction with the interface in real time through a multimodal perception algorithm. If abnormal behavior or operational errors are detected, a security response mechanism is triggered. Said S23 comprises: The control system collects real-time demand information from users and predicts their needs through machine learning algorithms and data analysis algorithms; Based on the prediction results, the control system pre-allocates possible interface permissions and resources for the user, and based on the user's operating habits, the control system performs personalized adaptation of the interface configuration; After the interface is unlocked, the control system dynamically allocates interface permissions based on the user's real-time needs and operating habits; the control system monitors user usage in real time and dynamically adjusts interface permissions and configurations based on the user's actual behavior and feedback; The control system sets upper and lower limits for permissions, and sets conditions and thresholds for triggering permission adjustments. If it determines that the user's behavior exceeds the limit, the control system automatically adjusts the permissions or triggers a security response mechanism.

2. The control method of a PLC controller based on a hidden interface according to claim 1, characterized in that: Said S1 comprises: S11. The user authenticates his / her identity through a multimodal authentication mechanism. S12. The control system analyzes the user's multimodal identity data and historical behavior data through a built-in deep learning model to construct a user identity feature map; S13: Real-time monitoring of the user's current behavior to see if it is consistent with the graph. If abnormal behavior is detected, the control system uses a built-in risk assessment model to assess the user's risk level based on multiple factors. S14. Based on the risk assessment results, the control system dynamically adjusts the user's permissions and access restrictions.

3. The control method of a PLC controller based on a hidden interface according to claim 2, characterized in that: Said S12 comprises: Collect user's multimodal identity data; pre-process the collected data; Based on the built-in deep learning model, it extracts and encodes the user's multimodal identity data, combines the extracted features with historical behavior data, and constructs a multi-dimensional user identity feature map; Visualize and interact with the graph, and regularly update the user identity feature graph; Implement anomaly detection mechanisms to trigger alerts and notify administrators when user behavior is significantly different from the graph.

4. The control method of a PLC controller based on a hidden interface according to claim 2, characterized in that: Said S13 comprises: Through multi-source information, it captures and records user operations and interaction details in real time, and performs preliminary classification and filtering of user behaviors to exclude irrelevant or redundant information. Compare user behavior captured in real time with the behavior patterns in the established user identity feature map, and use anomaly detection algorithms to detect abnormal behaviors that deviate significantly from normal behavior patterns; Score and categorize detected abnormal behaviors, distinguish different degrees of abnormality and possible risks, and collect multi-factor data related to users; Through feature engineering, key features and indicators are extracted from multi-factor data, abnormal behavior scores are combined with multi-factor features, and comprehensive risk assessment is performed through integrated learning algorithms.

5. The control method of a PLC controller based on a hidden interface according to claim 1, characterized in that: The S24 includes: The control system monitors the user's interaction with the interface in real time through a multimodal perception algorithm, and collects data related to each interaction method; Use machine learning algorithms to process and analyze the collected multimodal interaction data and detect abnormal behaviors. For detected abnormal behaviors, the control system further identifies and classifies them. For detected operational errors, the control system automatically corrects them. If automatic correction is not feasible or the user rejects the automatic correction, the control system will display an error message to the user through the user interface; For any detected serious abnormal behavior or high-risk operations, the control system triggers a security response mechanism.

6. The control method of a PLC controller based on a hidden interface according to claim 1, characterized in that: The S3 includes: S31. When an external device is connected, the control system identifies device information using a multimodal perception algorithm, where the device information includes device type, specifications, and performance parameters. S32. Based on device information, the control system predicts the user's programming and configuration requirements through a built-in deep learning model and generates an adaptive programming framework and configuration template; S33. Users fine-tune or customize the programming framework and configuration templates through the operation interface, and the control system updates the model in real time based on user feedback.

7. The control method of a PLC controller based on a hidden interface according to claim 1, characterized in that: Said S4 comprises: S41. The control system monitors the operating status of the equipment and the usage of the interfaces in real time based on multiple monitoring methods, and collects multi-modal monitoring data; S42. Record the collected monitoring data in real time into a distributed log system, and perform multimodal log analysis using a deep learning algorithm to obtain analysis results. S43. The obtained analysis results are displayed to the user through a visual interface, and predictive maintenance suggestions and optimization solutions based on machine learning are provided to the user.

8. The control method of a PLC controller based on a hidden interface according to claim 7, characterized in that: The S42 includes: Preprocess the collected multimodal monitoring data and classify and label the multimodal data according to data type and source; The pre-processed multimodal monitoring data is recorded in real time into a distributed log system through a streaming processing framework. Select a deep learning model based on the data type and analysis objectives; train the deep learning model using historical data and known problems and failure modes; Fuse the outputs of deep learning models from different modalities and fine-tune or retrain the deep learning models based on preliminary analysis results; Use an independent test data set to verify the accuracy of the analysis results by comparing them with the actual device status; if the verification results are not ideal, return to further optimization; The optimized and verified analysis results are stored in the distributed log system and the analysis results are visualized.

Images