Power distribution cabinet remote control method based on user behavior analysis and intelligent power distribution cabinet

Abstract

The invention relates to the technical field of intelligent power distribution systems, artificial intelligence and the like, and provides a power distribution cabinet remote control method based on user behavior analysis and an intelligent power distribution cabinet. The user behavior authority comprises an access behavior authority for accessing the intelligent power distribution cabinet system and a remote operation behavior authority for remotely controlling the power distribution cabinet when the power distribution cabinet is abnormal, and access behavior data of the intelligent power distribution cabinet system and remote operation behavior data when the power distribution cabinet is abnormal are acquired and input into the trained user behavior analysis AI model; according to the method, the access habits and remote operation habits of different user roles are analyzed, the user behavior permissions of different user roles are adjusted, and the access behaviors and remote operation behaviors of different user roles are dynamically managed, so that the user behavior permissions are dynamically managed, and the flexibility of user behavior permission management and the system security are improved.

Description

Technical Field

[0001] The present invention relates to the technical fields of intelligent power distribution systems, artificial intelligence and the like, and in particular to a remote control method for a power distribution cabinet based on user behavior analysis and an intelligent power distribution cabinet. Background Art

[0002] At present, although the intelligent distribution cabinet system supports system access and remote control operations when the distribution cabinet is abnormal, the system's user authority management mainly relies on static settings, which makes the authority setting lack flexibility. Static permissions cannot adapt to changes in user responsibilities or dynamic adjustments to business needs, resulting in excessive or insufficient permissions, affecting system security and operational efficiency. In addition, static management of user permissions lacks behavior monitoring and analysis, and cannot detect abnormal operations or potential security threats in a timely manner. Moreover, since permissions cannot be adjusted dynamically, permissions are easily abused or exploited by malicious users, increasing the risk of system attacks or misoperations. When permissions need to be adjusted, operation and maintenance personnel need to manually adjust permissions, which consumes human resources and is prone to human errors.

[0003] In summary, the user authority management technology of the existing intelligent distribution cabinet system has technical problems such as lack of flexibility in authority setting, inability to detect abnormal operations or potential security threats in a timely manner, and authority adjustment is labor-intensive and prone to human errors. Summary of the invention

[0004] In view of the deficiencies in the above-mentioned prior art, the present invention provides a remote control method for a distribution cabinet and an intelligent distribution cabinet based on user behavior analysis, so as to dynamically manage user behavior permissions and improve the flexibility of user behavior permission management and system security.

[0005] In a first aspect, the present invention provides a remote control method for a power distribution cabinet based on user behavior analysis, comprising: A user behavior recording module is configured to record the user behaviors of different user roles in the intelligent power distribution cabinet system. Different user roles are assigned different user behavior permissions, and the user behavior permissions include access behavior permissions to access the intelligent power distribution cabinet system and remote operation behavior permissions for remotely controlling the power distribution cabinet when the power distribution cabinet is abnormal; Obtain the access behavior data of the different user roles accessing the intelligent power distribution cabinet system and the remote operation behavior data of remotely controlling the power distribution cabinet when the power distribution cabinet is abnormal, recorded by the user behavior recording module, and input the access behavior data and the remote operation behavior data of the different user roles into the trained user behavior analysis AI model to analyze the access habits and remote operation habits of the different user roles; According to the access habits and remote operation habits of the different user roles obtained by analyzing the user behavior analysis AI model, the user behavior permissions of the different user roles are adjusted to dynamically manage the access behaviors and remote operation behaviors of the different user roles.

[0006] In a second aspect, the present invention provides an intelligent power distribution cabinet, which is remotely controlled using the above-mentioned power distribution cabinet remote control method based on user behavior analysis.

[0007] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a remote control method for a distribution cabinet based on user behavior analysis and an intelligent distribution cabinet. A user behavior recording module for recording user behaviors of different user roles in an intelligent distribution cabinet system is configured. Different user behavior permissions are assigned to different user roles, and the user behavior permissions include access behavior permissions for accessing the intelligent distribution cabinet system and remote operation behavior permissions for remotely controlling the distribution cabinet when the distribution cabinet is abnormal. The access behavior data of the different user roles accessing the intelligent distribution cabinet system and the remote operation behavior data of remotely controlling the distribution cabinet when the distribution cabinet is abnormal recorded by the user behavior recording module are obtained. The access behavior data and the remote operation behavior data of the different user roles are input into a trained user behavior analysis AI model to analyze the access habits and remote operation habits of the different user roles. According to the access habits and remote operation habits of the different user roles obtained by the user behavior analysis AI model, the user behavior permissions of the different user roles are adjusted to dynamically manage the access behaviors and remote operation behaviors of the different user roles, thereby dynamically managing user behavior permissions and improving the flexibility of user behavior permission management and system security. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The drawings described herein are used to provide further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0009] Figure 1 It is a flow chart of a method for remotely controlling a power distribution cabinet based on user behavior analysis according to an embodiment of the present invention; Figure 2 It is a schematic diagram of a system architecture in which an intelligent power distribution cabinet is remotely controlled using a power distribution cabinet remote control method based on user behavior analysis in an embodiment of the present invention. DETAILED DESCRIPTION

[0010] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only an embodiment of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.

[0011] See also Figure 1-Figure 2 , an embodiment of the present invention provides a distribution cabinet remote control method based on user behavior analysis and an intelligent distribution cabinet. The intelligent distribution cabinet is controlled using a distribution cabinet remote control method based on user behavior analysis. The distribution cabinet remote control method based on user behavior analysis may include step S101, step S102, and step S103. Step S101, step S102, and part or all of step S103 may be run on the server side. By configuring a user behavior recording module for recording user behaviors of different user roles in the intelligent distribution cabinet system, different user roles are assigned different user behavior permissions. The user behavior permissions include access behavior permissions to the intelligent distribution cabinet system and remote operation behavior permissions to remotely control the distribution cabinet when the distribution cabinet is abnormal. The user behavior recording module records the access of different user roles to the intelligent distribution cabinet system. The access behavior data of the distribution cabinet system and the remote operation behavior data of the remote control of the distribution cabinet when the distribution cabinet is abnormal, and the access behavior data and the remote operation behavior data of the different user roles are input into the trained user behavior analysis AI model to analyze the access habits and remote operation habits of the different user roles, and according to the access habits and remote operation habits of the different user roles obtained by the user behavior analysis AI model, the user behavior permissions of the different user roles are adjusted to dynamically manage the access behaviors and remote operation behaviors of the different user roles, thereby dynamically managing user behavior permissions and improving the flexibility of user behavior permission management and system security.

[0012] The remote control method of the power distribution cabinet based on user behavior analysis includes: S101, configuring a user behavior recording module for recording user behaviors of different user roles in the intelligent power distribution cabinet system, wherein different user roles are assigned different user behavior permissions, and the user behavior permissions include access behavior permissions for accessing the intelligent power distribution cabinet system and remote operation behavior permissions for remotely controlling the power distribution cabinet when the power distribution cabinet is abnormal; S102, obtaining the access behavior data of the different user roles accessing the intelligent power distribution cabinet system and the remote operation behavior data of remotely controlling the power distribution cabinet when the power distribution cabinet is abnormal, recorded by the user behavior recording module, and inputting the access behavior data and the remote operation behavior data of the different user roles into the trained user behavior analysis AI model to analyze the access habits and remote operation habits of the different user roles; S103. According to the access habits and remote operation habits of the different user roles obtained by analyzing the user behavior analysis AI model, the user behavior permissions of the different user roles are adjusted to dynamically manage the access behaviors and remote operation behaviors of the different user roles.

[0013] It should be noted that in the traditional intelligent power distribution cabinet system, user permissions are mostly statically configured, which is difficult to dynamically adjust according to the user's actual operation behavior or changes in responsibilities in a timely manner, which easily leads to unreasonable permission allocation, such as excessive or too small permissions, affecting system security or normal operation and maintenance. In addition, due to the lack of behavior monitoring and analysis, it is impossible to effectively monitor the user's daily access behavior and remote operation behavior, and it is impossible to identify abnormalities in a timely manner; and the cost of manual management is high, and permission changes usually rely on manual intervention, which is prone to operational errors or delays. In step S101 of this embodiment, a user behavior recording module is configured, and access behavior permissions and remote operation behavior permissions are set. Different users (administrators, operation and maintenance personnel, business management users, etc.) have different responsibilities in the intelligent power distribution cabinet system, and access behavior permissions and remote operation behavior permissions need to be finely distinguished. Access behavior permissions correspond to user operations such as browsing, viewing, and data querying of the system; remote operation behavior permissions correspond to control operations performed on the power distribution cabinet when the power distribution cabinet is abnormal (such as starting and stopping power supply, parameter adjustment, etc.). It can be understood that the traditional intelligent power distribution cabinet system does not distinguish and cannot meet actual needs. In step S101, by dividing user behavior permissions into two levels, namely, access behavior permissions and remote operation behavior permissions, user behavior can be managed dynamically and more flexibly. In step S102, user behavior data is obtained and input into the user behavior analysis AI model for analysis, which can solve the problem of lack of behavior monitoring and analysis in the traditional intelligent distribution cabinet system. In the traditional system, the user's access behavior and remote operation behavior cannot be automatically captured or can only rely on manual log viewing. In step S102, through the user behavior recording module configured in the system, the access behavior data and remote operation behavior data can be automatically captured and then input into the AI ​​model for in-depth analysis. Based on the learning and recognition capabilities of the user behavior analysis AI model, the AI ​​model can analyze the access habits and remote operation habits of the different user roles. By analyzing the access habits and remote operation habits of different user roles, it can be determined whether the current permission allocation matches the actual operation requirements or whether there are risks. In step S103, the user behavior permissions are dynamically adjusted according to the analysis results, and the access behaviors and remote operation behaviors of the different user roles are dynamically managed. Among them, user responsibilities may change with changes in project scale or staffing; some operation and maintenance personnel need more or higher remote operation permissions in the short term. The system can automatically increase or limit their permissions on the premise of verifying the rationality of user operation behavior, avoiding the security risks brought by ordinary business management users obtaining excessive remote operation permissions, and also avoiding the high maintenance costs and easy errors caused by frequent manual modification of permissions. It is understandable that different user roles can access the intelligent distribution cabinet system through the intelligent user terminal and remotely control the distribution cabinet end. The intelligent distribution cabinet system can run on the server side, and the distribution cabinet end can connect and communicate with the server side.

[0014] In some preferred embodiments, the access behavior permission includes the access behavior permission level and the access behavior permission content, and the level of the access behavior permission determines the amount of the access behavior permission content; the remote operation behavior permission includes the remote operation behavior permission level and the remote operation behavior permission content, and the level of the remote operation behavior permission determines the amount of the remote operation behavior permission content. It should be noted that in this embodiment, by dividing each type of permission in the access behavior permission and the remote operation behavior permission into two parts, the permission level and the permission content, the correspondence between the high and low levels and the executable operation scope (content) is clarified. With the expansion of the functions of the intelligent distribution cabinet system or the change of business needs, different levels can correspond to different depths or different types of access and remote operation content without completely reconstructing the permission system. When the user behavior analysis AI model recognizes that a user needs to be upgraded or downgraded, it can not only quickly adjust its level, but also synchronously change the associated permission content to achieve refined dynamic management of permissions.

[0015] In some preferred embodiments, the different user roles include administrators, operation and maintenance personnel, and business management users; the user behavior authority level of the administrator is higher than the user behavior authority level of the operation and maintenance personnel, and the user behavior authority level of the operation and maintenance personnel is higher than the user behavior authority level of the business management user. It should be noted that in a typical business scenario of an intelligent power distribution cabinet system, common user roles include administrators, operation and maintenance personnel, and business management users. In this embodiment, by stipulating the order of authority levels between different user roles, the system can be more in line with the actual operation and maintenance process during design and use, that is, the administrator has the highest authority and can perform comprehensive management and respond to emergencies; the operation and maintenance personnel have medium authority to handle daily operation and maintenance and some operations; business management users only perform minimum operations related to the business. This hierarchical allocation of authority levels can ensure security (prevent abuse of high authority) and efficiency (avoid cumbersome application processes as much as possible within the scope of authorization).

[0016] In some preferred embodiments, the remote operation behavior authority of the administrator includes remote start and stop of the power supply of the distribution cabinet, remote parameter adjustment, remote system reset and remote alarm processing; the remote operation behavior authority of the operation and maintenance personnel includes remote start and stop of the power supply of the distribution cabinet, remote parameter adjustment and remote system reset; the remote operation behavior authority of the business management user includes remote parameter adjustment related to the daily business needs of the business management user. It should be noted that the administrator usually needs the highest authority to deal with emergency or major changes (such as system reset, alarm processing). The operation and maintenance personnel can perform more technical operations (such as start and stop power supply, parameter adjustment, system reset), but there is no need to manage alarm strategies or core configuration strategies. Business management users only need limited remote parameter adjustments related to business needs, without getting involved in core technical operations, reducing misoperation or safety risks. In this embodiment, by clarifying the specific operations that different user roles can perform in remote operations, it is possible to achieve systematic management of the remote operation behaviors of the different user roles and improve the safety and reliability of the intelligent distribution cabinet system.

[0017] In some preferred embodiments, the access rights of the administrator include viewing and modifying system configuration, viewing all operation data, operation logs and alarm records, creating, deleting or adjusting user account information, and managing and adjusting the security policy of the intelligent power distribution cabinet system; the access rights of the operation and maintenance personnel include viewing system operation data and logs, viewing and maintaining equipment parameters, and downloading or exporting operation reports for fault analysis; the access rights of the business management user include viewing the power distribution status and equipment usage statistics related to the business, and querying and exporting business reports. It should be noted that different roles have different concerns about the intelligent power distribution cabinet system. The administrator needs to fully control the system configuration, user management, security policies, etc., so the access scope is the widest; the operation and maintenance personnel focus on maintenance, inspection and troubleshooting, and need to view logs and related equipment parameters; the business management user only needs to understand the data or statistical information related to the business to avoid obtaining too many technical access rights and causing security risks. In this embodiment, by clearly distinguishing the access scope, while ensuring efficient collaboration, the possibility of the system being misoperated or unauthorized access is minimized.

[0018] In some preferred embodiments, the user behavior analysis AI model adopts a supervised learning model, and the supervised learning model uses a decision tree model or a random forest model. It should be noted that the decision tree model and the random forest model are both supervised learning models. Both have good interpretability (such as visual decision paths and feature importance), which is easy for system operation and maintenance personnel to understand. User behavior analysis usually involves multi-dimensional features (such as access time, access frequency, abnormal operation frequency, user role category, etc.), and the decision tree / random forest model can better identify and utilize the complex correlations between these features to achieve classification or anomaly detection.

[0019] In some preferred embodiments, before training the user behavior analysis AI model, a training data set, a verification data set and a test data set are first obtained. The acquisition methods of the training data set, the verification data set and the test data set include: collecting access behavior data and remote operation behavior data of different user roles from the intelligent distribution cabinet system to obtain the original data of access behavior and remote operation behavior of different user roles; preprocessing the original data of access behavior and remote operation behavior of the different user roles to obtain the preprocessed access behavior data and remote operation behavior data of different user roles; classifying and labeling the preprocessed access behavior data and remote operation behavior data of different user roles to obtain the training data set, the verification data set and the test data set. It should be noted that machine learning in the industrial field must have a clear data management process: first collect the original data, then preprocess (format conversion, deduplication, missing value processing, etc.), and finally divide it into training set, verification set, and test set according to specific rules. This process allows subsequent model training, verification and testing to be carried out in the same feature space and consistent data distribution, avoiding problems such as data leakage or inconsistent distribution. By setting up the training set, validation set, and test set separately, we can continuously evaluate whether the model is overfitting during the training process and test its generalization ability on the final test set.

[0020] In some preferred embodiments, after obtaining the training data set, the verification data set and the test data set, if the supervised learning model uses a decision tree model, training the user behavior analysis AI model includes: inputting the training data set into the decision tree model for model training, so that the decision tree model learns the characteristic patterns of different user roles in access behavior and remote operation behavior, and generates a preliminary user behavior analysis model; using the verification data set to evaluate the performance of the preliminary user behavior analysis model, calculating the accuracy, recall rate and F1 score of the preliminary user behavior analysis model on the verification data set, and adjusting the depth of the decision tree model according to the accuracy, recall rate and F1 score to improve the accuracy and generalization ability of the preliminary user behavior analysis model, and obtain an optimized user behavior analysis model; using the test data set to perform a final evaluation on the optimized user behavior analysis model to obtain the trained user behavior analysis AI model. It should be noted that one of the common hyperparameters of decision trees is the depth of the tree. If the depth is too large, it is easy to overfit, and if the depth is too small, it is easy to underfit. In this embodiment, the model is evaluated using the validation set, and the decision tree depth is dynamically adjusted according to indicators such as accuracy, recall, and F1 score, so as to take into account both model accuracy and generalization ability. In addition, through the final evaluation of the test data set, a trained user behavior analysis AI model is obtained, which can confirm the reliability of the model in actual scenarios and meet the system's requirements for high security and low false alarm rate.

[0021] In some preferred embodiments, after obtaining the training data set, the verification data set and the test data set, if the supervised learning model uses a random forest model, training the user behavior analysis AI model includes: inputting the training data set into the random forest model for model training, so that the random forest model learns the characteristic patterns of different user roles in access behavior and remote operation behavior, and generates a preliminary user behavior analysis model; using the verification data set to evaluate the performance of the preliminary user behavior analysis model, calculating the accuracy, recall rate and F1 score of the preliminary user behavior analysis model on the verification data set, and adjusting the number of trees of the random forest model according to the accuracy, recall rate and F1 score to improve the accuracy and generalization ability of the preliminary user behavior analysis model, and obtain an optimized user behavior analysis model; using the test data set to perform a final evaluation on the optimized user behavior analysis model to obtain the trained user behavior analysis AI model. It should be noted that the random forest model is composed of multiple decision trees, and the number of trees is its important hyperparameter. If the number of trees is too small, the model is prone to underfitting; if the number of trees is too large, the training time and resource consumption may increase. In this embodiment, the number of trees is dynamically adjusted through the validation set indicators (accuracy, recall, F1 score) to achieve the optimal balance for industrial scenarios. Random forest can reduce the overfitting problem of a single decision tree through ensemble learning ideas. In complex distribution cabinet scenarios, random forest can handle more features and is more robust to outliers.

[0022] In some further embodiments, when adjusting the user behavior permissions of the different user roles according to the access habits of the different user roles obtained by the user behavior analysis AI model, it includes: comparing the user access habits output by the user behavior analysis AI model with the access behavior range preset by the system; when it is identified that the user access habits are not within the access behavior range, determining that the user behavior permissions of the user role need to be changed; after determining that the user behavior permissions need to be changed, generating corresponding access rights upgrade or downgrade plans according to the differentiated needs of different user roles in terms of access behavior, the access rights upgrade or downgrade plan includes the items that need to be opened or withdrawn in the specific access behavior permission content; according to the access rights upgrade or downgrade plan, adjusting the user behavior permissions of the corresponding user role to dynamically manage the access behavior of the corresponding user role. It should be noted that in this embodiment, by discovering abnormal access habits and automatically changing the execution permissions, the refined management needs of the intelligent distribution cabinet system in terms of accessing data, viewing information, browsing configurations, etc. can be met. Among them, comparing the user's access habits with the access behavior range preset by the system can clearly identify abnormal situations. In addition, the need to change permissions is determined based on the identification results. When there is a need to change, an upgrade or downgrade plan is generated to accurately divide which specific access permissions are to be opened or revoked, and ultimately the permission changes are executed and take effect, thus forming a closed-loop management from monitoring to execution, ensuring timely adjustment and controllability of access behavior permissions.

[0023] In some further embodiments, when adjusting the user behavior permissions of different user roles according to the remote operation habits of the different user roles obtained by the user behavior analysis AI model, it includes: comparing the remote operation habits output by the user behavior analysis AI model with the abnormal response operation behavior range preset by the system; when it is identified that the remote operation habits are not within the abnormal response operation behavior range, determining that the user behavior permissions of the user role need to be changed; after determining that the user behavior permissions need to be changed, according to the differentiated needs of different user roles in remote operation behaviors, generating a corresponding remote operation permission upgrade or downgrade plan, the remote operation permission upgrade or downgrade plan includes the items that need to be opened or withdrawn in the specific remote operation behavior permission content; according to the remote operation permission upgrade or downgrade plan, adjusting the user behavior permissions of the corresponding user role to dynamically manage the remote operation behavior of the corresponding user role. In this embodiment, by dynamically adjusting the permissions of remote operation behaviors (such as starting and stopping the power supply of the distribution cabinet, adjusting parameters, resetting the system, abnormal alarm processing, etc.), the intelligent distribution cabinet system can distinguish between the two behavior types with different security risk levels, namely, daily viewing / access and abnormal response operations, to achieve more refined permission management. Remote operation behavior is usually accompanied by higher security risks. Once improper operation occurs, it may cause equipment damage or safety accidents. In this embodiment, by comparing the remote operation habits with the range of abnormal response operation behaviors, potential risks can be discovered and prevented in a timely manner, and the operation permissions can be dynamically restricted or revoked.

[0024] In some further embodiments, when the same operation item in the remote operation behavior permission content of different user roles is remotely operated due to abnormal response, the remote abnormal control operation of the administrator takes precedence over the remote abnormal control operation of the operation and maintenance personnel; when the same operation item in the remote operation behavior permission content of the same multiple user roles is remotely operated due to abnormal response, the user trust scores of the same multiple user roles are analyzed, and the remote abnormal control operation of the user with a high user trust score takes precedence over the remote abnormal control operation of the user with a low user trust score. Further, when analyzing the user trust scores of the same multiple user roles, the user behavior analysis AI model is evaluated according to the access habits and the remote operation habits. It should be noted that in the traditional intelligent power distribution cabinet system, once a fault or abnormal situation occurs, multiple users (such as administrators, operation and maintenance personnel) may try to perform remote operations at the same time to troubleshoot or handle the exception. However, there is often controversy or confusion about whose operation should be executed first, especially in the case of concurrent operations. If there is a lack of priority management, the system may face repeated or conflicting operations. Different users performing the same remote operation at the same time may cause conflicting operation commands or even put the power distribution cabinet in an uncertain state. In this embodiment, remote abnormal control operations are performed according to role priority, and administrators take precedence over operation and maintenance personnel. Administrators usually bear higher-level management and decision-making responsibilities and have the authority to fully configure and control the system. In abnormal situations, the system often needs to respond quickly and comprehensively, and administrators are familiar with the system's global configuration, security policies, and emergency procedures, and can make optimal operations from a global perspective better than operation and maintenance personnel. Therefore, when multiple roles initiate the same remote abnormal control operation at the same time, giving priority to the administrator's operation can reduce the decision-making chain, speed up the processing process, and improve the success rate of system emergency disposal. When multiple user roles of the same priority perform the same operation item, the remote abnormal control operation priority is divided according to the user trust score. The user trust score is comprehensively evaluated by the user behavior analysis AI model based on the user's historical habits in access and remote operation behavior. The higher the score, the more reliable the user is in previous operations (for example, fewer erroneous operations, fewer anomalies, and more matching with role permissions, etc.). By giving high-trust users a higher priority and giving priority to their instructions in emergency situations, we can reduce the negative impact of commands from users with misoperations or poor safety records on the system. This is of direct significance for ensuring the safety and stability of the smart distribution cabinet system, and can also motivate users to maintain good operating habits to a certain extent, forming positive feedback. In addition, after analyzing the user's access habits and remote operation habits, the user behavior analysis AI model can further score the user's trust in the user's access habits and remote operation habits.

[0025] It should be pointed out that the above embodiments are only preferred specific implementation modes of the present invention, and the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A remote control method for a power distribution cabinet based on user behavior analysis, characterized in that: include: A user behavior recording module is configured to record the user behaviors of different user roles in the intelligent power distribution cabinet system. Different user roles are assigned different user behavior permissions, and the user behavior permissions include access behavior permissions to access the intelligent power distribution cabinet system and remote operation behavior permissions for remotely controlling the power distribution cabinet when the power distribution cabinet is abnormal; Obtain the access behavior data of the different user roles accessing the intelligent power distribution cabinet system and the remote operation behavior data of remotely controlling the power distribution cabinet when the power distribution cabinet is abnormal, recorded by the user behavior recording module, and input the access behavior data and the remote operation behavior data of the different user roles into the trained user behavior analysis AI model to analyze the access habits and remote operation habits of the different user roles; According to the access habits and remote operation habits of the different user roles obtained by analyzing the user behavior analysis AI model, the user behavior permissions of the different user roles are adjusted to dynamically manage the access behaviors and remote operation behaviors of the different user roles.

2. The method for remote control of a power distribution cabinet based on user behavior analysis according to claim 1, characterized in that: The access behavior permission includes the access behavior permission level and the access behavior permission content. The level of the access behavior permission level determines the amount of the access behavior permission content. The remote operation behavior authority includes a remote operation behavior authority level and a remote operation behavior authority content. The remote operation behavior authority level determines the amount of the remote operation behavior authority content.

3. The method for remote control of a power distribution cabinet based on user behavior analysis according to claim 2, characterized in that: The different user roles include administrators, operation and maintenance personnel, and business management users; the user behavior authority level of the administrator is higher than the user behavior authority level of the operation and maintenance personnel, and the user behavior authority level of the operation and maintenance personnel is higher than the user behavior authority level of the business management user.

4. The method for remote control of a power distribution cabinet based on user behavior analysis according to claim 3, characterized in that: The administrator's remote operation authority includes remote start and stop of the power supply of the distribution cabinet, remote parameter adjustment, remote system reset and remote alarm processing; the operation and maintenance personnel's remote operation authority includes remote start and stop of the power supply of the distribution cabinet, remote parameter adjustment and remote system reset; the business management user's remote operation authority includes remote parameter adjustment related to the daily business needs of the business management user.

5. The method for remote control of a power distribution cabinet based on user behavior analysis according to claim 3, characterized in that: The administrator's access rights include viewing and modifying system configuration, viewing all operating data, operation logs and alarm records, creating, deleting or adjusting user account information, and managing and adjusting the security policy of the intelligent distribution cabinet system; the operation and maintenance personnel's access rights include viewing system operating data and logs, viewing and maintaining equipment parameters, and downloading or exporting operation reports for fault analysis; the business management user's access rights include viewing business-related distribution status, equipment usage statistics, and querying and exporting business reports.

6. The remote control method for a power distribution cabinet based on user behavior analysis according to any one of claims 1 to 5, characterized in that: The user behavior analysis AI model adopts a supervised learning model, and the supervised learning model uses a decision tree model or a random forest model.

7. The method for remote control of a power distribution cabinet based on user behavior analysis according to claim 6, characterized in that: Before training the user behavior analysis AI model, first obtain a training data set, a verification data set and a test data set. The methods for obtaining the training data set, the verification data set and the test data set include: collecting access behavior data and remote operation behavior data of different user roles from the intelligent distribution cabinet system to obtain the original data of the access behavior and remote operation behavior of different user roles; preprocessing the original data of the access behavior and remote operation behavior of the different user roles to obtain the preprocessed access behavior data and remote operation behavior data of different user roles; classifying and labeling the preprocessed access behavior data and remote operation behavior data of different user roles to obtain the training data set, the verification data set and the test data set.

8. The method for remote control of a power distribution cabinet based on user behavior analysis according to claim 7, characterized in that: After obtaining the training data set, the verification data set and the test data set, if the supervised learning model uses a decision tree model, training the user behavior analysis AI model includes: inputting the training data set into the decision tree model for model training, so that the decision tree model learns the characteristic patterns of different user roles in access behavior and remote operation behavior, and generates a preliminary user behavior analysis model; using the verification data set to perform performance evaluation on the preliminary user behavior analysis model, calculating the accuracy, recall rate and F1 score of the preliminary user behavior analysis model on the verification data set, and adjusting the depth of the decision tree model according to the accuracy, recall rate and F1 score to improve the accuracy and generalization ability of the preliminary user behavior analysis model to obtain an optimized user behavior analysis model; using the test data set to perform a final evaluation on the optimized user behavior analysis model to obtain the trained user behavior analysis AI model.

9. The method for remote control of a power distribution cabinet based on user behavior analysis according to claim 7, characterized in that: After obtaining the training data set, the verification data set and the test data set, if the supervised learning model uses a random forest model, training the user behavior analysis AI model includes: inputting the training data set into the random forest model for model training, so that the random forest model learns the characteristic patterns of different user roles in access behavior and remote operation behavior, and generates a preliminary user behavior analysis model; using the verification data set to perform performance evaluation on the preliminary user behavior analysis model, calculating the accuracy, recall rate and F1 score of the preliminary user behavior analysis model on the verification data set, and adjusting the number of trees of the random forest model according to the accuracy, recall rate and F1 score to improve the accuracy and generalization ability of the preliminary user behavior analysis model, and obtain an optimized user behavior analysis model; using the test data set to perform a final evaluation on the optimized user behavior analysis model to obtain the trained user behavior analysis AI model.

10. An intelligent power distribution cabinet, characterized in that: The intelligent power distribution cabinet is remotely controlled using the power distribution cabinet remote control method based on user behavior analysis as described in any one of claims 1 to 9.

Images