Electric power practical training room intelligent management system and method based on unmanned recording and broadcasting technology

Abstract

The invention discloses an electric power training room intelligent management system based on an unmanned recording and broadcasting technology and a method thereof, and belongs to the technical field of supervision processing. The method is used for solving the technical problem that in an existing scheme, reliability and comprehensive autonomous supervision analysis and management effects of implementation of an intelligent risk identification scheme of an electric power practical training room are poor. The method comprises the following steps: carrying out routine abnormal whole-course supervision and recording on electric power practical training operations of different students in an electric power practical training room to obtain first practical operation abnormal record data corresponding to the different students, and carrying out whole-course supervision and autonomous abnormal identification recording on the electric power practical training operations of the different students through a monitoring identification technology; second practical operation abnormity record data corresponding to different trainees are obtained, and processing analysis of practical operation abnormity autonomous identification influence is carried out on the second practical operation abnormity record data according to the first practical operation abnormity record data corresponding to different trainees; and performing targeted optimization training on intelligent identification defects of different abnormal types in a self-adaptive manner according to an analysis result.

Description

Technical Field

[0001] This invention relates to the field of monitoring and processing technology, specifically to an intelligent management system and method for power training rooms based on unmanned recording and broadcasting technology. Background Technology

[0002] A power training lab is a facility specifically designed for teaching, practical operation, and skills training in power-related majors. It is typically equipped with various power equipment, simulation systems, safety tools, and experimental devices, aiming to help students or professionals master practical skills in the operation, maintenance, repair, and safe operation of power systems.

[0003] Existing power training room management solutions are typically designed around three core objectives: safety, efficiency, and standardization, covering multiple dimensions such as systems, processes, technology, and personnel. However, existing power training room management solutions have certain shortcomings in implementation. They cannot combine power operation supervision data to proactively monitor and analyze the reliability and comprehensiveness of the existing power operation risk identification and to optimize management in a targeted manner. As a result, the reliability and comprehensiveness of the intelligent risk identification solution for power training rooms and the effectiveness of autonomous monitoring, analysis, and management are not good. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent management system and method for power training rooms based on unmanned recording and broadcasting technology, which solves the technical problems of poor reliability and comprehensiveness in the implementation of intelligent risk identification schemes for power training rooms and the poor effect of autonomous supervision, analysis and management in existing schemes.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] The intelligent management system for power training rooms based on unmanned recording and broadcasting technology includes a regular power training anomaly monitoring and analysis module, which is used to monitor and record the regular anomalies of different students' power training operations in the power training room according to the training number, and obtain the first operation anomaly record data corresponding to each student.

[0007] The intelligent power training anomaly monitoring and analysis module is used to monitor and autonomously identify and record anomalies in the power training operations of different trainees based on monitoring and identification technology, and obtain the second operation anomaly record data corresponding to different trainees.

[0008] The intelligent identification, evaluation and management module for power training anomalies is used to process and analyze the impact of the first operational anomaly record data corresponding to different trainees on their second operational anomaly record data based on the operational anomaly number, and adaptively implement targeted optimization training for intelligent identification defects of different anomaly types based on the analysis results.

[0009] Preferably, when conducting routine and full-process monitoring of electrical training operations by different trainees in the electrical training room, the first anomaly detection stamp, the first anomaly content, and the first anomaly type corresponding to the occurrence of the anomaly during the trainee's electrical training process are obtained;

[0010] The total number of first anomalies obtained by the trainee during the power operation is counted and set as the first anomaly identifier. The first anomaly identifier is then sorted and combined with several first anomaly discovery stamps, first anomaly contents and first anomaly types obtained by the supervisor according to the power operation sequence to obtain the first operation anomaly record data corresponding to the trainee.

[0011] Preferably, the second practical anomaly record data includes the second anomaly identifier of the trainee and a second anomaly discovery stamp, second anomaly content and second anomaly type of several regulatory identification sorting combinations.

[0012] Preferably, when preprocessing the first and second practical operation anomaly record data corresponding to different trainees according to the practical training number, the first and second practical operation anomaly record data corresponding to the trainees are analyzed through the anomaly consistency identification function to output the anomaly supervision consistency value μ corresponding to the power practical operation anomaly of different trainees.

[0013] Among them, the abnormal supervision consistency value includes a value of 0 or 1;

[0014] The student with the abnormal monitoring consistency value of 0 is marked as the first student;

[0015] The student with the abnormal regulatory consistency value of 1 is marked as the second student.

[0016] Preferably, when the value of the first anomaly identifier in the first practical anomaly record data of the second student is the same as the value of the second anomaly identifier in the second practical anomaly record data, the second student is subjected to autonomous anomaly identification consistency processing analysis.

[0017] Match all the first abnormal content in the first practical abnormal record data of the second student with all the self-generated abnormal content in its second practical abnormal record data in the order of the first abnormal discovery stamp;

[0018] If all the first abnormal content in the first practical abnormal record data of the second student matches all the second abnormal content in its second practical abnormal record data, then an autonomously identified abnormal consistency label is generated.

[0019] If the first abnormal content in the first practical abnormal record data of the second student does not match all the second abnormal content in its second practical abnormal record data, an autonomous identification abnormality inconsistency label is generated, and an intelligent identification defect investigation scheme is implemented based on the autonomous identification abnormality inconsistency label.

[0020] Preferably, when the value of the first abnormality identifier in the first practical abnormality record data of the second trainee is different from the value of the second abnormality identifier in the second practical abnormality record data, an intelligent identification and defect investigation scheme is implemented on the second practical abnormality record data obtained by the supervision of the second trainee.

[0021] Preferably, when implementing the intelligent identification and defect investigation scheme, the first abnormal content in the first practical abnormal record data of the second student is sequentially matched with the second abnormal content in the second practical abnormal record data, and the first abnormal content that does not match is marked as the target abnormal content, and the first abnormal type to which the target abnormal content belongs is marked as the target abnormal type.

[0022] Based on the first anomaly discovery stamp and the recording time period corresponding to the target anomaly content, the recorded video of the corresponding student's power practice is marked as the target recorded video;

[0023] The recorded videos belonging to the same target anomaly type are sorted and combined to obtain the target recorded video set corresponding to the target anomaly type.

[0024] Preferably, when performing data analysis on the intelligent identification defects of all target anomaly types, the total number of target recorded videos in the target recorded video set corresponding to the target anomaly type is counted, and then calculated using the formula... Calculate the impact degree σ of the identification defect corresponding to the target anomaly type; where n is the total number of target recorded videos corresponding to the target anomaly type; N is the total number of all first anomaly contents corresponding to the target anomaly type in the first practical anomaly record data of all trainees; A is the standard value of the identification defect impact;

[0025] If the impact of the identified defect is less than 0, a low impact warning for the identified defect is generated, and the first autonomous optimization scheme for the corresponding target anomaly type is implemented.

[0026] Conversely, a high-impact warning for identification defects is generated, and a second autonomous optimization scheme for the corresponding target anomaly type is implemented.

[0027] Preferably, the expression for the anomaly consistency identification function is: In the formula, a and b are the values ​​of the first abnormality identifier in the first practical abnormality record data of the trainee and the second abnormality identifier in the second practical abnormality record data, respectively.

[0028] Intelligent management methods for power training labs based on unmanned recording and broadcasting technology include:

[0029] Based on the training number, routine abnormalities in the power training operation of different students in the power training room are monitored and recorded in sequence to obtain the first abnormal operation record data corresponding to each student.

[0030] Based on monitoring and identification technology, the entire process of power training operations of different trainees is monitored and anomalies are automatically identified and recorded, resulting in second-stage anomaly record data for different trainees.

[0031] Based on the training number, the first practical operation anomaly record data corresponding to different trainees is used to process and analyze the impact of the practical operation anomaly autonomous identification on their second practical operation anomaly record data. Based on the analysis results, targeted optimization training is carried out for intelligent identification defects of different anomaly types.

[0032] Compared to existing solutions, the beneficial effects achieved by this invention are:

[0033] This invention monitors and records routine anomalies in the power training operations of different trainees in the power training room, obtaining first-level anomaly record data for each trainee. This not only enables proactive monitoring and statistical analysis of different anomalies in the power training operations of different trainees, but also provides reliable multi-dimensional verification data support for the reliability analysis of intelligent anomaly identification of existing monitoring and identification technologies.

[0034] This invention uses monitoring and identification technology to monitor and record abnormalities in the power training operations of different trainees throughout the entire process, and obtains second-level abnormality record data for each trainee. This enables trainees to autonomously identify and record abnormalities in their power training operations, and improves the diversity and comprehensiveness of abnormality monitoring in trainees' power training operations.

[0035] This invention preprocesses the first and second practical operation anomaly records corresponding to different trainees, enabling the classification of abnormalities in power training operations for different trainees. By analyzing the impact of the first practical operation anomaly record data on the second practical operation anomaly record data corresponding to different trainees, and adaptively optimizing the intelligent identification defects of different anomaly types based on the analysis results, this invention achieves proactive monitoring and analysis, as well as targeted optimization management, of existing autonomous identification schemes for power training operations anomalies. This improves the reliability and comprehensiveness of the intelligent risk identification scheme for power training rooms, enhancing the effectiveness of autonomous monitoring, analysis, and management. Attached Figure Description

[0036] The invention will now be further described with reference to the accompanying drawings.

[0037] Figure 1 This is a block diagram of the intelligent management system for power training rooms based on unmanned recording and broadcasting technology according to the present invention.

[0038] Figure 2 This is a flowchart of the intelligent management method for power training rooms based on unmanned recording and broadcasting technology according to the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Example 1: As Figure 1 As shown, the present invention is an intelligent management system for power training rooms based on unmanned recording and broadcasting technology, including a conventional power training anomaly monitoring and analysis module, an intelligent power training anomaly monitoring and analysis module, and a power training anomaly intelligent identification, evaluation, and management module.

[0041] The routine power training anomaly monitoring and analysis module is used to monitor and record routine anomalies in the power training room for different trainees according to their training numbers, obtaining the first anomaly record data for each trainee; including:

[0042] When conducting routine and full-process monitoring of abnormalities in the power training operations of different trainees in the power training room, the system obtains the first abnormality discovery stamp, the first abnormality content, and the first abnormality type corresponding to the occurrence of the abnormality during the trainee's power operation; the unit of the first abnormality discovery stamp is accurate to the second.

[0043] The first type of anomaly can be determined based on the actual anomaly classification criteria, including but not limited to the type of operation of the illegal tool and the type of operation of the illegal behavior.

[0044] It should be noted that routine and abnormal monitoring can be carried out throughout the entire process, specifically by using IoT technology and manual supervision to record and statistically analyze violations that occur during students' power training operations.

[0045] Specifically, when using IoT technology to record and statistically analyze violations during students' electrical training operations, gravity sensors, RFID tags, and infrared sensors are used to monitor and analyze the usage status of related tools during the students' electrical training operations. For example, gravity sensors, RFID tags, and / or infrared sensors are used to monitor and record whether students are wearing insulated gloves, safety helmets, or entering high-voltage areas without wearing insulated shoes.

[0046] Manual supervision can be carried out by the training instructors, focusing on recording and statistically analyzing students' violations during electrical practical operations;

[0047] In addition, identical violation data based on IoT technology and manual supervision can be processed using existing automated deduplication technology. The specific implementation steps will not be elaborated here.

[0048] The total number of all first anomalies obtained by the statistical trainee during the power operation is recorded and set as the first anomaly identifier. The first anomaly identifier is then sorted and combined with several first anomaly discovery stamps, first anomaly contents and first anomaly types obtained by the statistical trainee in the order of power operation to obtain the first operation anomaly record data corresponding to the trainee.

[0049] In this embodiment of the invention, by monitoring and recording routine anomalies in the power training operations of different trainees in the power training room, the first operational anomaly record data corresponding to each trainee is obtained. This not only enables proactive monitoring and statistics of different anomalies in the power training operations of different trainees, but also provides reliable multi-dimensional verification data support for the reliability analysis of intelligent anomaly identification of existing monitoring and identification technologies.

[0050] The intelligent power training anomaly monitoring and analysis module is used to monitor and autonomously identify anomalies in the power training operations of different trainees based on monitoring and identification technology, obtaining secondary operational anomaly record data corresponding to different trainees; including:

[0051] Among them, the second practical abnormality record data includes the second abnormality identifier of the trainee and several combinations of the second abnormality discovery stamp, second abnormality content and second abnormality type of the supervisory identification and sorting.

[0052] It should be noted that the method for obtaining and processing the second anomaly identifier is the same as that for obtaining and processing the first anomaly identifier;

[0053] Furthermore, the proactive anomaly identification, analysis, and recording of power training operations by different trainees based on monitoring and identification technology disclosed in this embodiment of the invention are existing conventional technical means, such as target detection algorithms: YOLO series (YOLOv5 / v7 / v8), Faster R-CNN; behavior recognition algorithms: spatiotemporal convolutional networks (3D-CNN); pose estimation algorithms: OpenPose; the specific implementation steps are not elaborated here;

[0054] In this embodiment of the invention, monitoring and identification technology is used to monitor and record the entire process of power training operations of different trainees and to identify and record abnormalities autonomously. This results in the acquisition of second-level operational abnormality record data for each trainee, thereby enabling autonomous identification and recording of abnormalities in trainees' power training operations and improving the diversity and comprehensiveness of abnormality monitoring in trainees' power training operations.

[0055] The intelligent identification, evaluation, and management module for power training anomalies is used to process and analyze the impact of the first operational anomaly record data corresponding to different trainees on their second operational anomaly record data based on the training number, and adaptively implement targeted optimization training for intelligent identification defects of different anomaly types based on the analysis results; including:

[0056] When preprocessing the first and second practical operation anomaly record data corresponding to different trainees according to the practical training number, the first and second practical operation anomaly record data corresponding to the trainees are analyzed through the anomaly consistency identification function, and the anomaly supervision consistency value μ corresponding to the power practical operation anomaly of different trainees is output.

[0057] The expression for the anomaly consistency identification function is: In the formula, a and b are the values ​​of the first abnormality identifier in the first practical abnormality record data of the trainee and the second abnormality identifier in the second practical abnormality record data, respectively.

[0058] Among them, the abnormal supervision consistency value is used to process and calculate the abnormal data obtained by different methods of supervision during the trainees' power training operation, so as to digitally represent the abnormal supervision status of the corresponding power training operation.

[0059] The abnormal monitoring consistency value includes a value of 0 or 1;

[0060] The student with the abnormal monitoring consistency value of 0 is marked as the first student;

[0061] The student with the abnormal monitoring consistency value of 1 is marked as the second student.

[0062] It should be noted that by preprocessing the first and second practical operation anomaly record data corresponding to different trainees, different anomaly types in the power training operation process of different trainees can be obtained. This allows for targeted anomaly verification and analysis of the power training operation of different trainees in the future, thereby improving the efficiency and pertinence of power training operation anomaly supervision and handling.

[0063] It is understandable that there are two situations for the abnormal supervision of the second trainee. One is that the value of the first abnormality identifier in the first practical abnormality record data of the second trainee is the same as the value of the second abnormality identifier in the second practical abnormality record data, but the power practical abnormalities obtained by different supervision methods are not exactly the same.

[0064] Another issue is that the value of the first anomaly marker in the first practical anomaly record data of the second trainee is different from the value of the second anomaly marker in the second practical anomaly record data, indicating that there is a vulnerability in the power practical anomaly data obtained by the supervisory system.

[0065] When the value of the first anomaly identifier in the first practical anomaly record data of the second student is the same as the value of the second anomaly identifier in the second practical anomaly record data, the second student will be subject to autonomous anomaly identification consistency processing analysis.

[0066] Match all the first abnormal content in the first practical abnormal record data of the second student with all the self-generated abnormal content in its second practical abnormal record data in the order of the first abnormal discovery stamp;

[0067] If all the first abnormal content in the first practical abnormal record data of the second student matches all the second abnormal content in its second practical abnormal record data, then an autonomously identified abnormal consistency label is generated.

[0068] If the first abnormal content in the first practical abnormal record data of the second student does not match all the second abnormal content in its second practical abnormal record data, an autonomous identification abnormality inconsistency label is generated, and an intelligent identification defect investigation plan is implemented based on the autonomous identification abnormality inconsistency label.

[0069] In addition, when the value of the first abnormality identifier in the first practical abnormality record data of the second trainee is different from the value of the second abnormality identifier in the second practical abnormality record data, an intelligent identification defect investigation scheme is implemented on the second practical abnormality record data obtained by the supervision of the second trainee.

[0070] When implementing the intelligent identification and defect investigation scheme, the first abnormal content in the first practical abnormal record data of the second student is sequentially matched with the second abnormal content in the second practical abnormal record data. The first abnormal content that does not match is marked as the target abnormal content, and the first abnormal type to which the target abnormal content belongs is marked as the target abnormal type.

[0071] It should be noted that the mismatch here refers to the fact that the first abnormal content could not be found in the second operational abnormal record data according to the first abnormal discovery stamp. In addition, since there are time errors in the recording of different methods, the embodiments of the present invention can match the first abnormal content with the corresponding second abnormal content based on the first abnormal discovery stamp. The matching can be based on a preset abnormal record error range. The specific value of the abnormal record error range can be determined based on all the data of the historical abnormal record error range. The specific value is not limited.

[0072] Based on the first anomaly discovery stamp and the recording time period corresponding to the target anomaly content, the recorded video of the corresponding student's power practice is marked as the target recorded video;

[0073] The recording and playback saving period starts with the first anomaly discovery stamp as the start timestamp, and the first anomaly end stamp corresponding to the first anomaly discovery stamp is determined according to the preset saving duration. The unit of the recording and playback saving period is seconds, and the specific value is not limited. It can be determined according to the existing recording and playback design data, or customized according to the application requirements of the actual application scenario.

[0074] The recorded videos belonging to the same target anomaly type are sorted and combined to obtain the target recorded video set corresponding to the target anomaly type;

[0075] It should be noted that the target recorded video set can provide reliable data support for the subsequent intelligent identification defect data analysis corresponding to different target anomaly types, and can also provide reliable sample training data support for the subsequent intelligent identification defect optimization training corresponding to different target anomaly types, thereby improving the diversity of target recorded video set processing and utilization.

[0076] Furthermore, when performing data analysis on the intelligent identification defects of all target anomaly types, the total number of target recorded videos in the target recorded video set corresponding to the target anomaly type is counted, and then calculated using the formula... Calculate the impact degree σ of the identification defect corresponding to the target anomaly type; where n is the total number of target recorded videos corresponding to the target anomaly type; N is the total number of all first anomaly contents in the first practical anomaly record data of all trainees corresponding to the target anomaly type; A is the standard value of the identification defect impact, the specific value can be determined according to the existing design requirements data corresponding to the target anomaly type, or it can be determined according to the median of the identification defect impact degree of all target anomaly types.

[0077] It should be noted that the defect impact is used to calculate the defect data obtained from the regulatory processing of the target anomaly type, in order to digitally represent the impact of the corresponding defect, and to provide a reliable basis for subsequent targeted optimization management of the target anomaly type.

[0078] If the impact of the identified defect is less than 0, a low impact warning for the identified defect is generated, and the first autonomous optimization scheme for the corresponding target anomaly type is implemented.

[0079] Conversely, a high-impact warning for identification defects is generated, and a second autonomous optimization scheme for the corresponding target anomaly type is implemented;

[0080] Among them, the first identification autonomous optimization scheme specifically uses only the target recorded video set associated with the target anomaly type to conduct targeted sample training and optimization updates for its identification rules and identification content;

[0081] The second identification autonomous optimization scheme specifically utilizes the target recorded video set associated with the target anomaly type, as well as other normal recorded videos, to conduct comprehensive sample training and optimization updates for its identification rules and content.

[0082] In this embodiment of the invention, by preprocessing the first and second practical operation anomaly record data corresponding to different trainees, it is possible to classify the abnormalities in power training operations of different trainees. By processing and analyzing the impact of the first practical operation anomaly record data corresponding to different trainees on the autonomous identification of practical operation anomalies, and adaptively optimizing and training the intelligent identification defects of different anomaly types based on the analysis results, it is possible to actively supervise and analyze the existing autonomous identification scheme for power training operation anomalies and optimize and manage it in a targeted manner, thereby improving the reliability and comprehensive autonomous supervision, analysis and management effect of the intelligent risk identification scheme for power training rooms.

[0083] Example 2: Figure 2 As shown, this invention is an intelligent management method for power training rooms based on unmanned recording and broadcasting technology, comprising:

[0084] Based on the training number, routine abnormalities in the power training operation of different students in the power training room are monitored and recorded in sequence to obtain the first abnormal operation record data corresponding to each student.

[0085] Based on monitoring and identification technology, the entire process of power training operations of different trainees is monitored and anomalies are automatically identified and recorded, resulting in second-stage anomaly record data for different trainees.

[0086] Based on the training number, the first practical operation anomaly record data corresponding to different trainees is used to process and analyze the impact of the practical operation anomaly autonomous identification on their second practical operation anomaly record data. Based on the analysis results, targeted optimization training is carried out for intelligent identification defects of different anomaly types.

[0087] In the several embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0088] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0089] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or in the form of hardware plus software functional modules.

[0090] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent management system for power training rooms based on unmanned recording and broadcasting technology, characterized in that: It includes a regular power training anomaly monitoring and analysis module, which is used to monitor and record the regular anomalies of different trainees in the power training room according to the training number, and obtain the first operation anomaly record data corresponding to each trainee; The intelligent power training anomaly monitoring and analysis module is used to monitor and autonomously identify and record anomalies in the power training operations of different trainees based on monitoring and identification technology, and obtain the second operation anomaly record data corresponding to different trainees. The intelligent identification, evaluation and management module for power training anomalies is used to process and analyze the impact of the first operational anomaly record data corresponding to different trainees on their second operational anomaly record data based on the operational anomaly number, and adaptively implement targeted optimization training for intelligent identification defects of different anomaly types based on the analysis results.

2. The intelligent management system for power training rooms based on unmanned recording and broadcasting technology according to claim 1, characterized in that, When conducting routine and full-process monitoring of abnormalities in the power training operations of different trainees in the power training room, the system obtains the first abnormality discovery stamp, the first abnormality content, and the first abnormality type corresponding to the occurrence of the abnormality during the trainee's power operation process. The total number of first anomalies obtained by the trainee during the power operation is counted and set as the first anomaly identifier. The first anomaly identifier is then sorted and combined with several first anomaly discovery stamps, first anomaly contents and first anomaly types obtained by the supervisor according to the power operation sequence to obtain the first operation anomaly record data corresponding to the trainee.

3. The intelligent management system for power training rooms based on unmanned recording and broadcasting technology according to claim 2, characterized in that, The second practical anomaly record data includes the second anomaly identifier of the trainee and several combinations of second anomaly discovery stamps, second anomaly content and second anomaly type for supervisory identification and sorting.

4. The intelligent management system for power training rooms based on unmanned recording and broadcasting technology according to claim 3, characterized in that, When preprocessing the first and second practical operation anomaly record data corresponding to different trainees according to the practical training number, the first and second practical operation anomaly record data corresponding to the trainees are analyzed through the anomaly consistency identification function, and the anomaly supervision consistency value μ corresponding to the power practical operation anomaly of different trainees is output. Among them, the abnormal supervision consistency value includes a value of 0 or 1; The student with the abnormal monitoring consistency value of 0 is marked as the first student; The student with the abnormal regulatory consistency value of 1 is marked as the second student.

5. The intelligent management system for power training rooms based on unmanned recording and broadcasting technology according to claim 4, characterized in that, When the value of the first anomaly identifier in the first practical anomaly record data of the second student is the same as the value of the second anomaly identifier in the second practical anomaly record data, the second student will be subject to autonomous anomaly identification consistency processing analysis. Match all the first abnormal content in the first practical abnormal record data of the second student with all the self-generated abnormal content in its second practical abnormal record data in the order of the first abnormal discovery stamp; If all the first abnormal content in the first practical abnormal record data of the second student matches all the second abnormal content in its second practical abnormal record data, then an autonomously identified abnormal consistency label is generated. If the first abnormal content in the first practical abnormal record data of the second student does not match all the second abnormal content in its second practical abnormal record data, an autonomous identification abnormality inconsistency label is generated, and an intelligent identification defect investigation scheme is implemented based on the autonomous identification abnormality inconsistency label.

6. The intelligent management system for power training rooms based on unmanned recording and broadcasting technology according to claim 5, characterized in that, When the value of the first anomaly identifier in the first practical anomaly record data of the second trainee is different from the value of the second anomaly identifier in the second practical anomaly record data, an intelligent identification and defect investigation scheme is implemented in the second practical anomaly record data obtained by the supervision of the second trainee.

7. The intelligent management system for power training rooms based on unmanned recording and broadcasting technology according to claim 5 or 6, characterized in that, When implementing the intelligent identification and defect investigation scheme, the first abnormal content in the first practical abnormal record data of the second student is sequentially matched with the second abnormal content in the second practical abnormal record data. The first abnormal content that does not match is marked as the target abnormal content, and the first abnormal type to which the target abnormal content belongs is marked as the target abnormal type. Based on the first anomaly discovery stamp and the recording time period corresponding to the target anomaly content, the recorded video of the corresponding student's power practice is marked as the target recorded video; The recorded videos belonging to the same target anomaly type are sorted and combined to obtain the target recorded video set corresponding to the target anomaly type.

8. The intelligent management system for power training rooms based on unmanned recording and broadcasting technology according to claim 7, characterized in that, When performing data analysis on intelligent identification defects of all target anomaly types, the total number of target recorded videos in the target recorded video set corresponding to the target anomaly type is counted, and then calculated using the formula... Calculate the impact degree σ of the identification defect corresponding to the target anomaly type; where n is the total number of target recorded videos corresponding to the target anomaly type; N is the total number of all first anomaly contents corresponding to the target anomaly type in the first practical anomaly record data of all trainees; A is the standard value of the identification defect impact; If the impact of the identified defect is less than 0, a low impact warning for the identified defect is generated, and the first autonomous optimization scheme for the corresponding target anomaly type is implemented. Conversely, a high-impact warning for identification defects is generated, and a second autonomous optimization scheme for the corresponding target anomaly type is implemented.

9. The intelligent management system for power training rooms based on unmanned recording and broadcasting technology according to claim 4, characterized in that, The expression for the anomaly consistency identification function is: In the formula, a and b are the values ​​of the first abnormality identifier in the first practical abnormality record data of the trainee and the second abnormality identifier in the second practical abnormality record data, respectively.

10. A method for intelligent management of power training rooms based on unmanned recording and broadcasting technology, using the intelligent management system for power training rooms based on unmanned recording and broadcasting technology as described in any one of claims 1-9, characterized in that, include: Based on the training number, routine abnormalities in the power training operation of different students in the power training room are monitored and recorded in sequence to obtain the first abnormal operation record data corresponding to each student. Based on monitoring and identification technology, the entire process of power training operations of different trainees is monitored and anomalies are automatically identified and recorded, resulting in second-stage anomaly record data for different trainees. Based on the training number, the first practical operation anomaly record data corresponding to different trainees is used to process and analyze the impact of the practical operation anomaly autonomous identification on their second practical operation anomaly record data. Based on the analysis results, targeted optimization training is carried out for intelligent identification defects of different anomaly types.

Images