Safety early warning method and system for vocational education training room

Abstract

The invention relates to the field of intelligent wearing, in particular to a vocational education training room safety early warning method and system, and the method comprises the steps: S10, collecting the operation data of a student in real time in a training process; s20, based on an AR display technology, superposing the practical training scene and the virtual information, and sending guidance information, a simulation operation process and question reply to a student terminal; s30, analyzing the operation data of the student based on a preset algorithm, and identifying dangerous behaviors and abnormal behaviors; s40, when dangerous behaviors and abnormal behaviors exist, an audio-visual early warning signal is sent out; and S50, storing the operation data and the early warning record of the student in a preset database, generating a feedback report, and sending the feedback report to an intelligent education platform end. The method has the effect of improving the safety, interactivity and effectiveness of practical training.

Description

Technical Field

[0001] The present application relates to the field of smart wearables, and specifically to a method and system for safety warning in vocational education training rooms. Background Art

[0002] At a time when vocational education is a key national development strategy, the safety management of training rooms has become an urgent problem to be solved. In recent years, the country has vigorously promoted the development of vocational education, with the core goal of improving students' practical training skills. However, the challenge faced by vocational education training rooms is the serious imbalance in the teacher-student ratio, which leads to students often being left alone during the training process, or the training resources being closed due to safety concerns, and failing to achieve truly effective skills training. This situation is mainly due to the fact that the number of teachers is far less than that of students, and due to concerns about safety accidents, the skill training potential of the training room is greatly limited.

[0003] In this context, the existing safety measures for vocational education training rooms, including safety training, physical protective equipment, video surveillance and on-site guidance by teachers, have ensured the safety of training to a certain extent, but there are still significant deficiencies in the safety, interactivity and effectiveness of training. Although safety training is indispensable, it is still common for students to forget and make mistakes in actual operations; traditional safety helmets and protective equipment only provide passive protection and lack real-time monitoring and early warning mechanisms; although the video surveillance system can record the scene, it lacks real-time analysis and immediate feedback to students; and on-site supervision by teachers is limited by the number of people and field of vision, making it difficult to achieve comprehensive coverage. Therefore, improvements are needed. Summary of the invention

[0004] In order to improve the safety, interactivity and effectiveness of practical training, this application provides a method and system for safety warning in vocational education training rooms.

[0005] The first object of the invention of this application is achieved through the following technical solutions:

[0006] A method for safety early warning in a vocational education training room, comprising the steps of:

[0007] S10: During the training process, the students’ operation data is collected in real time;

[0008] S20: Based on AR display technology, the training scene is superimposed with virtual information, and guidance information, simulated operation procedures, and question answers are sent to the student end;

[0009] S30: Analyze the student's operation data based on a preset algorithm to identify dangerous behaviors and abnormal behaviors;

[0010] S40: Send out audio-visual warning signals when there are dangerous or abnormal behaviors;

[0011] S50: Store the students' operation data and warning records in the preset database, generate a feedback report and send it to the smart education platform.

[0012] In a preferred embodiment, before the step of collecting the student's operation data in real time during the training process, the following steps are included:

[0013] S110: Locate the position of the dangerous area based on the three-dimensional spatial positioning technology and the preset training scene environment map;

[0014] S210: Based on AR display technology, dangerous areas are marked in real time and sent to the student end.

[0015] In a preferred embodiment, the step of collecting students' operation data in real time during the training process includes the following steps:

[0016] S101: Based on a preset algorithm, when it is recognized that a student starts to perform a key operation, the student's operation data is collected, the student's operation data includes multi-angle operation video, operation audio, training scene environment data, step frequency data, and the operation type is marked;

[0017] S102: The key operations include high-risk operations, fine operations, standardized operations, and emergency operations.

[0018] In a preferred embodiment, the AR display technology is used to superimpose the training scene with virtual information, and send guidance information, simulated operation procedures, and question answers to the student end, including the steps of:

[0019] S201: Matching the student's operation data and the requirements of the preset practical training task with the preset database to match the most relevant guidance information and simulation operation process;

[0020] S202: When receiving a question from a student, the question is matched with a preset database, an answer is matched, and the answer is sent to the student based on AR display technology.

[0021] In a preferred embodiment, the student's operation data and the requirements of the preset practical training task are matched with the preset database to match the most relevant guidance information and simulated operation process steps, including the steps

[0022] SA1: Identify students’ operation level based on their operation data;

[0023] SA2: Based on the students' operation level and the requirements of the preset practical training tasks, adjust the presentation of the guidance information and simulation operation process;

[0024] SA3: Based on AR display technology, the student terminal performs interactive steps on the simulated operation process;

[0025] SA4: The interactive steps include pause, replay, step-by-step learning, and evaluation.

[0026] In a preferred embodiment, the step of analyzing the student's operation data based on a preset algorithm to identify dangerous behaviors and abnormal behaviors includes the following steps:

[0027] SB: pre-processing the multi-angle operation video, the operation audio, and the step frequency data;

[0028] SB1: Based on the convolutional neural network deep learning algorithm, key features are gradually extracted from the multi-angle operation video, and the key features include student posture recognition and action trajectory from low level to high level;

[0029] SB2: extracting audio features from the operation audio, wherein the audio features include tone and audio;

[0030] SB3: extracting a cadence feature from the cadence data, wherein the cadence feature includes an average cadence value and a peak cadence value,

[0031] SB4: Fusing the key features, the audio features, and the step frequency features to output a multimodal feature set;

[0032] SB5: Compare the training scenario environment data with the preset safety environment and adjust the recognition threshold of dangerous and abnormal behaviors;

[0033] SB6: Based on the deep learning model, the multimodal feature set is compared with the recognition threshold for similarity;

[0034] SB7: When the similarity is less than the first preset threshold, the student's operation is considered to be normal behavior;

[0035] SB8: When the similarity is greater than the first preset threshold but less than the second preset threshold, the student's operation is considered to be abnormal behavior;

[0036] SB9: When the similarity is greater than the second preset threshold, the student's operation is considered to be a dangerous behavior.

[0037] In a preferred embodiment, the step of sending out an audiovisual warning signal when there is dangerous behavior or abnormal behavior includes the steps of:

[0038] S401: When there is dangerous behavior or abnormal behavior, a multimodal warning signal including visual and auditory is generated based on the student's operation data;

[0039] S402: When a warning signal is issued, emergency operation instructions and escape routes are pushed to the student end based on AR display technology.

[0040] The second invention objective of this application is achieved through the following technical solutions:

[0041] A system for safety early warning of vocational education training rooms, comprising:

[0042] Real-time acquisition module: during the training process, real-time acquisition of students' operation data;

[0043] Sending module: Based on AR display technology, the training scene is superimposed with virtual information, and guidance information, simulated operation procedures, and question answers are sent to the student end;

[0044] Identification module: Based on a preset algorithm, analyze the student's operation data to identify dangerous and abnormal behaviors;

[0045] Early warning module: when there is dangerous behavior or abnormal behavior, it will send out audio-visual early warning signals;

[0046] Storage module: Store students' operation data and warning records in the preset database, generate feedback reports and send them to the smart education platform.

[0047] The third invention objective of this application is achieved through the following technical solutions:

[0048] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for safety warning in vocational education training rooms are implemented.

[0049] The fourth objective of the present application is achieved through the following technical solutions:

[0050] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned method for safety warning in vocational education training rooms.

[0051] In summary, the present application includes at least one of the following beneficial technical effects:

[0052] 1. By collecting students' operation data in real time (S10), and using AR display technology to superimpose the training scene with virtual information, students are provided with real-time guidance information, simulated operation procedures and question answers (S20). At the same time, the operation data is analyzed based on a preset intelligent algorithm to identify dangerous and abnormal behaviors (S30). Once these behaviors are detected, the system immediately sends out an audio-visual warning signal (S40), and stores all operation data and warning records in a preset database (S50), and generates a feedback report to send to the smart education platform. The effect that this principle can achieve is that it not only improves the safety and interactivity of practical training, but also reduces the occurrence of safety accidents through timely and effective warnings and guidance. At the same time, it provides data support for teaching evaluation and risk management, thereby improving the overall teaching and management level of vocational education training rooms.

[0053] 2. First, accurately identify and locate the dangerous areas through three-dimensional spatial positioning technology and the preset training scene environment map (S110), and then use AR display technology (S210) to mark these dangerous areas in real time and display them to students. The effect of this is that students can intuitively identify potential dangerous areas through the AR interface during the training process, thereby avoiding or reducing the occurrence of misoperation and safety accidents. This principle not only enhances the safety of the training environment, but also improves students' cognition and understanding of the training environment through the integration of technology, and realizes the effective combination of training teaching and safety management.

[0054] 3. In step S10, the key operations that students start to perform are intelligently identified through a preset algorithm (S101), and the collection of multi-angle operation videos, operation audios, training scene environmental data, and step frequency data is immediately started, and the operation types are marked. These key operations include high-risk operations, fine operations, standardized operations, and emergency operations (S102). The effect that can be achieved by this principle is that the system can capture and analyze the detailed behavior and environmental information of students when performing important operations in a targeted manner, ensuring that accurate safety monitoring and guidance can be provided at critical moments. This not only improves the safety of practical training, but also provides support for teaching evaluation and operation standardization through detailed data records, thereby improving the teaching quality of the training room and the students' operational skills.

[0055] 4. In step S20, the student's operation data and preset practical training task requirements are matched with the preset database (S201) to find the most relevant guidance information and simulate the operation process. When the student receives the question, the question is matched with the database to provide the corresponding answer (S202), and then the answer is sent to the student in real time using AR display technology. The effect that this principle can achieve is that the system can provide customized guidance and support based on the students' actual operation conditions and specific task requirements, ensuring that students can get the most relevant and timely help during the training process. This not only improves the personalization and interactivity of practical training teaching, but also enhances students' learning experience and operation skills through an efficient question-and-answer system, thereby improving the efficiency and safety of practical training. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flowchart of an implementation of a method embodiment for safety warning in a vocational education training room of the present application;

[0057] Figure 2 This is a flowchart of an implementation before step S10 in an embodiment of a method for safety warning in a vocational education training room of the present application;

[0058] Figure 3 This is a flowchart of an implementation of step S10 in an embodiment of a method for safety warning in a vocational education training room of the present application;

[0059] Figure 4 This is a flowchart for implementing step S20 in an embodiment of a method for safety warning in a vocational education training room of the present application;

[0060] Figure 5 This is a flowchart for implementing step S201 in an embodiment of a method for safety warning in a vocational education training room of the present application;

[0061] Figure 6 This is a flowchart of an implementation of step S30 in an embodiment of a method for safety warning in a vocational education training room of the present application;

[0062] Figure 7 This is a flowchart of an implementation of step S40 in an embodiment of a method for safety warning in a vocational education training room of the present application;

[0063] Figure 8 This is a principle block diagram of a computer device of the present application. DETAILED DESCRIPTION

[0064] The following is combined with Figure 1-8 This application is described in further detail.

[0065] In one embodiment, if Figure 1As shown, the present application discloses a method for safety early warning of vocational education training rooms, which specifically includes the following steps:

[0066] S10: During the training process, the students’ operation data is collected in real time;

[0067] S20: Based on AR display technology, the training scene is superimposed with virtual information, and guidance information, simulated operation procedures, and question answers are sent to the student end;

[0068] S30: Analyze the student's operation data based on a preset algorithm to identify dangerous behaviors and abnormal behaviors;

[0069] S40: Send out audio-visual warning signals when there are dangerous or abnormal behaviors;

[0070] S50: Store the students' operation data and warning records in the preset database, generate a feedback report and send it to the smart education platform.

[0071] In this embodiment, the working principle is to collect students' operation data in real time (S10), and use AR display technology to superimpose the training scene with virtual information to provide students with real-time guidance information, simulated operation procedures and question answers (S20). At the same time, the operation data is analyzed based on a preset intelligent algorithm to identify dangerous behaviors and abnormal behaviors (S30). Once these behaviors are found, the system immediately sends out an audio-visual warning signal (S40), and stores all operation data and warning records in a preset database (S50), and generates a feedback report to send to the smart education platform. The effect that this principle can achieve is that it not only improves the safety and interactivity of practical training teaching, but also reduces the occurrence of safety accidents through timely and effective warnings and guidance. At the same time, it provides data support for teaching evaluation and risk management, thereby improving the overall teaching and management level of vocational education training rooms.

[0072] Figure 2 , before step S10, including the steps:

[0073] S110: Locate the position of the dangerous area based on the three-dimensional spatial positioning technology and the preset training scene environment map;

[0074] S210: Based on AR display technology, dangerous areas are marked in real time and sent to the student end.

[0075] In this embodiment, the principle is to first accurately identify and locate the position of the dangerous area through three-dimensional spatial positioning technology and a preset practical training scene environment map (S110), and then use AR display technology (S210) to mark these dangerous areas in real time and display them to students. The effect of this is that students can intuitively identify potential dangerous areas through the AR interface during the training process, thereby avoiding or reducing the occurrence of misoperation and safety accidents. This principle not only enhances the safety of the training environment, but also improves students' cognition and understanding of the training environment through the integration of technology, and realizes the effective combination of practical training teaching and safety management.

[0076] Figure 3 , step S10, comprising the steps of:

[0077] S101: Based on a preset algorithm, when it is recognized that a student starts to perform a key operation, the student's operation data is collected, the student's operation data includes multi-angle operation video, operation audio, training scene environment data, step frequency data, and the operation type is marked;

[0078] S102: The key operations include high-risk operations, fine operations, standardized operations, and emergency operations.

[0079] In this embodiment, the principle is that in step S10, a preset algorithm is used to intelligently identify the key operations that students start to perform (S101), and then start the collection of multi-angle operation videos, operation audios, training scene environmental data, and step frequency data, and mark the operation types. These key operations include high-risk operations, fine operations, standardized operations, and emergency operations (S102). The effect that can be achieved by such a principle is that the system can capture and analyze the detailed behavior and environmental information of students when performing important operations in a targeted manner, ensuring that accurate safety monitoring and guidance can be provided at critical moments. This not only improves the safety of practical training teaching, but also provides support for teaching evaluation and operation standardization through detailed data records, thereby improving the teaching quality of the training room and the students' operating skills.

[0080] Figure 4 , step S20, including the steps

[0081] S201: Matching the student's operation data and the requirements of the preset practical training task with the preset database to match the most relevant guidance information and simulation operation process;

[0082] S202: When receiving a question from a student, the question is matched with a preset database, an answer is matched, and the answer is sent to the student based on AR display technology.

[0083] In this embodiment, the principle is that in step S20, the student's operation data and preset practical training task requirements are matched with the preset database (S201) to find the most relevant guidance information and simulate the operation process, and when the student receives the question, the question is matched with the database to provide the corresponding answer (S202), and then the answer is sent to the student in real time using AR display technology. The effect that this principle can achieve is that the system can provide customized guidance and support based on the students' actual operation conditions and specific task requirements, ensuring that students can get the most relevant and timely help during the practical training process. This not only improves the personalization and interactivity of practical training teaching, but also enhances students' learning experience and operational skills through an efficient question-and-answer system, thereby improving the efficiency and safety of practical training.

[0084] Figure 5 , step S201, comprising the steps

[0085] SA1: Identify students’ operation level based on their operation data;

[0086] SA2: Based on the students' operation level and the requirements of the preset practical training tasks, adjust the presentation of the guidance information and simulation operation process;

[0087] SA3: Based on AR display technology, the student terminal performs interactive steps on the simulated operation process;

[0088] SA4: The interactive steps include pause, replay, step-by-step learning, and evaluation.

[0089] In this embodiment, the principle is that in step S201, the operation level of the student is identified by analyzing the student's operation data (SA1), and according to this level and the requirements of the preset practical training tasks, the presentation method of the guidance information and the simulated operation process is dynamically adjusted (SA2). Using AR display technology, students can interact with the simulated operation process on the student side (SA3), including executing interactive steps such as pause, replay, step-by-step learning, and evaluation (SA4). The effect that this principle can achieve is that the system provides each student with a customized learning experience. Through interactive operation simulation, students can learn and practice practical operations according to their own learning rhythm and understanding level, thereby improving the autonomy and efficiency of learning. This personalized teaching method not only enhances students' operational skills, but also promotes students' skill consolidation and improvement through real-time feedback and evaluation mechanisms, effectively improving the overall effect of practical training teaching.

[0090] Figure 6 , step S30, comprising the steps of:

[0091] SB: pre-processing the multi-angle operation video, the operation audio, and the step frequency data;

[0092] SB1: Based on the convolutional neural network deep learning algorithm, key features are gradually extracted from the multi-angle operation video, and the key features include student posture recognition and action trajectory from low level to high level;

[0093] SB2: extracting audio features from the operation audio, wherein the audio features include tone and audio;

[0094] SB3: extracting a cadence feature from the cadence data, wherein the cadence feature includes an average cadence value and a peak cadence value,

[0095] SB4: Fusing the key features, the audio features, and the step frequency features to output a multimodal feature set;

[0096] SB5: Compare the training scenario environment data with the preset safety environment and adjust the recognition threshold of dangerous and abnormal behaviors;

[0097] SB6: Based on the deep learning model, the multimodal feature set is compared with the recognition threshold for similarity;

[0098] SB7: When the similarity is less than the first preset threshold, the student's operation is considered to be normal behavior;

[0099] SB8: When the similarity is greater than the first preset threshold but less than the second preset threshold, the student's operation is considered to be abnormal behavior;

[0100] SB9: When the similarity is greater than the second preset threshold, the student's operation is considered to be a dangerous behavior.

[0101] In this embodiment, based on multimodal data fusion and deep learning technology, the purpose of safety warning in the training room is achieved by real-time monitoring and analysis of students' operating behaviors. Specifically, the system first preprocesses the multi-angle operation video, operation audio and cadence data (SB) in order to purify the data and improve the accuracy of subsequent analysis. Next, the convolutional neural network deep learning algorithm is used to extract key visual features such as students' posture and movement trajectory from the video (SB1), while extracting tone and audio features from the audio (SB2), and extracting the cadence average and peak value from the cadence data (SB3). These features are fused into a multimodal feature set (SB4) to form a comprehensive behavior description.

[0102] The system then compares the training scenario environment data with the preset safety environment standards (SB5) and adjusts the recognition thresholds for dangerous and abnormal behaviors based on the comparison results. This step ensures the dynamic and adaptable nature of the recognition process, and can automatically adjust the warning standards according to different training environments.

[0103] Through the deep learning model, the system compares the multimodal feature set with the recognition threshold for similarity (SB6), and judges the student's operation behavior based on the comparison results. When the similarity is less than the first preset threshold, the operation is considered normal (SB7); when the similarity is between the two preset thresholds, the operation is considered abnormal (SB8); and when the similarity is greater than the second preset threshold, the operation is considered dangerous (SB9).

[0104] Figure 7 , step S40, comprising the steps of:

[0105] S401: When there is dangerous behavior or abnormal behavior, a multimodal warning signal including visual and auditory is generated based on the student's operation data;

[0106] S402: When a warning signal is issued, emergency operation instructions and escape routes are pushed to the student end based on AR display technology.

[0107] In this embodiment, the principle is that in step S40, when dangerous or abnormal behavior is detected, the system generates a multimodal warning signal including vision and hearing based on the student's operation data (S401), and pushes emergency operation instructions and escape routes to the student end through AR display technology (S402). The effect that can be achieved by this principle is that when the system identifies potential safety risks, it can quickly issue alarms to students through multiple sensory pathways to improve the immediacy and effectiveness of the warning. At the same time, the intuitive guides and paths provided by AR technology enable students to quickly understand and implement emergency measures, thereby greatly improving the safety of the training environment in emergency situations and the students' self-rescue ability, and effectively reducing the risk of accidents.

[0108] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0109] In one embodiment, a system for safety warning of a vocational education training room is provided, and the system for safety warning of a vocational education training room corresponds to a method for safety warning of a vocational education training room in the above embodiment. The system for safety warning of a vocational education training room includes:

[0110] Real-time acquisition module: during the training process, real-time acquisition of students' operation data;

[0111] Sending module: Based on AR display technology, the training scene is superimposed with virtual information, and guidance information, simulated operation procedures, and question answers are sent to the student end;

[0112] Identification module: Based on a preset algorithm, analyze the student's operation data to identify dangerous and abnormal behaviors;

[0113] Early warning module: when there is dangerous behavior or abnormal behavior, it will send out audio-visual early warning signals;

[0114] Storage module: Store students' operation data and warning records in the preset database, generate feedback reports and send them to the smart education platform.

[0115] Optionally, also include:

[0116] Positioning module: locates the dangerous area based on three-dimensional spatial positioning technology and preset training scene environment map;

[0117] The first sending module: Based on AR display technology, the dangerous area is marked in real time and sent to the student end.

[0118] Optionally, also include:

[0119] The first acquisition module: based on a preset algorithm, when it is recognized that a student starts to perform a key operation, the student's operation data begins to be collected. The student's operation data includes multi-angle operation videos, operation audio, training scene environment data, and step frequency data, and the operation type is marked;

[0120] First definition module: The key operations include high-risk operations, fine operations, standardized operations, and emergency operations.

[0121] Optionally, also include:

[0122] The first matching module: matches the student's operation data and the requirements of the preset practical training tasks with the preset database to match the most relevant guidance information and simulated operation process;

[0123] The second matching module: When receiving questions from students, the questions are matched with the preset database, the answers are matched, and the answers are sent to the students based on AR display technology.

[0124] Optionally, also include:

[0125] Operation level module: Identify students’ operation level based on their operation data;

[0126] Adjustment module: based on the students' operation level and the requirements of the preset practical training tasks, adjust the presentation of the guidance information and the simulation operation process;

[0127] Interactive module: Based on AR display technology, students can interact with the simulated operation process;

[0128] Second definition module: The interactive steps include pause, replay, step-by-step learning, and evaluation.

[0129] Optionally, also include:

[0130] The first module: pre-processing the multi-angle operation video, the operation audio, and the step frequency data;

[0131] The second module: based on the convolutional neural network deep learning algorithm, gradually extract key features from the multi-angle operation video, and the key features include student posture recognition and action trajectory from low level to high level;

[0132] The third module: extracting audio features from the operation audio, wherein the audio features include tone and audio;

[0133] The fourth module: extracting the cadence feature from the cadence data, wherein the cadence feature includes the cadence average value and the cadence peak value.

[0134] The fifth module: fuses the key features, the audio features, and the step frequency features to output a multimodal feature set;

[0135] Module 6: Compare the training scenario environment data with the preset safety environment and adjust the recognition threshold of dangerous and abnormal behaviors;

[0136] Module 7: Based on the deep learning model, the multimodal feature set is compared with the recognition threshold for similarity;

[0137] Module 8: When the similarity is less than the first preset threshold, the student's operation is considered to be normal behavior;

[0138] Module 9: When the similarity is greater than the first preset threshold but less than the second preset threshold, the student's operation is considered to be abnormal behavior;

[0139] Module 10: When the similarity is greater than the second preset threshold, the student's operation is considered to be a dangerous behavior.

[0140] Optionally, also include:

[0141] Warning signal module: When there is dangerous behavior or abnormal behavior, a multimodal warning signal including visual and auditory is generated based on the student's operation data;

[0142] Push module: When a warning signal is issued, emergency operation instructions and escape routes are pushed to students based on AR display technology.

[0143] For the specific definition of a system for safety warning in vocational education training rooms, please refer to the definition of a method for safety warning in vocational education training rooms mentioned above, which will not be repeated here. Each module in the above-mentioned system for safety warning in vocational education training rooms can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0144] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store multi-angle operation videos, operation audios, and training scene environment data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for safety early warning of a vocational education training room is implemented.

[0145] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for safety early warning in a vocational education training room is implemented.

[0146] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a method for safety early warning in a vocational education training room is implemented.

[0147] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0148] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. A method for safety early warning in vocational education training rooms, characterized in that: Includes steps: During the training process, students’ operation data is collected in real time; Based on AR display technology, the practical training scene is superimposed with virtual information, and guidance information, simulated operation procedures, and question answers are sent to the student end; Based on a preset algorithm, the operation data of the student is analyzed to identify dangerous behaviors and abnormal behaviors; When there is dangerous or abnormal behavior, audio and visual warning signals are issued; The students' operation data and warning records are stored in the preset database, and a feedback report is generated and sent to the smart education platform.

2. According to claim 1, a method for safety early warning of vocational education training rooms is characterized in that: The step of collecting the student's operation data in real time during the training process includes the following steps: Based on three-dimensional spatial positioning technology and preset training scene environment maps, locate the location of dangerous areas; Based on AR display technology, dangerous areas are marked in real time and sent to students.

3. According to claim 1, a method for safety early warning of vocational education training rooms is characterized in that: The step of collecting students' operation data in real time during the training process includes the following steps: Based on the preset algorithm, when it is recognized that the student starts to perform key operations, the student's operation data begins to be collected. The student's operation data includes multi-angle operation videos, operation audio, training scene environment data, and step frequency data, and the operation type is marked; The key operations include high-risk operations, fine operations, standardized operations, and emergency operations.

4. A method for safety early warning in vocational education training rooms according to claim 1, characterized in that: The AR display technology is used to superimpose the training scene with virtual information, and send guidance information, simulated operation procedures, and question answers to the student end, including the steps of Match the students' operation data and the requirements of the preset practical training tasks with the preset database to match the most relevant guidance information and simulated operation process; When receiving questions from students, the system matches the questions with the preset database, finds the answers, and sends the answers to students based on AR display technology.

5. A method for safety early warning in vocational education training rooms according to claim 4, characterized in that: The student's operation data and the requirements of the preset practical training tasks are matched with the preset database to match the most relevant guidance information and simulated operation process steps, including steps Identify students' operation levels based on their operation data; Based on the students' operation level and the requirements of the preset practical training tasks, adjust the presentation of the guidance information and the simulated operation process; Based on AR display technology, the student terminal performs interactive steps on the simulated operation process; The interactive steps include pause, replay, step-by-step learning, and evaluation.

6. A method for safety early warning in vocational education training rooms according to claim 1, characterized in that: The step of analyzing the student's operation data based on a preset algorithm to identify dangerous behaviors and abnormal behaviors includes the following steps: Preprocessing the multi-angle operation video, the operation audio, and the step frequency data; Based on the convolutional neural network deep learning algorithm, key features are gradually extracted from the multi-angle operation video, and the key features include, from low level to high level, the student's posture recognition and movement trajectory; Extracting audio features from the operation audio, the audio features including tone and audio; Extracting a cadence feature from the cadence data, wherein the cadence feature includes an average cadence value and a peak cadence value, The key feature, the audio feature, and the step frequency feature are integrated to output a multimodal feature set; Compare the training scenario environment data with the preset safety environment and adjust the recognition threshold of dangerous and abnormal behaviors; Based on the deep learning model, the multimodal feature set is compared with the recognition threshold for similarity; When the similarity is less than the first preset threshold, the student's operation is considered to be normal behavior; When the similarity is greater than the first preset threshold but less than the second preset threshold, the student's operation is considered to be abnormal behavior; When the similarity is greater than a second preset threshold, the student's operation is considered to be a dangerous behavior.

7. A method for safety early warning in vocational education training rooms according to claim 1, characterized in that: The step of sending out an audiovisual warning signal when there is a dangerous behavior or abnormal behavior comprises the following steps: When there are dangerous or abnormal behaviors, a multimodal warning signal including visual and auditory is generated based on the students' operation data; When a warning signal is issued, emergency operation instructions and escape routes are pushed to students based on AR display technology.

8. A system for safety warning in vocational education training rooms, comprising: Real-time acquisition module: during the training process, real-time acquisition of students' operation data; Sending module: Based on AR display technology, the training scene is superimposed with virtual information, and guidance information, simulated operation procedures, and question answers are sent to the student end; Identification module: Based on a preset algorithm, analyze the student's operation data to identify dangerous and abnormal behaviors; Early warning module: when there is dangerous behavior or abnormal behavior, it will send out audio-visual early warning signals; Storage module: Store students' operation data and warning records in the preset database, generate feedback reports and send them to the smart education platform.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a method for safety early warning in a vocational education training room as described in claims 1-7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of a method for safety early warning in a vocational education training room as described in claims 1-7 are implemented.

Images