Offline fire-fighting training intelligent management method and system based on VR technology

Abstract

The invention discloses an offline fire-fighting training intelligent management method and system based on a VR technology, and the method comprises the following steps: S1, constructing a plurality of fire-fighting scenes through employing a Unity 3D engine; s2, based on an Open XR open source protocol, multiple interaction modes are realized; s3, performing real-time identification and feedback on the operation of the trainee by adopting a deep learning algorithm; s4, the system automatically generates performance data of the trainees in the training process, the system multiplies the performance data by a decision-making weight value and puts the product into a decision tree algorithm, an evaluation result is given, a personalized training report is generated, a manager conducts targeted guidance and evaluation on the trainees according to the evaluation report, and the burden of manual evaluation is reduced; and S5, all training data and evaluation results are uploaded to a cloud database for centralized management and analysis, existing knowledge blind spots are identified through a data mining technology, and training contents and methods are optimized. The system integrates examination, study and evaluation, is high in practicability, and can customize a training scheme for a user.

Description

Technical Field

[0001] The present invention relates to the field of offline fire training, and in particular to an intelligent management method and system for offline fire training based on VR technology. Background Art

[0002] At present, the fire emergency training learning modules of enterprises and hotels are still mainly based on traditional visual explanations and media playback learning, and the examination modules are traditional paper-based fire theory examinations, lacking effective interaction and practical training. This training model has the following significant shortcomings:

[0003] 1. Single teaching method: mainly relying on PPT and video explanations, lacking interactivity and participation.

[0004] 2. Limited opportunities for practical exercises: The frequency of field exercises is low and cannot meet daily learning needs.

[0005] 3. Outdated assessment method: Paper-based interviews are used, which cannot effectively evaluate students’ practical abilities.

[0006] 4. Waste of resources: Traditional training is time-consuming, labor-intensive, expensive and inefficient.

[0007] 5. Increased burden of management evaluation: The evaluation of training effectiveness mainly relies on manual methods, which increases the workload of managers. Summary of the invention

[0008] In order to solve the existing problems, the present invention provides an offline fire training intelligent management method and system based on VR technology. The specific scheme is as follows:

[0009] An intelligent management method for offline fire training based on VR technology, comprising the following steps:

[0010] S1, using Unity3D engine to build multiple firefighting scenes;

[0011] S2, based on the Open XR open source protocol, enables multiple interaction methods;

[0012] S3, uses deep learning algorithms to identify and provide feedback on students’ operations in real time;

[0013] S4, the system automatically generates the trainee's performance data during the training process. The system multiplies the performance data by the decision weight value and puts it into the decision tree algorithm to give the evaluation results and generate a personalized training report. The management personnel provide targeted guidance and evaluation to the trainees based on the evaluation report, reducing the burden of manual evaluation;

[0014] S5, uploads all training data and evaluation results to the cloud database for centralized management and analysis, identifies existing knowledge blind spots through data mining technology, and optimizes training content and methods.

[0015] Preferably, the scenario constructed in step S1 includes a fire scene, a correct use scenario of a fire extinguisher or a fire blanket, and a choice of an escape route.

[0016] Preferably, the multiple interaction modes in step S2 include: correct use of fire extinguishers or fire blankets, escape route selection, and the working principle of fire alarms, so that trainees can operate flexibly in a VR environment, perform firefighting practice operations, and enhance the realism of the training.

[0017] Preferably, in step S3, a convolutional neural network (CNN) is used to process video data, identify the trainees' actions during training, determine whether they comply with standard operating procedures, and provide timely feedback.

[0018] Preferably, the performance data in step S4 includes reaction time, operation accuracy and decision rationality.

[0019] Preferably, the fire simulation training system based on any of the above methods comprises a learning module, an examination module, a data analysis module, a data storage module, and an evaluation feedback module;

[0020] Daily learning users are in the learning module for all fire function learning. During this period, the indicators formed by the trainees, including time, accuracy, experience duration, and number of training projects, are recorded in the data storage module; emergency test needs will be in the test module, and the above-mentioned indicators generated during the test are also recorded in the data storage module; after the test, the data analysis module will retrieve the user indicator data in the data storage module of this user for data analysis, and feed back the results to the evaluation feedback module to provide users with customized training plans with scientific basis.

[0021] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. After the computer program is run, any of the above methods is executed.

[0022] The present invention also discloses a computer system, including a processor and a storage medium, wherein a computer program is stored on the storage medium, and the processor reads and runs the computer program from the storage medium to execute any of the methods described above.

[0023] The beneficial effects of the present invention are:

[0024] 1. The present invention integrates examination, learning and evaluation. Compared with the traditional fire training assessment and evaluation model, it achieves integrated management and reduces the data control pressure of managers.

[0025] 2. The present invention is a practical training with low cost and can be used for daily training. Compared with traditional practical training, which requires the purchase of real firefighting equipment and the hiring of firefighting professionals for demonstration, the method provided by the present invention only requires the cost of software development and virtual reality equipment, and can be used for daily multiple learning, so as to achieve real practical learning of firefighting operations.

[0026] 3. The present invention adopts scientific customized analysis. It uses artificial intelligence algorithms to predict and analyze user behavior, create customized training reports for users, and can customize a set of training plans for users to fill in the gaps. User data can be stored in the cloud for a long time. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 It is a principle block diagram of the fire fighting simulation training system of the present invention;

[0029] Figure 2 A flow chart of an examination or learning mode of a hotel hidden danger troubleshooting system according to an embodiment of the present invention;

[0030] Figure 3 A schematic diagram of a behavior prediction CNN network model of the present invention;

[0031] Figure 4 Schematic diagram of the decision tree algorithm of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] An intelligent management method for offline fire training based on VR technology, comprising the following steps:

[0034] S1, using Unity3D engine to build multiple firefighting scenes; the constructed scenes include fire scene scenes, correct use of fire extinguishers or fire blankets, escape route selection, etc. The scenes contain a variety of interactive elements, such as firefighting equipment and safety instructions, to enhance the students' sense of participation.

[0035] S2, based on the Open XR open source protocol, implements a variety of interactive methods, such as the correct use of fire extinguishers or fire blankets, escape route selection, and the working principle of fire alarms, so that trainees can operate flexibly in a VR environment, conduct firefighting practice operations, and enhance the realism of training.

[0036] S3 uses deep learning algorithms to identify and provide feedback on trainees’ operations in real time. It uses convolutional neural networks (CNNs) to process video data, identify trainees’ actions during training, determine whether they comply with standard operating procedures, and provide timely feedback.

[0037] like Figure 3 The diagram of the CNN network model for behavior prediction is the prediction model in the decision-making algorithm. Its status is the core of the decision-making algorithm and is the actual logic of the prediction result. If the elements in the weight matrix of the above indicators are represented by the letter W, such as the experience time weight W1, the operation score weight W2..., and then through the form of matrix multiplication, W1*experience time weight+W2*operation score+...., a score is finally obtained. According to the comparison between the score and the preset result matrix, the corresponding user performance is given.

[0038] S4, the system automatically generates the trainee's performance data during the training process, including indicators such as reaction time, operation accuracy, and decision rationality. The system multiplies the above performance data by the decision weight value and puts it into the decision tree algorithm to give the evaluation results and generate a personalized training report. Managers provide targeted guidance and evaluation to trainees based on the evaluation report, reducing the burden of manual evaluation.

[0039] S5, uploads all training data and evaluation results to the cloud database for centralized management and analysis, identifies existing knowledge blind spots through data mining technology, and optimizes training content and methods.

[0040] like Figure 1 As shown, a fire simulation training system based on any of the above methods includes a learning module, an examination module, a data analysis module, a data storage module, and an evaluation feedback module.

[0041] Daily learning users are in the learning module for all fire function learning. During this period, the indicators formed by the trainees, including time, accuracy, experience duration, and number of training projects, are recorded in the data storage module; emergency test needs will be in the test module, and the above-mentioned indicators generated during the test are also recorded in the data storage module; after the test, the data analysis module will retrieve the user indicator data in the data storage module of this user for data analysis, and feed back the results to the evaluation feedback module to provide users with customized training plans with scientific basis.

[0042] Implementation example Figure 2 The figure shows the test or learning mode flow chart of the hotel hidden danger inspection system. After selecting the test or learning mode according to user needs, enter the fire emergency capability hidden danger inspection module to conduct combustible inspection and obstruction inspection respectively. Among them, combustible inspection includes high-power electrical appliances, unextinguished cigarette butts, and broken sockets. The inspection of obstructions includes smoke alarms, sprinkler systems, whether the fire soft concept area is blocked, and whether the normally closed fire door is opened.

[0043] When all the above risks are eliminated, the test or study time is over. After that, the user performance data is uploaded to the database for storage, and the user score is analyzed using the decision tree algorithm. Then, the user's risk elimination ability evaluation results are further displayed, including the score conclusion, the scoring details of each area, the system learning suggestions, and the user portrait.

[0044] like Figure 4 As shown, the decision tree algorithm is an evaluation algorithm that uses the classification result given by the preset decision score based on the multi-angle evaluation index matrix and the weight matrix as the final presentation effect. In this invention, when a user completes the fire training task in the system, corresponding relevant data will be generated. These data are integrated together and are called user performance. These user performance elements are used as the input evaluation matrix components, including experience time, user performance data, accuracy, and inspection object score weights. The budgeted weight matrix is ​​used as the indicator weight. The above two matrices are used as input to obtain the user's hidden danger inspection ability evaluation result, which is also represented by a multi-index matrix. The components are score conclusions, scoring details for each place, targeted user portraits, system recommendations, etc.

[0045] The present invention integrates examination, learning and evaluation. Compared with the traditional fire training assessment and evaluation model, it achieves integrated management and reduces the data control pressure of managers. In addition, the present invention is practical training, which is low-cost and can be used for daily training. Compared with traditional practical training, which requires the purchase of real firefighting equipment and the hiring of firefighting professionals for demonstrations, the method provided by the present invention only needs to be spent on software development and virtual reality equipment costs, and multiple daily learning can be carried out to achieve real practical learning of firefighting operations. The present invention adopts scientific customized analysis. Artificial intelligence algorithms are used to predict and analyze user behavior to create user-customized training reports. A set of training plans can be customized for users to check for omissions and fill in the gaps, and user data can be stored in the cloud for a long time for retention.

[0046] The present invention also discloses a computer-readable storage medium and a computer system, wherein a computer program is stored on the computer-readable storage medium, and after the computer program is run, any of the above methods is executed. A computer system includes a processor and a storage medium, wherein the storage medium stores a computer program, and the processor reads and runs the computer program from the storage medium to execute any of the above methods.

[0047] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. The technician may implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present invention.

[0048] The various illustrative logic blocks, modules, and circuits described in conjunction with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in cooperation with a DSP core, or any other such configuration.

[0049] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read and write information from / to the storage medium. In an alternative, a storage medium may be integrated into a processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and the storage medium may reside in a user terminal as discrete components.

[0050] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented as a computer program product in software, each function may be stored on or transmitted by a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, including any medium that facilitates the transfer of a computer program from one place to another. Storage media may be any available medium that can be accessed by a computer. As an example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer. Any connection is also properly referred to as a computer-readable medium. For example, if the software is transmitted from a website, a server, or other remote source using a coaxial cable, a fiber optic cable, a twisted pair, a digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of the medium. Disk and disc as used herein include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, wherein disk often reproduces data magnetically, while disc reproduces data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0051] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein, but should be granted the widest scope consistent with the principles and novel features disclosed herein.

[0052] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent management method for offline fire training based on VR technology, characterized in that: The following steps are involved: S1, using Unity3D engine to build multiple firefighting scenes; S2, based on the Open XR open source protocol, enables multiple interaction methods; S3, uses deep learning algorithms to identify and provide feedback on students’ operations in real time; S4, the system automatically generates the trainee's performance data during the training process. The system multiplies the performance data by the decision weight value and puts it into the decision tree algorithm to give the evaluation results and generate a personalized training report. The management personnel provide targeted guidance and evaluation to the trainees based on the evaluation report, reducing the burden of manual evaluation; S5, uploads all training data and evaluation results to the cloud database for centralized management and analysis, identifies existing knowledge blind spots through data mining technology, and optimizes training content and methods.

2. The method according to claim 1, characterized in that: The scenarios constructed in step S1 include fire scene scenarios, correct use scenarios of fire extinguishers or fire blankets, and selection of escape routes.

3. The method according to claim 1, characterized in that The various interactive modes in step S2 include: the correct use of fire extinguishers or fire blankets, escape route selection, and the working principle of fire alarms, so that trainees can flexibly operate in a VR environment, perform firefighting practice operations, and enhance the realism of the training.

4. The method according to claim 1, characterized in that: In step S3, a convolutional neural network (CNN) is used to process video data, identify the trainees’ actions during training, determine whether they comply with standard operating procedures, and provide timely feedback.

5. The method according to claim 1, characterized in that: The performance data in step S4 includes reaction time, operation accuracy and decision rationality.

6. A firefighting simulation training system based on any of the methods described in claims 1-5, characterized in that: It includes learning module, examination module, data analysis module, data storage module and evaluation feedback module; Daily learning users are in the learning module for all fire function learning. During this period, the indicators formed by the trainees, including time, accuracy, experience duration, and number of training projects, are recorded in the data storage module; emergency test needs will be in the test module, and the above-mentioned indicators generated during the test are also recorded in the data storage module; after the test, the data analysis module will retrieve the user indicator data in the data storage module of this user for data analysis, and feed back the results to the evaluation feedback module to provide users with customized training plans with scientific basis.

7. A computer-readable storage medium, characterized in that: A computer program is stored on the medium, and after the computer program is run, the method according to any one of claims 1 to 5 is executed.

8. A computer system, characterized in that: The method comprises a processor and a storage medium, wherein a computer program is stored in the storage medium, and the processor reads and runs the computer program from the storage medium to execute the method as claimed in any one of claims 1 to 5.

Images