Comprehensive assessment method and system for aviation emergency simulation rescue training

Abstract

The invention relates to the technical field of emergency simulation rescue training, and discloses a comprehensive examination and evaluation method and system for aviation emergency simulation rescue training. The method comprises the following steps: constructing and deploying a theoretical training subsystem to collect theoretical assessment data of trainees; collecting real-time training data of an air rescue training subsystem, an underwater escape training subsystem and an environment simulation subsystem; constructing an evaluation analysis model in a semi-automatic mode based on a guide or a graphical modeling mode based on an operator; analyzing the real-time training data according to the evaluation analysis model to obtain a machine evaluation result; obtaining an operator evaluation result of the real-time training data; and performing weighted average on the machine evaluation result and the operator evaluation result, and obtaining a training examination comprehensive scoring result in combination with theoretical examination data. According to the method, the evaluation analysis model is established for analysis to give a machine evaluation result, a training examination comprehensive scoring result of the trainee is given in combination with an operator evaluation result and theoretical examination data, machine evaluation and professional evaluation are integrated, and quantitative and qualitative analysis and evaluation of aviation emergency simulation rescue training quality and effect are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency simulation rescue training, and in particular to a comprehensive assessment method and system for aviation emergency simulation rescue training. Background Art

[0002] Helicopter air rescue, helicopter ground rescue, water survival, underwater escape and ground first aid training is a very important task that requires a high degree of professional knowledge and skills. In order to improve the training effect and achieve the best rescue effect, it is necessary to collect and analyze the data during the training process. However, there are many main training facilities for aviation emergency rescue training, and the data sources are complex and diverse. At present, there is a lack of comprehensive evaluation and professional evaluation integration solutions for aviation emergency rescue training, making it difficult to achieve quantitative and qualitative analysis and evaluation of the quality and effect of aviation emergency rescue training simulation training. Summary of the invention

[0003] The main purpose of the present invention is to provide a comprehensive assessment and evaluation method and system for aviation emergency simulation rescue training, aiming to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a comprehensive assessment method for aviation emergency simulation rescue training, comprising:

[0005] Constructing a theoretical training subsystem and deploying the theoretical training subsystem to collect theoretical assessment data of training personnel;

[0006] Collect real-time training data of the air rescue training subsystem, underwater escape training subsystem and environmental simulation subsystem;

[0007] Construct evaluation and analysis models using a wizard-based semi-automatic approach or an operator-based graphical modeling approach;

[0008] Analyze the real-time training data according to the evaluation analysis model to obtain a machine evaluation result;

[0009] obtaining operator evaluation results of the real-time training data;

[0010] The machine evaluation result and the operator evaluation result are weighted averaged, and a comprehensive training assessment score result is obtained based on the weighted average result and the theoretical assessment data.

[0011] In some embodiments, the construction of a theoretical training subsystem and the deployment of the theoretical training subsystem to collect theoretical assessment data of trainees include:

[0012] Establish user management module, course management module, learning management module, examination management module and theoretical learning statistical analysis module based on B / S architecture;

[0013] Constructing an initial theoretical training subsystem according to the user management module, course management module, learning management module, examination management module and theoretical learning statistical analysis module;

[0014] The initial theoretical training subsystem is set according to a preset safety technology to obtain a theoretical training subsystem;

[0015] Use Docker to deploy the theoretical training subsystem and manage the containerized deployment environment through Docker Compose;

[0016] The theoretical assessment data of the trainees are collected according to the deployed theoretical training subsystem.

[0017] In some embodiments, the setting of the initial theoretical training subsystem according to the preset safety technology includes:

[0018] Setting up user authentication and authorization for the initial theoretical training subsystem based on JWT technology;

[0019] Encrypting and setting the user password of the initial theoretical training subsystem according to BCrypt technology;

[0020] Performing data transmission security settings on the database of the initial theoretical training subsystem according to MySQL's SSL encryption technology;

[0021] Perform SQL attack check settings on the initial theoretical training subsystem based on the parameterized query technology of MyBatis;

[0022] The initial theoretical training subsystem is set up to filter and escape user input content according to the template syntax of Vue.js.

[0023] In some embodiments, the use of Docker to deploy the theoretical training subsystem and managing the containerized deployment environment through Docker Compose includes:

[0024] MySQL is used as the database of the theoretical training subsystem, and a database container is created and run through Docker;

[0025] Redis is used as the cache database of the theoretical training subsystem, and a Redis container is created and run through Docker;

[0026] Use Elasticsearch as the full-text search engine of the theoretical training subsystem, and create and run the Elasticsearch container through Docker;

[0027] Use Spring Boot framework to develop the backend application of the theoretical training subsystem, and use Docker to build and run the application container;

[0028] Use Vue.js framework to develop the front-end application of the theoretical training subsystem, and build and run the application container through Docker;

[0029] The theoretical training subsystem is log-collected, analyzed, and visualized based on ELK, and Prometheus and Grafana are used to monitor and analyze the performance of the theoretical training subsystem.

[0030] In some embodiments, the collecting of real-time training data of the air rescue training subsystem, the underwater escape training subsystem, and the environmental simulation subsystem includes:

[0031] Build signal acquisition software based on the adapter model;

[0032] The signal acquisition software is used to collect video surveillance data of the air rescue training subsystem, underwater escape training subsystem and environmental simulation subsystem, wearable device data, motion parameters of simulated helicopters and water environment parameters;

[0033] Performing real-time preprocessing on the video surveillance data, wearable device data, motion parameters of the simulated helicopter, and water environment parameters to obtain processed training data; wherein the preprocessing includes filtering, checking, and limiting;

[0034] The processed training data is converted into a unified access data format to obtain real-time training data.

[0035] In some embodiments, the signal acquisition software includes: an ID connection configuration file, a data packet configuration file, and an operating environment file; wherein,

[0036] The ID connection configuration file is used for the signal acquisition software to perform ID connection with the data communication software, and the connection properties are configured through the fmi.conf file;

[0037] The data packet configuration file is used for communication between the signal acquisition software and the underlying hardware communication module, and the connection properties are configured through the fmi_trans_cfg.xml file; the attribute content of the fmi_trans_cfg.xml file includes key parameters and a configuration file framework, the key parameters include the config parameters in protocols, the config parameters in protocol, and the parameters in the field subset; the config parameters in protocols indicate the use of the modbusTCP protocol.

[0038] In some embodiments, the wizard-based semi-automatic method or operator-based graphical modeling method is used to construct the evaluation analysis model, including:

[0039] A plurality of evaluation index items are set based on a graphical modeling environment, wherein the index items include whether a safety accident occurs, task completion time, number of operations, overshoot, number of oscillations, and number of erroneous operations;

[0040] Setting the indicator relationship between the indicator items based on a tree structure;

[0041] The indicator weights of the indicator items are set according to the indicator relationship and importance; wherein the sum of the weights of indicators at the same level is one;

[0042] Set the indicator value calculation criteria according to the calculation formula calculation criteria and the input evaluation calculation criteria;

[0043] Establishing an evaluation index system according to the index items, index relationships, index weights and index value calculation criteria;

[0044] An evaluation and analysis model is constructed according to the evaluation index system using a wizard-based semi-automatic method or an operator-based graphical modeling method.

[0045] In some embodiments, analyzing the real-time training data according to the evaluation analysis model to obtain a machine evaluation result includes:

[0046] Reading the real-time training data;

[0047] Taking the real-time training data as a whole, extracting samples from the real-time training data to obtain sample data, so as to establish a calculation correspondence between the collected real-time training data and the analysis and evaluation indicators;

[0048] Calculate the sample data according to the indicator value calculation criteria in the evaluation indicator system to obtain the indicator value;

[0049] Based on the preset mode, analysis, evaluation and calculation are performed according to the indicator value to obtain a machine evaluation result; wherein the preset mode includes an evaluation mode, an analysis mode and a prediction mode.

[0050] In some embodiments, the analyzing, evaluating and calculating according to the indicator value based on a preset mode includes:

[0051] When the preset mode is the evaluation mode, the index values ​​are respectively calculated according to the simulation data and the empirical data in accordance with the preset evaluation algorithm;

[0052] When the preset mode is the analysis mode, an influencing factor analysis is performed on the key factors that affect the change of the indicator value;

[0053] When the preset mode is the prediction mode, a quantitative mathematical model between the sample data fitting factors and the index values ​​is constructed, and the preset exploration factor space is explored and analyzed through the mathematical model.

[0054] In addition, to achieve the above purpose, the present invention also proposes a comprehensive assessment and evaluation system for aviation emergency simulation rescue training, comprising:

[0055] Theoretical assessment module, used to construct a theoretical training subsystem and deploy the theoretical training subsystem to collect theoretical assessment data of trainees;

[0056] Data parameter acquisition module, used to collect real-time training data of the air rescue training subsystem, underwater escape training subsystem and environmental simulation subsystem;

[0057] An evaluation and analysis model building module is used to build an evaluation and analysis model in a semi-automatic way based on a wizard or in a graphical modeling way based on an operator;

[0058] A first evaluation module, used to analyze the real-time training data according to the evaluation analysis model to obtain a machine evaluation result;

[0059] A second evaluation module, used to obtain an operator evaluation result of the real-time training data;

[0060] The comprehensive evaluation module is used to perform weighted averaging on the machine evaluation results and the operator evaluation results, and obtain a comprehensive scoring result of the training assessment based on the weighted average result and the theoretical assessment data.

[0061] The present invention provides a comprehensive assessment and evaluation method for aviation emergency simulation rescue training, including: constructing a theoretical training subsystem, and deploying the theoretical training subsystem to collect theoretical assessment data of trainees; collecting real-time training data of air rescue training subsystem, underwater escape training subsystem and environmental simulation subsystem; constructing an evaluation and analysis model based on a wizard-based semi-automatic method or an operator-based graphical modeling method; analyzing the real-time training data according to the evaluation and analysis model to obtain a machine evaluation result; obtaining an operator evaluation result of the real-time training data; weighted averaging the machine evaluation result and the operator evaluation result, and obtaining a comprehensive scoring result of training assessment according to the weighted average result and the theoretical assessment data. In the present invention, theoretical training and practical training are combined, and the collected theoretical assessment data and real-time training data are analyzed by building an evaluation and analysis model to give a machine evaluation result, and the comprehensive scoring result of the training assessment of the trainees is given in combination with the operator evaluation result, so as to realize the integration of machine evaluation and professional evaluation, thereby realizing quantitative and qualitative analysis and evaluation of the quality and effect of aviation emergency simulation rescue training, which is conducive to scientifically carrying out training evaluation, effectively improving training effect, and providing more efficient training management for aviation emergency rescue training. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a flow chart of an embodiment of a comprehensive assessment and evaluation method for aviation emergency simulation rescue training according to the present invention;

[0063] Figure 2 This is a schematic diagram of the signal acquisition software involved in the embodiment of the present invention;

[0064] Figure 3 A schematic diagram of the signal acquisition software structure involved in the embodiment of the present invention;

[0065] Figure 4 This is a schematic diagram of ID configuration attributes involved in the embodiment of the present invention;

[0066] Figure 5 A schematic diagram of connection attribute configuration involved in an embodiment of the present invention;

[0067] Figure 6 A schematic diagram of the logic flow of the assessment and evaluation involved in the embodiment of the present invention;

[0068] Figure 7 This is a flow chart of the assessment and evaluation involved in the embodiment of the present invention;

[0069] Figure 8 A schematic diagram of an analysis and evaluation index system involved in an embodiment of the present invention;

[0070] Fig. 9A schematic diagram of a data preprocessing process in an analysis and evaluation process involved in an embodiment of the present invention;

[0071] Fig.10 A schematic diagram illustrating an analysis and evaluation mode involved in an embodiment of the present invention;

[0072] Fig.11 It is a structural block diagram of an embodiment of a comprehensive assessment and evaluation system for aviation emergency simulation rescue training according to the present invention;

[0073] Fig.12 The present invention is a schematic diagram of the structure of an electronic device in a hardware operating environment according to an embodiment of the present invention.

[0074] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0075] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0076] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0077] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0078] The present invention provides a comprehensive assessment method and system for aviation emergency simulation rescue training.

[0079] The embodiment of the present invention provides a comprehensive assessment method for aviation emergency simulation rescue training, referring to Figure 1 , Figure 1 The present invention is a flowchart of an embodiment of a comprehensive assessment and evaluation method for aviation emergency simulation rescue training.

[0080] like Figure 1 As shown, the comprehensive assessment and evaluation method for aviation emergency simulation rescue training includes:

[0081] Step S100: construct a theoretical training subsystem and deploy the theoretical training subsystem to collect theoretical assessment data of trainees;

[0082] Step S200: collecting real-time training data of the air rescue training subsystem, the underwater escape training subsystem and the environmental simulation subsystem;

[0083] Step S300: constructing an evaluation analysis model in a semi-automatic manner based on a wizard or in a graphical modeling manner based on an operator;

[0084] Step S400: Analyze the real-time training data according to the evaluation analysis model to obtain a machine evaluation result;

[0085] Step S500: obtaining the operator evaluation result of the real-time training data;

[0086] Step S600: performing weighted averaging on the machine evaluation result and the operator evaluation result, and obtaining a comprehensive training assessment score result according to the weighted average result and the theoretical assessment data.

[0087] It should be noted that the execution subject in this embodiment may be an electronic device, which may be a computer device with data processing functions, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, a computer device is used as an example for explanation.

[0088] It is understandable that this embodiment is explained by taking the professional training subsystem of aviation emergency rescue training including eight subsystems as an example. The multi-professional training subsystem mainly undertakes the emergency rescue training functions of each profession, and at the same time, the interconnection of various professional systems can be realized through the training integration platform to realize multi-professional joint training. The professional training subsystem includes a helicopter air rescue training subsystem, a helicopter ground simulation training subsystem, an underwater escape training subsystem, a water survival training subsystem, a ground first aid training subsystem, an aviation emergency rescue VR training subsystem, a theoretical training subsystem, and a training equipment subsystem.

[0089] In one embodiment, a theoretical training subsystem is constructed and deployed to collect theoretical assessment data of trainees, including: establishing a user management module, a course management module, a learning management module, an examination management module and a theoretical learning statistical analysis module based on a B / S architecture; constructing an initial theoretical training subsystem according to the user management module, the course management module, the learning management module, the examination management module and the theoretical learning statistical analysis module; setting the initial theoretical training subsystem according to a preset security technology to obtain a theoretical training subsystem; deploying the theoretical training subsystem using Docker, and managing the containerized deployment environment through Docker Compose; and collecting theoretical assessment data of trainees according to the deployed theoretical training subsystem.

[0090] It should be noted that the theoretical training subsystem is a comprehensive management and teaching platform for aviation emergency rescue training. It integrates aviation emergency professional technical materials with multimedia technology and computer technology, and has functions such as course management, courseware management, and student assessment, to achieve interactive teaching and autonomous theoretical learning, improve students' learning interest and participation, and provide more efficient training management for aviation emergency rescue theory training. The courseware of the theoretical training subsystem complies with the international SCORM standard, and the course content covers helicopter safety, basic knowledge, aviation physiology, emergency response, patient boarding and disembarking, medical transfer procedures, etc. The courseware uses a combination of pictures, text, and videos to achieve teaching purposes.

[0091] Specifically, the theoretical training subsystem adopts a B / S architecture mode, i.e., a browser-based client / server architecture, and a configurable loading course content package, the specific contents of which include but are not limited to basic aviation rescue technology, intermediate aviation rescue technology, and advanced aviation rescue technology. In this embodiment, the theoretical training subsystem adopts a B / S architecture mode with the following advantages: no client needs to be installed, and users can use the system by simply accessing it through a browser, which reduces user usage costs; the client does not require maintenance, which reduces system management costs; the theoretical training subsystem can be used across platforms and devices, which improves the applicability of the system; and the maintenance and upgrade of the subsystem are more convenient.

[0092] Exemplarily, the theoretical training subsystem includes functional modules such as user management, course management, learning management, examination management and statistical analysis. The user management module is used to implement functions such as user registration, login, password modification, and personal information modification to ensure the security of user identity and the privacy of personal information. The course management module is used to implement functions such as adding, deleting, modifying, and checking courses, course classification management, course search, and recommendation to ensure the integrity and diversity of course content. The learning management module is used to implement functions such as the preservation of user learning records, the recording of learning progress, and the viewing of learning history records, which is convenient for flexible use. The examination management module is used to implement functions such as the generation of examination papers, the preservation of examination records, and the statistics of examination results to provide users with feedback on examination opportunities and examination results. The statistical analysis module is used to implement functions such as statistical analysis of user learning records and examination results, and statistical analysis of course learning progress, so that administrators can conduct a comprehensive analysis and understanding of the students' learning situation.

[0093] In one embodiment, the initial theoretical training subsystem is set up according to the preset security technology, including: setting user authentication and authorization of the initial theoretical training subsystem according to JWT technology; encrypting the user password of the initial theoretical training subsystem according to BCrypt technology; setting data transmission security of the database of the initial theoretical training subsystem according to MySQL's SSL encryption technology; setting SQL attack check for the initial theoretical training subsystem according to MyBatis's parameterized query technology; and filtering and escaping user input content according to the template syntax of Vue.js.

[0094] In this embodiment, Vue.js, Spring Boot, MySQL, Redis, Elasticsearch and other technologies are used, and tools such as Docker, Kubernetes, Jenkins, ELK, Prometheus and Grafana are used for deployment and monitoring, so as to achieve efficient, safe and reliable emergency rescue training management. Among them, JWT technology is used to implement user authentication and authorization to ensure the security of user identity. BCrypt technology is used to encrypt user passwords to ensure the security of user passwords. The SSL encryption function of MySQL technology is used to ensure the data transmission security of the database. The parameterized query function of MyBatis technology is used to prevent SQL injection attacks. The template syntax of Vue.js technology is used to filter and escape the content entered by the user to prevent cross-site scripting attacks.

[0095] In one embodiment, the theoretical training subsystem is deployed using Docker, and the containerized deployment environment is managed through Docker Compose, including: using MySQL as the database of the theoretical training subsystem, creating and running a database container through Docker; using Redis as the cache database of the theoretical training subsystem, creating and running a Redis container through Docker; using Elasticsearch as the full-text search engine of the theoretical training subsystem, creating and running an Elasticsearch container through Docker; using the Spring Boot framework to develop the back-end application of the theoretical training subsystem, and building and running an application container through Docker; using the Vue.js framework to develop the front-end application of the theoretical training subsystem, and building and running an application container through Docker; collecting, analyzing and visualizing logs of the theoretical training subsystem based on ELK, and using Prometheus and Grafana to monitor and analyze the performance of the theoretical training subsystem.

[0096] Specifically, the theoretical training subsystem is deployed using Docker, and Docker Compose is used to manage the containerized deployment environment. It mainly includes the following components: Database: Use MySQL as the database, and use Docker to create and run the database container. Redis: Use Redis as the cache database, and use Docker to create and run the Redis container. Elasticsearch: Use Elasticsearch as the full-text search engine, and use Docker to create and run the Elasticsearch container. Back-end application: Use the Spring Boot framework to develop back-end applications, and use Docker to build and run application containers. Front-end application: Use the Vue.js framework to develop front-end applications, and use Docker to build and run application containers. Monitoring and logging: Use ELK (Elasticsearch, Logstash, and Kibana) to collect, analyze, and visualize logs, and use Prometheus and Grafana to monitor and perform performance analysis on the theoretical training subsystem.

[0097] It can be understood that the database design of this embodiment includes: user table: storing basic information of users, including user name, password, email, telephone number, role and other fields; course schedule: storing basic information of courses, including course name, course description, course cover and other fields; chapter table: storing chapter information of courses, including chapter name, chapter description, chapter video and other fields, and having a one-to-many relationship with the course schedule; learning record table: storing learning record information of users, including user ID, course ID, chapter ID, learning time and other fields; examination paper table: storing examination paper information, including examination paper name, examination time, number of questions, examination time limit and other fields; examination record table: storing examination record information of users, including user ID, examination paper ID, examination score, examination time and other fields; administrator table: storing basic information of administrators, including administrator username, password, email and other fields.

[0098] In one embodiment, real-time training data of an air rescue training subsystem, an underwater escape training subsystem, and an environmental simulation subsystem are collected, including: constructing a signal acquisition software based on an adapter mode; collecting video surveillance data, wearable device data, motion parameters of simulated helicopters, and water environment parameters of the air rescue training subsystem, the underwater escape training subsystem, and the environmental simulation subsystem through the signal acquisition software; performing real-time preprocessing on the video surveillance data, wearable device data, motion parameters of simulated helicopters, and water environment parameters to obtain processed training data; wherein the preprocessing includes filtering, checking, and limiting; converting the processed training data into a unified access data format to obtain real-time training data.

[0099] In this embodiment, Figure 2 As shown in the schematic diagram of the signal acquisition software, the signal acquisition software establishes a unified abstraction of the simulator hardware through the adapter mode, realizes the decoupling of physical devices and logical models, and improves the reliability and expansion performance of the system. The signal acquisition software has the following functions: Signal acquisition: collects hardware operation instructions from each hardware console and performs real-time preprocessing, including filtering, verification, limiting, etc.; Signal control: receives host computer instructions and converts host computer instructions into hardware control signals to drive corresponding equipment, including six-degree-of-freedom motion platforms, instruments, and indicator lights; Signal management: has the local management function of collecting and transmitting signals, and can index, disable, and debug output signals; Signal inspection: checks the difference between local signals and remote signals (simulation required signals), and gives detailed explanations of the differences to guide users to perform hardware consistency checks.

[0100] Specifically, real-time training data is obtained based on the device parameter acquisition and conversion system in the signal acquisition software. The device parameter acquisition and conversion system collects real-time parameters and data of the operation of various equipment in the three major systems of air rescue training system, underwater escape training system, and environmental simulation system. It includes three modules, of which the air rescue training system, underwater escape training system, and environmental simulation system each correspond to an acquisition module. The device parameter acquisition and conversion system is aimed at various types of software and hardware equipment, providing functions such as signal acquisition and conversion, and can uniformly access and manage heterogeneous equipment. For the console, it is mainly used to collect signals from console hardware devices (lights, buttons, rudders, buzzers, etc.), and establish a real-time connection with the data communication software. The real-time acquisition frequency is not less than 20Hz, and the control delay is less than 50ms.

[0101] Specifically, the collected data includes three types: video monitoring data: trainees' movements, handling behaviors, etc.; wearable device data: trainees' physiological data, heart rate, pulse, etc.; data of other equipment and facilities: simulated helicopter motion parameters, water environment parameters, etc. Based on the video acquisition and analysis system, the trainees' training process is recorded and stored to obtain video monitoring data. The video acquisition and analysis system includes but is not limited to fixed and pan-tilt cameras (audio and video synchronization) and video recorders (storage time is not less than half a year). Based on the wearable data acquisition system, various physiological characteristics of the human body are collected for real-time pulse and blood pressure monitoring to obtain wearable device data. The wearable data acquisition system includes but is not limited to physiological monitoring watches or bracelets and physiological data centralized monitoring software, providing each trainee with accurate physiological data analysis (pulse, body temperature, blood pressure), collecting real-time vital signs data through an intelligent gateway, and using PCs and web browsers to view the changes in the vital signs signals of all trainees as a whole. At the same time, the early warning system is used to detect dangers in a timely manner and provide help.

[0102] In one example, a physiological monitoring watch or bracelet in a wearable data acquisition system integrates a 6-axis MEMS sensor, supports multiple sports monitoring, and adopts a dual-mode ultra-low power architecture combining Bluetooth and CAT1. Exemplarily, the wearable data acquisition system includes a power supply circuit, a microprocessor, a Bluetooth module, and a CAT1 communication module. The Bluetooth module and the CAT1 communication module are respectively connected to the microprocessor, wherein the Bluetooth module adopts AOA combined with iBeacon fusion positioning technology to facilitate the collection of life characteristic signals of trainees, and has the advantages of high accuracy, large range, low power consumption, and low maintenance cost. The device equipped with the Bluetooth module uses the BLE function to send its own unique ID to the surrounding area, and the software that receives the ID, that is, the physiological data centralized monitoring software, will operate according to the ID. The power supply circuit provides power for the entire acquisition device. The input power supply passes through a diode to prevent the power supply from being reversed and two filter capacitors, and then the power supply voltage is input through the power chip. The power supply is stabilized by a voltage regulator. The power supply after the voltage regulator is connected to a voltage regulator, and the power supply is obtained by stepping down the voltage. Here, the voltage regulator can adopt a high-precision, low-power forward voltage regulator to ensure the excellent performance of the power supply circuit and the normal operation of the Bluetooth module, thereby reducing the power consumption and failure of the entire Bluetooth module.

[0103] It should be noted that, in actual applications, the process of collecting real-time training data of the air rescue training subsystem, underwater escape training subsystem and environmental simulation subsystem may include the following steps: Step 1, creating a system model file: abstracting the equipment used in the air rescue training subsystem, underwater escape training subsystem and environmental simulation subsystem into models, and several models constitute the entire data interaction system. The system model file is the basis for data interaction. The model file defines the identification, version, description and parameters of each model; Step 2, requesting a local model file: before initiating a data exchange request, the initiator of data exchange first obtains its own model file; Step 3, updating the local model data structure: after obtaining its own model file, the initiator parses the corresponding model file and initializes the local model management structure, including parameter cache, update queue, event trigger, etc. transmitter and bridge; Step 4, initiate data update: the data exchange initiator obtains the model parameters of the corresponding device based on the index of the pre-updated model parameters, puts them into the parameter cache, and puts them into the update queue after adding the corresponding parameter index; Step 5, refresh the update queue: the data exchange initiator reorganizes and encodes the data in the update queue, and sends it through the network after the encoding is completed; Step 6, receive data update: the data exchange processor receives the data of the data exchange initiator, decodes it, generates parameter data, and puts the corresponding parameter data into the system global parameter cache; Step 7, forward data update: the data exchange processor repackages and encodes the updated data according to the parameters declared for each model in the system model file, and finally sends it to the receiver; Step 8, receive data: the receiver receives the data forwarded by the processor, updates the local cache, and completes the data exchange process.

[0104] It can be understood that during the above-mentioned data collection and processing process, data interaction is achieved between the devices in the air rescue training subsystem, the underwater escape training subsystem and the environmental simulation subsystem based on the data bus; the model configuration information corresponding to all devices is concentrated on the Server side, and each device is distributed on different Client sides as the initiator or receiver of data exchange.

[0105] Specifically, in the second step, when the Client corresponding to the initiator is started, it pulls the corresponding local model file from the Server, thereby obtaining its own model file. The specific implementation process includes: Step 2.1, the Client reads the corresponding device attributes, generates a model identifier based on the attributes, and generates a model request data packet containing the model identifier, wherein the model request data packet includes a packet header and a data area, and the packet header includes a domain identifier, a packet length, a sender identifier, a packet type, a timestamp, and a reserved word. For the model request data packet, the sender identifier is the generated model identifier; Step 2.2, after the Server receives the model request data packet from the Client, it checks the correctness and integrity of the data, reads the system model file loaded into the memory, selects the model file with the same model identifier as the model request data packet from the model file, and the model file The file includes an XML paragraph, which is placed in the data area of ​​the model request data packet. After modifying the relevant identification information, the timestamp of the Server side is loaded in the model request data packet, and the corresponding data packet is returned to the corresponding Client side; step 2.3, after the Client side receives the data packet returned by the Server side, it checks whether the model identifier in the data packet matches the local model identifier. If they match, execute step 2.4; otherwise, return to step 2.1; step 2.4, the Client side calculates the time drift between the Client side and the Server side based on the timestamp data of the Server side. According to the time accuracy requirements of the experiment, if the drift is exceeded, the system clock of the Client side is adjusted; wherein, the model file includes XML fragments, and the XML fragments include XML fragments that record model attribute information and XML fragments that record model parameter information.

[0106] It should be noted that in order to solve the data synchronization waiting caused by network transmission, the update data is saved in the form of a pre-allocated data structure. The external interface only needs to read or write data from the system memory, and automatically update and maintain the data in the memory. Among them, the message types include Bool, Int, Real and Buf types. The server end, as the data exchange processor, continuously listens for data on a fixed network port. The server end manages all parameters in the form of a two-dimensional linked list. The data management is centered on the parameters. The global index of the parameters is organized into a first-dimensional linked list. The unique parameter can be accessed through the index. At the same time, the speed of index access is improved by hashing the index. The global index of each parameter links the same parameter of multiple models (the equipment used in the air rescue training subsystem, the underwater escape training subsystem and the environmental simulation subsystem is abstracted into models), so that the same parameter of different models has independent data cache space, thereby reducing the waiting overhead of data synchronization and improving data forwarding efficiency. Due to the difference in the number of parameters used by the model, the number of models linked to different parameters is different.

[0107] In one embodiment, the signal acquisition software includes: an ID connection configuration file, a data packet configuration file, and an operating environment file; wherein the ID connection configuration file is used for the signal acquisition software to establish an ID connection with the data communication software, and the connection properties are configured through the fmi.conf file; the data packet configuration file is used for the signal acquisition software to establish a communication connection with the underlying hardware communication module, and the connection properties are configured through the fmi_trans_cfg.xml file; the attribute content of the fmi_trans_cfg.xml file includes key parameters and a configuration file framework, the key parameters include the config parameters in protocols, the config parameters in protocols, and the parameters in the field subset; the config parameters in protocols indicate the use of the modbusTCP protocol.

[0108] Specifically, the signal acquisition software is client software, programmed in C++ and JavaScript, and developed in VS environment. The structure of the signal acquisition software is as follows: Figure 3 As shown, it mainly includes ID connection configuration file, data packet configuration file, and operating environment file. It mainly matches the data packet in data communication through the configuration file, so it has good portability.

[0109] For example, the ID connection configuration file is mainly used for the signal acquisition software and the data communication software to perform ID connection, and the connection properties are configured by a file named "fmi.conf" (the property content is as follows: Figure 4 As shown in the figure); Data packet configuration is mainly used for communication between the signal acquisition software and the underlying hardware communication module. The connection properties are configured by a file named "fmi_trans_cfg.xml" (the property content is as shown in the figure). Figure 5 ). Figure 5 In this configuration file, the config parameter in protocols, the config parameter in protocol, and all the parameters in the field subset are key parameters, and the others are the configuration file framework. The meaning of config="modbus,10.60.3.1,500" in protocols is that the modbusTCP protocol is adopted, the IP address of the hardware communication module device is 10.60.3.1, and the communication port number is "500". The meaning of config=""AI,1,0,8"" in protocol is that the data type of this data packet is analog input, which automatically corresponds to the analog input memory address in the standard modbusTCP communication. "1" is the function code, "0" is the starting address, and "8" is the data length.

[0110] For example, regarding Figure 5Shown as "<field id="30110000"name="ai1">

[0111] <addr offset="0"bitpos="0"byteorder="0" / >

[0112] <value type="ushort"min="0"max="100"k="1"b="0" / >

[0113] "Among them, id="30110000" in the field subset corresponds to the index in the data communication software; offset="0", marking the starting address; byteorder="0", byte starting position; type="ushort", data type; min="0", minimum value; max="100", maximum value; k="1", proportional coefficient; b="0", offset.

[0114] It should be noted that the assessment and evaluation system can be used for data analysis. The assessment and evaluation system collects trainee training assessment process data, i.e. real-time training data, through the video acquisition and analysis system, wearable data acquisition system, and equipment parameter acquisition and conversion system, and gives a comprehensive assessment of the trainee assessment by comparing the system assessment preset library. The assessment and evaluation data is stored to retain valid data information for subsequent performance record inquiries.

[0115] Specifically, Figure 6 The assessment logic shown in the figure is that the assessment module performs automatic scoring and subjective scoring respectively through data recording and operation playback, and finally obtains a comprehensive assessment score. Comprehensive evaluation is performed through auxiliary replay evaluation, real-time data recording, handling time, and handling action standardization to achieve automatic machine scoring (machine evaluation results); the control desk trainer observes the handling and operation details of trainees in various positions in real time to perform subjective scoring (operator evaluation results). The machine score and the control desk operator score are weighted and added to obtain the comprehensive training assessment score.

[0116] In this embodiment, the assessment process is as follows: Figure 7 As shown, the assessment process is carried out through indicator construction tools, data preprocessing tools and evaluation analysis tools.

[0117] Specifically, the indicator construction tool is used to assist users in constructing and managing the evaluation indicator system. The sub-modules and functions included are as follows: Evaluation indicator system modeling: providing users with a graphical modeling environment to assist them in conveniently constructing the indicator system. Users can set the attributes of the indicators and save the indicator system; Evaluation indicator system management: realizing the classification management of the evaluation indicator system, and providing an external interface for reading the evaluation indicator system; Indicator system library: used to store the evaluation indicator system.

[0118] Specifically, the data preprocessing tool is used to assist users in performing mathematical operations and format management on raw data so that the processed data can meet the data requirements of the evaluation. The sub-modules and functions included are as follows: Raw data reading: It is compatible with a variety of raw data file formats and reads raw data (training and assessment process data such as real-time training data); Data sample extraction: Extract data samples from raw data to obtain valuable data, and plan the data samples. Preprocessing formula editing: It allows users to edit data preprocessing formulas in a visual form in the form of a formula editor, and provides the function of saving formulas. Preprocessing results: Call the preprocessing function to perform preprocessing formula operations, obtain preprocessing results, and provide the function of saving preprocessing results.

[0119] Specifically, the evaluation and analysis tool mainly completes the evaluation and analysis model modeling, operation, result generation and other auxiliary functions. The sub-modules and functions included are as follows: Evaluation and analysis model modeling: provides two evaluation model modeling capabilities: a wizard-based semi-automatic method or an operator-based graphical manual modeling method; Evaluation and analysis model running engine: schedules the operation of the evaluation and analysis model, completes the model function, and finally obtains the evaluation and analysis results, and stores the results in the evaluation and analysis result library; Evaluation and analysis report generation: automatically generates an evaluation and analysis report based on the relevant information of the evaluation and the needs of the user; Operator library: used to store and manage operator plug-ins.

[0120] In one embodiment, an evaluation and analysis model is constructed in a semi-automatic manner based on a wizard or in a graphical modeling manner based on an operator, including: setting multiple evaluation index items based on a graphical modeling environment, the index items including whether a safety accident occurs, task completion time, number of operations, overshoot, number of oscillations, and number of misoperations; setting index relationships between the index items based on a tree structure; setting index weights of the index items according to the index relationships and importance; wherein the sum of weights of indicators at the same level is one; setting index value calculation criteria according to calculation formula calculation criteria and input evaluation calculation criteria; establishing an evaluation index system according to the index items, index relationships, index weights, and index value calculation criteria; and constructing an evaluation and analysis model according to the evaluation index system in a semi-automatic manner based on a wizard or in a graphical modeling manner based on an operator.

[0121] Specifically, the establishment of the index system: the evaluation index system is modeled based on a graphical modeling environment. The analytical evaluation index is a concept and value that describes the quantitative characteristics of the objective overall phenomenon and reflects the measurement standard of the evaluation object. The conceptual part is called the index name and the numerical part is called the index value. The construction of the evaluation index system includes: the indicators for measuring the evaluation object, the hierarchical relationship of these indicators, the preference of the decision maker for each indicator, the value measurement standard of each indicator by the decision maker, etc. Figure 8 As shown, the established analysis and evaluation index system includes index items, relationships between indicators, index weights, index value calculation criteria, etc.

[0122] Specifically, the index item is the name of the index and the individual attribute information. The index name is the name of the factor that reflects the objective phenomenon. It is obtained after analyzing the objective business and can be calculated through business data, test data, or formulated by experts. The individual attributes of the index are the attribute characteristics of the index itself, such as quantitative calculation, qualitative calculation and other attributes. These attributes determine the role of the index in the analysis and evaluation calculation process, and will directly affect the correctness of the analysis and evaluation results. In this embodiment, the function of establishing a new index is provided for the user, and the user can conveniently input various attributes of the index item. The index items include but are not limited to whether a safety accident occurs, the task completion time, the number of operations, the overshoot, the number of oscillations, and the number of misoperations.

[0123] Specifically, the relationship between indicators includes the constraint relationship of the same level and the hierarchical relationship of the hierarchy, which are described by a tree structure. The constraint relationship of the same level is the relationship between indicators at the same level, and the indicators are calculated and processed accordingly according to this constraint relationship of the same level. The hierarchical relationship of the hierarchy is the relationship between indicators at different levels. The calculation and definition of an indicator may be determined by the combination of some sub-indicators, so there is a parent-child relationship of indicators, and there can be multi-level parent-child relationships. When designing, it is necessary to provide users with an intuitive, easy-to-use, and clear indicator relationship display interface.

[0124] Specifically, the indicator weight describes the importance of the indicator among the indicators of the same level, and reflects the influence of the previous indicator value. Each indicator has a different degree of importance when calculating the value of the upper-level indicator, and the focus should be differentiated between indicators. This different importance is expressed by the indicator weight in the indicator system. The weights of the indicators of the same level add up to 1, and the size of the weight describes the importance of the indicator.

[0125] Specifically, the indicator value calculation criteria are used to define how to calculate the indicator value of the indicator. Define the calculation criteria, through which the data in the database can be used to calculate the data results of the indicator value. Due to the differences and limitations in the calculation methods of different indicators, the calculation criteria can be roughly divided into two categories: one is the calculation criteria with calculation formulas, which must strictly follow the defined calculation formulas for calculation; the other is the calculation criteria for expert evaluation, which only has a description of the evaluation criteria, and the final result of the indicator value is obtained through expert evaluation input.

[0126] Specifically, the evaluation and analysis model can be constructed by manual modeling, semi-automatic modeling or graphical modeling based on operators. Exemplarily, the motivation of the design evaluation and analysis model is used to conduct demand analysis and formal representation of the evaluation index system, and support the input of multiple data sources (including but not limited to relational data sources, Hbase and other data sources). These data reflect the multi-faceted characteristics of indicator items, the relationship between indicators, the weight of indicators, and the calculation criteria of indicator values, ensuring a unified data format and consistent constraint relationships; using a data wizard, extracting and configuring data of different data source types, and integrating the data of multiple indicator items, the relationship between indicators, the weight of indicators, and the calculation criteria of indicator values ​​to construct an evaluation and analysis model.

[0127] In one embodiment, the real-time training data is analyzed according to the evaluation and analysis model to obtain a machine evaluation result, including: reading the real-time training data; taking the real-time training data as a whole, extracting samples from the real-time training data to obtain sample data, so as to establish a calculation correspondence between the collected real-time training data and the analysis and evaluation indicators; calculating the sample data according to the indicator value calculation criteria in the evaluation indicator system to obtain the indicator value; performing analysis and evaluation calculation according to the indicator value based on a preset mode to obtain a machine evaluation result; wherein the preset mode includes an evaluation mode, an analysis mode and a prediction mode.

[0128] It should be noted that data preprocessing: organize and calculate the real-time training data, and establish a calculation correspondence between the original collected real-time training data and the analysis and evaluation indicators. The original collected real-time training data may be disorganized or may be data in a standard database, but no matter how the data is obtained, it cannot be guaranteed that it can completely correspond to the indicators in the indicator system. The indicator system for analysis and evaluation is flexible, and different analysis and evaluation methods will produce different analysis and evaluation indicator systems. The indicator systems established by different analysis and evaluation personnel may also be different. Based on a fixed pattern to correspond to a flexible and changeable pattern, a corresponding relationship needs to be established in the middle. In this embodiment, data preprocessing is used to establish a corresponding relationship.

[0129] Specifically, Fig. 9 As shown in the figure, data preprocessing mainly includes two tasks: extracting samples from data and calculating the index values ​​in the index system. Extract samples from the original data (real-time training data), that is, take the original data as the population and extract a sample as the representative of the population, which is the data basis for analysis and evaluation. Remove expired and large-error data from the original data to avoid adverse effects on analysis and evaluation. The amount of original data is also huge, and there is no need to calculate each data. Extract representative data from these data, which can fully reflect the overall characteristics and provide an objective reference for analysis and evaluation. When extracting data samples, you can extract from data items and data values ​​separately. Some data items are meaningless to analysis and evaluation, so these data items can be filtered out. There will also be large-error or expired data values ​​in valuable data items, which also need to be filtered. In addition, providing the function of batch processing of data can enable users to complete data sample extraction faster.

[0130] It is understandable that, during the sample extraction process, the present embodiment can also divide the collected data samples into different schemes for processing. The data samples can be divided into multiple scheme samples, but the same indicator system needs to be used for analysis, evaluation and calculation of different schemes. The purpose of data extraction from different schemes is mainly to be able to compare the results horizontally and explain the problem more clearly. Multiple sets of scheme data can also support more factor analysis and prediction calculations, and the obtained analysis and evaluation results are more accurate and comprehensive.

[0131] Specifically, the indicator value calculation criteria in the evaluation indicator system are to use the indicator value calculation method in the indicator attribute: the indicator value in the indicator system is calculated based on the sample data. At this stage, the sample data needs to be calculated according to the indicator value calculation method in the indicator system. The calculation method can be pre-set during the establishment of the evaluation indicator system. In actual use, it is still necessary to analyze the characteristics of the sample data, find the relationship between the sample data and the indicator value of the indicator system, and selectively calculate the indicator value.

[0132] In one embodiment, analysis, evaluation and calculation are performed based on the indicator value based on a preset mode, including: when the preset mode is an evaluation mode, respectively solving the indicator value according to the simulation data and the empirical data according to a preset evaluation algorithm; when the preset mode is an analysis mode, performing an influencing factor analysis on the key factors that affect the change of the indicator value; when the preset mode is a prediction mode, fitting a quantitative mathematical model between the sample data and the indicator value, and exploring and analyzing the preset exploration factor space through the mathematical model.

[0133] It should be noted that the analysis, evaluation and calculation are not just a simple solution of the evaluation index to obtain the evaluation index value of each solution. In order to analyze the influencing factors behind the problem, it is usually necessary to analyze the factors that have a greater impact on the evaluation index to assist in the optimization of the solution. Moreover, there is usually uncertainty in the problems studied by the analysis and evaluation. Although the simulation explores the uncertainty space to a certain extent, these explorations are carried out at limited points. Solving the index value in a larger uncertainty area requires an increase in the number of simulations, which will be unaffordable in terms of time and money. On the other hand, even if the cost of conducting simulation experiments at enough points can be borne, the result data obtained at these discrete points cannot form an in-depth understanding of the problem. For example, when a certain factor changes, what is the trend of the indicator change, or when a certain lower-level indicator value changes, what is the trend of the upper-level indicator value change. In response to the above problems, the analysis and evaluation environment of the computer device in this embodiment supports three preset modes of compatible evaluation / analysis / prediction, such as Fig.10 shown.

[0134] Specifically, the evaluation mode: according to the simulation data and expert experience data, the corresponding index value of each scheme is solved according to a certain evaluation algorithm, with the purpose of evaluating whether the scheme can meet the use requirements of aviation emergency simulation rescue training assessment or ranking the various schemes. Analysis mode: The purpose is to analyze the influencing factors and identify the key factors that affect the change of indicators. Prediction mode: Using the existing data samples, fit the quantitative approximate mathematical model between the factors and indicators, and explore the unexplored factor space through the mathematical model to obtain a deep understanding of the problem.

[0135] It can be understood that the present embodiment is compatible with the three preset modes of evaluation / analysis / prediction, and any one of the three modes of evaluation, analysis or prediction can be selected for evaluation and analysis. The computer analysis and evaluation environment can switch modes and dock data as needed among the three modes, and the three preset modes can be used in combination to solve complex problems. Exemplarily, the relevant methods and algorithms of the three preset modes of evaluation, analysis and prediction (such as the preset weight calculation method, hierarchical analysis method, performance evaluation method, fuzzy comprehensive evaluation method, weighted average method, etc.) are organically integrated into the analysis and evaluation environment of the computer device used in the present embodiment in advance, forming a large number of evaluation, analysis and prediction operators. In addition, the analysis and evaluation environment can guide the next work content according to the current mode and work stage, dynamically switch the application mode, and automatically realize the docking of relevant data.

[0136] In one embodiment, the method further includes: exporting results. Generating an analysis and evaluation report such as a report and a graph based on the comprehensive scoring results of the training assessment to assist in decision-making or provide guidance. This embodiment does not limit the specific report form of the analysis and evaluation report.

[0137] Exemplarily, the analysis and evaluation report includes name (data type is String), student number (data type is String), subject (data type is String), machine score (data type is float, precision is 0.01), control desk operator score (data type is float, precision is 0.01) and comprehensive score (data type is float, precision is 0.01).

[0138] This embodiment provides a comprehensive assessment and evaluation method for aviation emergency simulation rescue training, which combines theoretical training and practical training, analyzes the collected theoretical assessment data and real-time training data by building an assessment and analysis model, gives a machine assessment result, and gives a comprehensive scoring result of the trainee's training assessment in combination with the operator assessment result, thereby integrating machine assessment and professional assessment, thereby achieving quantitative and qualitative analysis and evaluation of the quality and effect of aviation emergency simulation rescue training, which is conducive to scientifically conducting training evaluation, effectively improving training effects, and providing more efficient training management for aviation emergency rescue training.

[0139] In addition, an embodiment of the present invention also proposes a storage medium, on which is stored a comprehensive assessment and evaluation program for aviation emergency simulation rescue training. When the comprehensive assessment and evaluation program for aviation emergency simulation rescue training is executed by a processor, the steps of the comprehensive assessment and evaluation method for aviation emergency simulation rescue training as described above are implemented.

[0140] Reference Fig.11 , Fig.11 The present invention is a structural block diagram of an embodiment of a comprehensive assessment and evaluation system for aviation emergency simulation rescue training.

[0141] like Fig.11 As shown, the comprehensive assessment and evaluation system for aviation emergency simulation rescue training includes:

[0142] Theoretical assessment module 10, used to construct a theoretical training subsystem and deploy the theoretical training subsystem to collect theoretical assessment data of trainees;

[0143] The data parameter acquisition module 20 is used to collect real-time training data of the air rescue training subsystem, the underwater escape training subsystem and the environmental simulation subsystem;

[0144] An evaluation and analysis model building module 30 is used to build an evaluation and analysis model in a semi-automatic manner based on a wizard or in a graphical modeling manner based on an operator;

[0145] A first evaluation module 40 is used to analyze the real-time training data according to the evaluation analysis model to obtain a machine evaluation result;

[0146] A second evaluation module 50, used to obtain an operator evaluation result of the real-time training data;

[0147] The comprehensive evaluation module 60 is used to perform weighted averaging on the machine evaluation result and the operator evaluation result, and obtain a comprehensive scoring result of the training assessment according to the weighted average result and the theoretical assessment data.

[0148] This embodiment provides a comprehensive assessment and evaluation system for aviation emergency simulation rescue training, which combines theoretical training and practical training, analyzes the collected theoretical assessment data and real-time training data by building an assessment and analysis model, gives a machine assessment result, and gives a comprehensive scoring result of the trainee's training assessment in combination with the operator assessment result, thereby integrating machine assessment and professional assessment, thereby achieving quantitative and qualitative analysis and evaluation of the quality and effect of aviation emergency simulation rescue training, which is conducive to scientifically conducting training evaluation, effectively improving training effects, and providing more efficient training management for aviation emergency rescue training.

[0149] It should be noted that the technical details that are not described in detail in the embodiment of the comprehensive assessment and evaluation system for aviation emergency simulation rescue training can be referred to the comprehensive assessment and evaluation method for aviation emergency simulation rescue training as described above provided in any embodiment of the present invention, and will not be repeated here.

[0150] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, which includes: a memory, a processor, and a comprehensive assessment and evaluation program for aviation emergency simulation rescue training stored in the memory and executable on the processor, wherein the comprehensive assessment and evaluation program for aviation emergency simulation rescue training is configured to implement the comprehensive assessment and evaluation method for aviation emergency simulation rescue training as described above.

[0151] Reference Fig.12 , Fig.12 The figure is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present invention.

[0152] like Fig.12As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM memory) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0153] Those skilled in the art will understand that Fig.12 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0154] like Fig.12 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a comprehensive assessment and evaluation program for aviation emergency simulation rescue training.

[0155] exist Fig.12 In the electronic device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in the electronic device, and the electronic device calls the comprehensive assessment and evaluation program for aviation emergency simulation rescue training stored in the memory 1005 through the processor 1001, and executes the comprehensive assessment and evaluation method for aviation emergency simulation rescue training provided in an embodiment of the present invention.

[0156] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0157] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0158] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0159] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0160] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0161] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A comprehensive assessment method for aviation emergency simulation rescue training, characterized in that: include: Constructing a theoretical training subsystem and deploying the theoretical training subsystem to collect theoretical assessment data of training personnel; Collect real-time training data of the air rescue training subsystem, underwater escape training subsystem and environmental simulation subsystem; Construct evaluation and analysis models using a wizard-based semi-automatic approach or an operator-based graphical modeling approach; Analyze the real-time training data according to the evaluation analysis model to obtain a machine evaluation result; obtaining operator evaluation results of the real-time training data; The machine evaluation result and the operator evaluation result are weighted averaged, and a comprehensive training assessment score result is obtained based on the weighted average result and the theoretical assessment data.

2. The method according to claim 1, characterized in that The construction of the theoretical training subsystem and the deployment of the theoretical training subsystem to collect theoretical assessment data of training personnel include: Establish user management module, course management module, learning management module, examination management module and theoretical learning statistical analysis module based on B / S architecture; Constructing an initial theoretical training subsystem according to the user management module, course management module, learning management module, examination management module and theoretical learning statistical analysis module; The initial theoretical training subsystem is set according to a preset safety technology to obtain a theoretical training subsystem; Use Docker to deploy the theoretical training subsystem and manage the containerized deployment environment through Docker Compose; The theoretical assessment data of the trainees are collected according to the deployed theoretical training subsystem.

3. The method according to claim 2, characterized in that The setting of the initial theoretical training subsystem according to the preset safety technology includes: Setting up user authentication and authorization for the initial theoretical training subsystem based on JWT technology; Encrypting and setting the user password of the initial theoretical training subsystem according to BCrypt technology; Performing data transmission security settings on the database of the initial theoretical training subsystem according to MySQL's SSL encryption technology; Perform SQL attack check settings on the initial theoretical training subsystem based on the parameterized query technology of MyBatis; The initial theoretical training subsystem is set up to filter and escape user input content according to the template syntax of Vue.js.

4. The method according to claim 2, characterized in that The use of Docker to deploy the theoretical training subsystem and the management of the containerized deployment environment through Docker Compose include: MySQL is used as the database of the theoretical training subsystem, and a database container is created and run through Docker; Redis is used as the cache database of the theoretical training subsystem, and a Redis container is created and run through Docker; Use Elasticsearch as the full-text search engine of the theoretical training subsystem, and create and run the Elasticsearch container through Docker; Use Spring Boot framework to develop the backend application of the theoretical training subsystem, and use Docker to build and run the application container; Use Vue.js framework to develop the front-end application of the theoretical training subsystem, and build and run the application container through Docker; The theoretical training subsystem is log-collected, analyzed, and visualized based on ELK, and Prometheus and Grafana are used to monitor and analyze the performance of the theoretical training subsystem.

5. The method according to claim 1, characterized in that The real-time training data of the air rescue training subsystem, the underwater escape training subsystem and the environmental simulation subsystem are collected, including: Build signal acquisition software based on the adapter model; The signal acquisition software is used to collect video surveillance data of the air rescue training subsystem, underwater escape training subsystem and environmental simulation subsystem, wearable device data, motion parameters of simulated helicopters and water environment parameters; Performing real-time preprocessing on the video surveillance data, wearable device data, motion parameters of the simulated helicopter, and water environment parameters to obtain processed training data; wherein the preprocessing includes filtering, checking, and limiting; The processed training data is converted into a unified access data format to obtain real-time training data.

6. The method according to claim 5, characterized in that The signal acquisition software includes: ID connection configuration file, data packet configuration file, and operating environment file; wherein, The ID connection configuration file is used for the signal acquisition software to perform ID connection with the data communication software, and the connection properties are configured through the fmi.conf file; The data packet configuration file is used for communication between the signal acquisition software and the underlying hardware communication module, and the connection properties are configured through the fmi_trans_cfg.xml file; the attribute content of the fmi_trans_cfg.xml file includes key parameters and a configuration file framework, the key parameters include the config parameters in protocols, the config parameters in protocol, and the parameters in the field subset; the config parameters in protocols indicate the use of the modbusTCP protocol.

7. The method according to any one of claims 1 to 6, characterized in that The wizard-based semi-automatic method or operator-based graphical modeling method is used to construct the evaluation and analysis model, including: A plurality of evaluation index items are set based on a graphical modeling environment, wherein the index items include whether a safety accident occurs, task completion time, number of operations, overshoot, number of oscillations, and number of erroneous operations; Setting the indicator relationship between the indicator items based on a tree structure; The indicator weights of the indicator items are set according to the indicator relationship and importance; wherein the sum of the weights of indicators at the same level is one; Set the indicator value calculation criteria according to the calculation formula calculation criteria and the input evaluation calculation criteria; Establishing an evaluation index system according to the index items, index relationships, index weights and index value calculation criteria; An evaluation and analysis model is constructed according to the evaluation index system using a wizard-based semi-automatic method or an operator-based graphical modeling method.

8. The method according to claim 7, characterized in that The step of analyzing the real-time training data according to the evaluation analysis model to obtain a machine evaluation result includes: Reading the real-time training data; Taking the real-time training data as a whole, extracting samples from the real-time training data to obtain sample data, so as to establish a calculation correspondence between the collected real-time training data and the analysis and evaluation indicators; Calculate the sample data according to the indicator value calculation criteria in the evaluation indicator system to obtain the indicator value; Based on the preset mode, analysis, evaluation and calculation are performed according to the indicator value to obtain a machine evaluation result; wherein the preset mode includes an evaluation mode, an analysis mode and a prediction mode.

9. The method according to claim 8, characterized in that The performing analysis, evaluation and calculation according to the indicator value based on the preset mode includes: When the preset mode is the evaluation mode, the index values ​​are respectively calculated according to the simulation data and the empirical data in accordance with the preset evaluation algorithm; When the preset mode is the analysis mode, an influencing factor analysis is performed on the key factors that affect the change of the indicator value; When the preset mode is the prediction mode, a quantitative mathematical model between the sample data fitting factors and the index values ​​is constructed, and the preset exploration factor space is explored and analyzed through the mathematical model.

10. A comprehensive assessment and evaluation system for aviation emergency simulation rescue training, characterized in that: include: Theoretical assessment module, used to construct a theoretical training subsystem and deploy the theoretical training subsystem to collect theoretical assessment data of trainees; Data parameter acquisition module, used to collect real-time training data of the air rescue training subsystem, underwater escape training subsystem and environmental simulation subsystem; An evaluation and analysis model building module is used to build an evaluation and analysis model in a semi-automatic way based on a wizard or in a graphical modeling way based on an operator; A first evaluation module, used to analyze the real-time training data according to the evaluation analysis model to obtain a machine evaluation result; A second evaluation module, used to obtain an operator evaluation result of the real-time training data; The comprehensive evaluation module is used to perform weighted averaging on the machine evaluation results and the operator evaluation results, and obtain a comprehensive scoring result of the training assessment based on the weighted average result and the theoretical assessment data.

Images