Tourism management teaching practice auxiliary device

Abstract

The invention relates to the field of tourism management teaching, and discloses a tourism management teaching practice auxiliary device, which comprises head display equipment, a display screen, a loudspeaker and a host, and is characterized in that a multi-dimensional scoring module and a self-adaptive feedback module are stored in the host; the multi-dimensional scoring module performs comprehensive scoring on the performance of the practical trainee through multiple dimensions such as pronunciation accuracy, speech speed, grammar use, vocabulary richness, intonation and emotion expression and the like, and deals with fuzziness in scoring through a fuzzy comprehensive evaluation method; the self-adaptive feedback module predicts the performance trend of a practical trainee by using a long short-term memory network, dynamically adjusts feedback content based on a Bayesian optimization algorithm, and provides personalized real-time feedback; in addition, the device further comprises a multi-person cooperative training module which supports cooperative interaction of multiple trainees in the virtual environment, and the system generates a cooperative feedback report through cooperative score and contribution value calculation. The practical operation and team cooperation ability of tourism management teaching can be improved, and the practical training effect is improved.

Description

Technical Field

[0001] The invention relates to the technical field of tourism management teaching, in particular to a tourism management teaching practice auxiliary device. Background Art

[0002] With the rapid development of the tourism industry, the demand for teaching in the tourism management major is also increasing, especially for the cultivation of practical operation ability. Traditional tourism management teaching mostly relies on classroom lectures and case analysis. Although it can convey theoretical knowledge, it lacks in the cultivation of practical operation ability, language expression and teamwork. Actual work scenes such as tour guide explanations, customer reception, and complaint handling are difficult to effectively simulate through traditional teaching methods. Students lack immersive experience and it is difficult to exercise their adaptability and professional skills in real environments.

[0003] In recent years, although some colleges and institutions have tried to introduce practical teaching methods such as simulated operations and role-playing, these methods are often limited by venues and resources and cannot provide students with a highly simulated training environment. In addition, existing language training systems usually only score on a single dimension such as pronunciation and grammar, which makes it difficult to fully and objectively reflect students' overall performance. Feedback on students' language proficiency mostly relies on teachers' subjective evaluations and lacks a real-time, personalized feedback mechanism, which results in students being unable to discover and improve their shortcomings in a timely manner during the learning process.

[0004] At the same time, in actual tourism management work, teamwork is particularly important, but in the existing teaching model, students' teamwork training lacks effective simulation and evaluation methods, making it difficult to fully cultivate students' collaborative awareness and team communication skills. Therefore, the existing technology has major deficiencies in simulation practice scenarios, comprehensive language assessment, and teamwork training, and more advanced and comprehensive technical means are needed to improve this situation. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides a tourism management teaching practice auxiliary device, which provides an immersive language training and team collaboration simulation environment for tourism management teaching through virtual reality technology combined with an intelligent scoring and feedback system, thereby improving students' practical operation ability and teamwork ability.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a tourism management teaching practice auxiliary device, comprising:

[0007] Head-mounted display device, equipped with virtual reality software for generating virtual scenes related to tourism management;

[0008] Display screen, used to display the trainees’ interactions and operations in the virtual environment in real time;

[0009] Speakers for outputting audio generated by the trainee and the virtual environment;

[0010] The host connects the head-mounted display, display, and speakers. The host contains a processor and memory. The memory stores:

[0011] A multi-dimensional scoring module is used to comprehensively score trainees based on their pronunciation accuracy, grammar usage, speaking speed and fluency, vocabulary richness, and intonation and emotional expression;

[0012] Adaptive feedback module, used to provide real-time feedback based on the trainee's performance.

[0013] Preferably, the multi-dimensional scoring module includes:

[0014] The input module is used to obtain the trainee's performance characteristics, including pronunciation accuracy, grammar usage, speaking speed and fluency, vocabulary richness, intonation and emotional expression;

[0015] The scoring module is used to generate a multi-dimensional feature vector and score each feature component to generate a feature vector x = [x1, x2, ..., x n ], where x i is the trainee’s score in the i-th feature dimension, and n is the total number of features;

[0016] The weighted summation module is used to calculate the comprehensive score based on the feature vector. The comprehensive score calculation formula is:

[0017]

[0018] Among them, w i is the weight of the ith feature. The weight is selected based on the preset training goal and actual performance data to ensure that the importance of each dimension in the comprehensive score is reasonably reflected;

[0019] The fuzzy evaluation module is used to deal with the ambiguity caused by inaccurate pronunciation or intonation fluctuations in the scoring process, and maps the scores of each dimension to fuzzy sets:

[0020]

[0021] Among them, u j is the predefined evaluation level, μ(u j ) is the degree of membership, which indicates the performance of the trainee in this evaluation level;

[0022] The fuzzy evaluation module is used to generate the final fuzzy score through fuzzy comprehensive evaluation. The fuzzy evaluation module performs weighted comprehensive evaluation on the fuzzy scores of each feature. The comprehensive score result is:

[0023]

[0024] Where W is the weight vector, is the rating matrix containing each fuzzy rating;

[0025] Output module, used to output the trainee's final scoring result S fuzzy and use it for the control and adaptive adjustment of subsequent feedback modules.

[0026] Preferably, the adaptive feedback module comprises:

[0027] The real-time monitoring module is used to collect the trainee's language performance data in the virtual scene, including pronunciation, speaking speed, grammar usage and emotional expression, and generate time series data {x t}, where x t represents the performance characteristics of the trainee at time point t;

[0028] A learning path prediction module, used to predict the future performance of the trainee based on the time series data using a long short-term memory network, and the prediction results are used to determine the weak links of the trainee;

[0029] The feedback generation module is used to generate personalized feedback information through machine learning algorithms based on the output of the learning path prediction module, which is used to classify and identify the problem categories in the trainee's current performance and generate corresponding improvement suggestions based on the classification results;

[0030] The real-time feedback output module is used to provide the generated personalized feedback to trainees, teachers and other students in real time through the head-mounted display device, display screen and speaker, so as to make immediate improvements and teaching guidance.

[0031] Preferably, the adaptive feedback module further comprises:

[0032] Feedback optimization module, which is used to dynamically adjust the frequency and content of feedback based on the trainee's learning performance through the Bayesian optimization algorithm to maximize the trainee's learning effect;

[0033] The Bayesian optimization algorithm is used to calculate the trainee learning effect function f(θ) according to the feedback system parameter θ, and gradually adjust the parameter θ to find the optimal value θ * = arg maxθ f (θ) to ensure that trainees receive the most effective feedback at every stage of the training process.

[0034] Preferably, the machine learning algorithm is a random forest or a support vector machine.

[0035] Preferably, the memory further stores:

[0036] Multi-person collaborative training module is used to support collaborative learning and interaction among multiple trainees.

[0037] Preferably, the multi-person collaborative training module includes:

[0038] Collaborative scoring sharing module, used to obtain individual scores of multiple trainees in collaborative scenarios and team average rating The final score of each trainee is calculated according to the following formula:

[0039]

[0040] Among them, S i is the final score of trainee i, α is the weight parameter, and the weight parameter is used to adjust the balance between individual performance and team performance to evaluate the individual’s contribution to the team;

[0041] The collaborative behavior analysis module is used to analyze the behavioral characteristics of each trainee in the collaborative process based on their performance in the collaborative scoring sharing module, record the number of interactions, conversation quality, and role of each trainee in the team, and generate a behavioral characteristic matrix:

[0042]

[0043] Among them, a ij represents the behavioral score of trainee i for the jth collaborative task, m is the number of team members, and n is the number of collaborative tasks.

[0044] Preferably, the multi-person collaborative training module further includes:

[0045] The collaborative feedback generation module is used to quantify the contribution of each trainee according to the Shapley value in cooperative game theory. The calculation formula of the Shapley value is:

[0046]

[0047] Among them, v(S) is the team performance of subset S, φ i (v) is the contribution value of trainee i to the overall performance of the team, and N is the set of team members;

[0048] The collaborative feedback output module is used to output the team contribution feedback of each trainee obtained by calculating the Shapley value. The feedback content includes the analysis of the individual's strengths and weaknesses in the collaborative task and improvement suggestions. The feedback is presented through the display screen and speakers for reference by team members, teachers and other students.

[0049] The present invention also provides a tourism management teaching practice method using the device, comprising the following steps:

[0050] Initialize the device, including the head display, display, speaker, and host;

[0051] Load virtual scenes related to tourism management into the head-mounted display device and generate a virtual training environment for trainees;

[0052] Obtain the trainee's performance characteristics, including pronunciation accuracy, speaking speed, grammar usage, vocabulary richness, intonation and emotional expression, generate feature vectors, and calculate the trainee's comprehensive score based on a multi-dimensional scoring model;

[0053] The fuzzy comprehensive evaluation method is used to deal with the fuzziness in the scoring process, each feature score is mapped to a fuzzy set, and the final fuzzy comprehensive score is generated;

[0054] Based on the scoring results, real-time feedback is provided through the adaptive feedback module, including:

[0055] Use long short-term memory networks to predict trainees’ future performance;

[0056] Generate personalized feedback based on the trainee's current performance, which is presented through a display screen, a speaker, and a head-mounted display device;

[0057] Use Bayesian optimization algorithms to dynamically adjust feedback content and strategies to maximize training results;

[0058] Output final rating and improvement suggestions.

[0059] The method further includes a multi-person collaborative training step, wherein the multi-person collaborative training step includes:

[0060] Obtain individual scores and team average scores of multiple trainees in the collaborative scenario, and calculate the final score of each trainee based on the individual score and team score;

[0061] Record the behavioral characteristics of each trainee during the collaboration process and generate a behavioral characteristic matrix to describe the collaborative performance of each trainee;

[0062] Calculate the contribution value of each trainee in the team and generate collaborative feedback based on the contribution value;

[0063] Output collaborative feedback content, including each trainee’s role performance in the team and suggestions for improvement.

[0064] The present invention provides a tourism management teaching practice auxiliary device. It has the following beneficial effects:

[0065] 1. The present invention uses a head-mounted display device to enable trainees to enter a highly simulated virtual reality scene, simulating actual work scenes in tourism management such as tour guide explanations and hotel receptions. This immersive training environment enables students to participate in practical operations in person, which is far superior to the traditional classroom teaching mode and helps to improve students' practical operation ability and learning participation.

[0066] 2. The present invention uses a multi-dimensional scoring module to comprehensively and objectively evaluate the trainees' language performance from multiple dimensions, including pronunciation accuracy, speaking speed, grammar usage, vocabulary richness, intonation and emotional expression. This multi-dimensional evaluation method ensures the scientificity and accuracy of the scoring results, allowing students to understand the strengths and weaknesses of their own performance from different perspectives.

[0067] 3. The present invention introduces the fuzzy comprehensive evaluation method, so that the system can handle the ambiguity in the scoring process. For example, it will not deduct points too harshly for slight deviations in speech speed or intonation, thereby generating a more reasonable score. This mechanism improves the flexibility of scoring, ensures that the performance of trainees can be more accurately reflected, and avoids overly harsh evaluation.

[0068] 4. The adaptive feedback module of the present invention generates targeted and personalized feedback by monitoring the trainee's performance in real time, and outputs it synchronously through the head display device, display screen and speaker. The trainee can adjust his performance immediately according to the feedback and quickly improve his shortcomings. This personalized feedback mechanism significantly improves learning efficiency, enabling trainees to receive effective guidance and improvement in a short period of time.

[0069] 5. The present invention uses the Bayesian optimization algorithm to dynamically adjust the feedback content and strategy to ensure that each feedback is optimized according to the trainee's current learning status and needs. This dynamic adjustment mechanism can maximize the training effect, avoid unnecessary repeated feedback, and ensure that each trainee can get the most effective guidance at the most appropriate time.

[0070] 6. The multi-person collaboration training module of the present invention enables multiple trainees to interact and collaborate in the same virtual environment, simulating actual work scenarios such as team tour guides and cross-cultural communication. Through collaboration scoring and contribution analysis, the system not only evaluates the individual performance of each member, but also measures their ability to collaborate in the team, which helps to cultivate trainees' teamwork skills.

[0071] 7. The present invention calculates individual contributions in teamwork through Shapley values ​​and can generate collaborative feedback reports for each trainee. This feedback not only reflects the trainee's individual performance, but also analyzes his or her contribution to teamwork in detail, helping the trainee to better understand how to play a role in the team and improve the cultivation of teamwork ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 is a schematic diagram of the device structure of the first embodiment of the present invention;

[0073] Figure 2 It is a schematic diagram of the use of the device of the first embodiment of the present invention;

[0074] Figure 3 is a schematic diagram of the device structure of the second embodiment of the present invention;

[0075] Figure 4 It is a schematic diagram of the use of the device of the second embodiment of the present invention;

[0076] Figure 5 It is a flow chart of the teaching practice method of the present invention.

[0077] Among them, 10. Host; 11. Multi-dimensional scoring module; 12. Adaptive feedback module; 13. Multi-person collaborative training module; 20. Head-mounted display device; 30. Display screen; 40. Speaker. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the specification 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.

[0079] Embodiment 1:

[0080] Please refer to the attached Figure 1 -Attached Figure 2 The embodiment of the present invention provides a tourism management teaching practice auxiliary device, which combines virtual reality technology with a multi-dimensional intelligent feedback system to assist language training and practical operations in tourism management teaching. By using this device, students can conduct practical training in a virtual tourism scene, and the system can evaluate students' language performance in real time and give feedback, thereby improving students' actual work ability. The device includes a head display device 20, a display screen 30, a speaker 40, and a host 10. The various components of the device of the present invention are described in detail below.

[0081] Headset 20

[0082] The head display device 20 in the embodiment of the present invention is configured with virtual reality software for generating virtual scenes related to tourism management. The head display device 20 can be a common VR head display device 20, such as Oculus, HTC Vive, etc., with high-resolution display and wide viewing angle support. The head display device 20 can generate virtual scenes related to the tourism industry according to the set teaching content, such as scenic spots explained by tour guides, hotel front desks, travel agency reception desks, etc., to simulate actual working environments and task scenarios.

[0083] The head display device 20 completely immerses the trainees in the virtual environment, allowing them to interact and operate in a highly restored scene. Students can use the head display device 20 to perform operations such as tour guide explanations and communication with virtual customers in the virtual scene, thereby enhancing their practical operation capabilities. Compared with traditional classroom teaching, virtual reality scenes can simulate various scenarios in the tourism industry more realistically and specifically, greatly improving students' participation and learning effects.

[0084] Display 30

[0085] The display screen 30 is used to project the trainee's operation in the virtual environment in real time for teachers and other students to observe and learn. The display screen 30 synchronizes the interaction and dialogue in the virtual scene in real time, and teachers and other students can understand the trainee's performance through the display screen 30. The display screen 30 not only supports static image display, but also can present details such as the dialogue and actions of the trainee with virtual tourists or customers in the virtual environment.

[0086] One of the functions of the display screen 30 is to provide an intuitive display effect for teaching, so that all participants can watch the performance of each trainee, and further provide teaching interaction and feedback guidance. The teacher can comment on the students' language expression, attitude and business operation by observing the content on the display screen 30, and help the trainees improve their performance.

[0087] Speaker 40

[0088] The speaker 40 is used to output the audio of the trainee and the virtual environment, including the trainee's language expression and the audio feedback generated in the virtual scene. For example, questions raised by virtual tourists in the virtual scene, or background sounds in the scene (such as traffic, scenic spot guide sounds, etc.) are all played in real time through the speaker 40. The setting of the speaker 40 can synchronize the trainee's language expression and the sound in the virtual scene to the teacher and other students, providing a more immersive teaching environment.

[0089] The use of the loudspeaker 40 can amplify the trainee's language performance in the virtual scene, making it easier for other onlookers to understand and evaluate. At the same time, the sound effects in the virtual scene can also enhance the teaching atmosphere, allowing students to experience the working scenes in the tourism industry more realistically.

[0090] Host 10

[0091] The host 10 is one of the core components of the device of the present invention. It connects the head display device 20, the display screen 30 and the speaker 40, and is responsible for controlling the operation of the entire system. The host 10 includes a processor and a memory. The processor is used to execute the scoring and feedback algorithm, and the memory is used to store the virtual reality scene and the training data of the trainee. The host 10 can run the virtual reality software and update the virtual scene content in real time through interaction with the head display device 20.

[0092] The core functions of the host 10 are reflected in its two main modules of storage and execution: a multi-dimensional scoring module 11 and an adaptive feedback module 12.

[0093] The multi-dimensional scoring module 11 is used to conduct a comprehensive and objective evaluation of the trainees' language performance. Through real-time monitoring and analysis of multiple language dimensions, the system can quantify the trainees' language operations in the virtual scene of tourism management from multiple angles, and generate the final scoring results through weighted synthesis. This module is closely integrated with the adaptive feedback module 12, and the scoring results are directly used for the adjustment and optimization of the feedback module, thereby providing accurate training guidance for the trainees.

[0094] In this embodiment, the multi-dimensional language performance characteristics of the trainee are obtained.

[0095] The multi-dimensional scoring module 11 first obtains the trainee's performance characteristics through speech recognition and natural language processing technology. Each characteristic represents a language dimension, including:

[0096] Pronunciation accuracy: Through speech recognition technology, the system analyzes the match between the trainee's pronunciation and the standard pronunciation. This feature measures whether the trainee's pronunciation is correct and is expressed as a percentage.

[0097] Grammar usage: The module uses natural language processing (NLP) technology to analyze the trainee's sentence structure and grammatical rules to determine whether they conform to language standards. The system automatically detects syntactic errors and records the number of errors to generate a score for this dimension.

[0098] Speech speed and fluency: The system monitors the trainee's speech rhythm and coherence, and calculates the number of words pronounced per minute and the length of pauses. Based on this data, the system determines whether the speech is fluent and whether the speech speed is too fast or too slow. This feature evaluates the fluency and adaptability of the performance.

[0099] Vocabulary richness: The system evaluates whether the trainee uses rich and appropriate vocabulary by analyzing the diversity of their vocabulary. The repetition rate, complexity and diversity of vocabulary will be used as the basis for scoring.

[0100] Intonation and emotional expression: The module is based on voice adjustment technology and monitors whether the trainee's intonation changes and emotional expressions are suitable for specific scenarios. For example, a tour guide's explanation needs to have a sense of hierarchy and emotional integration. The system analyzes these elements and generates a score.

[0101] In this embodiment, the feature vector is generated

[0102] After obtaining multiple language dimension features, the system uses each feature value as a component of a vector to form the trainee's language performance feature vector. The vector is represented as:

[0103] x=[x1,x2,…,x n ]

[0104] where x i is the trainee’s score in the i-th feature dimension, and n is the total number of features.

[0105] In this embodiment, the comprehensive score is calculated

[0106] In order to obtain the trainee's comprehensive language ability score, the system uses a weighted summation method to process the feature vector. Each dimension has a preset weight w i , these weights can be adjusted according to the training objectives or course focus. For example, some scenarios may focus more on pronunciation accuracy, while other scenarios may focus more on grammar usage. Therefore, the system calculates the comprehensive score according to the following formula:

[0107]

[0108] Among them, S is the comprehensive score of the trainee, w i is the weight of the i-th dimension. The weight distribution is usually determined by the teaching objectives or specific scenario requirements, so that the score can accurately reflect the actual language ability of the trainees.

[0109] In this embodiment, the fuzzy evaluation process

[0110] In order to deal with the ambiguity in the scoring, especially in some cases when language errors may not seriously affect the overall performance, the system introduces a fuzzy comprehensive evaluation method. The score of each feature is mapped to a fuzzy set to evaluate the trainee's performance more flexibly.

[0111] Defining fuzzy sets for:

[0112]

[0113] Among them, u j represents the preset performance level (such as excellent, good, average, poor), μ(u j) represents the trainee's membership in this level. The system performs fuzzy judgment on each dimension and converts the score into a fuzzy membership matrix.

[0114] Then, the fuzzy comprehensive evaluation model is used to perform weighted calculation on the fuzzy scores of all dimensions to generate a fuzzy comprehensive score:

[0115]

[0116] Where W is the weight vector, is the rating matrix containing each fuzzy rating.

[0117] In this embodiment, the scoring result is output

[0118] Finally, the system generates a final scoring report based on the fuzzy comprehensive score and the individual scores of each dimension. The scoring results are fed back to the teacher and other trainees through the display screen 30 and the speaker 40, and the teacher can make a detailed evaluation and explanation of the trainee's performance based on the score. At the same time, the scoring results will also be input into the adaptive feedback module 12 to provide a basis for subsequent real-time feedback.

[0119] This scoring mechanism not only comprehensively covers all dimensions of trainees' language performance, but also can flexibly adjust the evaluation focus according to specific teaching needs, ensuring that the scoring process has wide adaptability and high accuracy.

[0120] The adaptive feedback module 12 is designed to provide personalized, real-time feedback based on the trainee's language performance. This module works in conjunction with the multi-dimensional scoring module 11 to generate timely and targeted feedback information by real-time monitoring and analysis of the trainee's performance data, and combining historical data with the prediction model. The main function of the adaptive feedback module 12 is to evaluate the trainee's performance trend through a machine learning algorithm, and adjust the feedback content and strategy through a feedback optimization algorithm to improve the trainee's learning effect.

[0121] In this embodiment, real-time monitoring and data collection

[0122] The adaptive feedback module 12 first monitors the trainee's language performance data in real time through the processor in the host 10. Specifically, the system continuously collects and processes data related to pronunciation, grammar, speaking speed, intonation, etc. as time series data {x t The time series data reflects the trainee's continuous performance in the virtual scene and contains the specific language feature value at each time point t.

[0123] After these data are processed by the multi-dimensional scoring module 11, corresponding scoring results are generated. The feedback module judges the current performance of the trainee based on these results and prepares personalized feedback content accordingly.

[0124] In this embodiment, the learning path prediction based on historical data

[0125] In order to provide more accurate feedback, the adaptive feedback module 12 uses the trainee's historical performance data to predict their future performance trends. This module performs time series prediction through a long short-term memory network (LSTM), which is a recursive neural network suitable for processing time series data and can capture the long-term dependencies in the trainee's language performance.

[0126] The specific calculation process of LSTM is as follows:

[0127] h t =σ(W h [h t-1 ,x t ]+b h )

[0128] Among them, h t is a hidden state, indicating that the system knows the trainee at time point h t The prediction, h t-1 is the hidden state at the previous moment, x t is the current input data (the trainee’s current language performance), W h is the weight matrix, b h is the bias and σ is the activation function.

[0129] By analyzing time series data, LSTM can predict the performance trends of trainees, laying the foundation for the system to generate more targeted feedback. If the prediction results show that the trainee has persistent problems in a specific area (such as pronunciation or grammar), the system will strengthen the feedback in that area.

[0130] In this embodiment, personalized feedback is generated

[0131] Based on the prediction of the trainee's future performance, the adaptive feedback module 12 generates personalized feedback information based on the current score and historical performance. The feedback information is automatically classified and decided through machine learning algorithms (such as support vector machines or random forests). The system identifies the trainee's weaknesses in different language dimensions, such as pronunciation errors or unstable speaking speed, and then provides specific improvement suggestions.

[0132] The content of feedback is not limited to directly pointing out mistakes, but also includes affirming good performance to further consolidate the trainees' language ability. In this process, the system will dynamically adjust the focus of feedback to ensure that trainees will not feel frustrated due to excessive corrections and can improve quickly.

[0133] In this embodiment, feedback optimization and dynamic adjustment

[0134] In order to improve the effectiveness of feedback, the adaptive feedback module 12 dynamically adjusts the content and frequency of feedback through the Bayesian optimization algorithm. The Bayesian optimization algorithm gradually optimizes the feedback parameters of the system based on the trainee's current performance data and past learning feedback, so that each round of feedback can have the greatest positive impact on the trainee's performance.

[0135] The goal of Bayesian optimization is to find the optimal parameter θ of the feedback system * , so that the trainee's learning effect function f(θ) is maximized. Bayesian optimization uses the Gaussian process as a prior distribution to model the effect of feedback and iteratively adjust the feedback parameters. The optimization process can be expressed as:

[0136] θ * = arg max θ f(θ)

[0137] Through such optimization, the system can ensure that the content and timing of each feedback are fine-tuned to suit the specific needs of the trainees.

[0138] In this embodiment, the feedback output mode is

[0139] The personalized feedback information generated by the adaptive feedback module 12 is synchronously output through the head display device 20, the display screen 30 and the speaker 40. The trainee can directly see the feedback information provided by the system in the virtual scene through the head display device 20, and the teacher and other students can understand the trainee's performance and feedback content through the display screen 30 and the speaker 40. This multi-dimensional feedback output method not only ensures that the trainee can improve his or her performance in a timely manner, but also promotes the teacher's control and adjustment of the teaching process.

[0140] In this embodiment, the feedback result is recycled

[0141] After each training session, feedback information will be stored by the system and used for prediction in the next training session. The errors and improvement measures made by the trainee in the previous training session will affect the generation method and content of subsequent feedback, forming an adaptive learning closed loop. This recycling ensures that the system can continuously adjust the feedback strategy as the trainee progresses, achieving self-optimization of the personalized learning path.

[0142] In summary, through this embodiment, the present invention provides efficient and accurate language training support, and improves the effect and personalized experience of tourism management teaching practice.

[0143] Embodiment 2:

[0144] Please refer to the attached Figure 3 -Attached Figure 4The second embodiment of the present invention is basically the same as the first embodiment, and both provide a tourism management teaching practice auxiliary device based on virtual reality. However, the difference of this embodiment is that a multi-person collaborative training module 13 is further stored in the memory, and the module is used to support collaborative learning and interaction between multiple trainees.

[0145] The multi-person collaborative training module 13 of the present invention provides an interactive and collaborative learning environment for multiple trainees in the virtual reality tourism management teaching practice. Different from single-person training, the multi-person collaborative training module 13 creates a virtual team scene, enabling trainees to complete tasks together, simulating the team work environment in the tourism industry, such as tour guide team collaboration, cross-cultural customer reception, etc. This module not only evaluates the individual performance of each trainee, but also analyzes the overall performance of the team and the contribution of each member through collaborative scoring and collaborative feedback mechanisms, thereby providing comprehensive evaluation and improvement suggestions for trainees.

[0146] In this embodiment, the collaborative scoring sharing module

[0147] The multi-person collaborative training module first uses the collaborative scoring sharing module to score and analyze the performance of multiple trainees in the collaborative scenario. Each trainee's performance includes both his or her individual contribution and his or her performance in teamwork. Therefore, the system generates a personal score for each trainee. and team average rating Finally, the trainee’s total score is calculated.

[0148] The total score is calculated as follows:

[0149]

[0150] Among them, S i is the total score of trainee i, and α is an adjustable weight parameter used to balance the impact of individual performance and team performance on the total score. The individual score reflects the trainee’s independent contribution in language performance and task completion, while the team score measures their synergy and support in collaboration.

[0151] In this embodiment, the collaborative behavior analysis module

[0152] In order to further refine the performance of each trainee, the system records the specific behavioral characteristics of each trainee in the team through the collaborative behavior analysis module. The system monitors the interaction of each member in the team in real time, including factors such as task allocation, communication frequency and decision-making contribution. This module generates a behavioral characteristic matrix Among them, a ij represents the behavioral score of trainee i for the jth collaborative task, m is the number of team members, and n is the number of collaborative tasks.

[0153] Each element in the matrix reflects the trainee's performance in a specific task, for example, the trainee's explanation time in the tour guide team, the frequency of answering questions, etc. By analyzing the behavior matrix, the system can identify the trainee's team roles (such as leader, supporter, executor) and give personalized feedback based on these roles.

[0154] In this embodiment, the collaborative feedback generation module

[0155] Collaborative training not only evaluates the individual and team performance of trainees, but also measures their contribution to the overall team success. Therefore, the collaborative feedback generation module calculates the contribution of each trainee to the team through the Shapley value in cooperative game theory. The calculation method of the Shapley value takes into account the contribution of each trainee to different sub-group teams, ensuring that the feedback results accurately quantify the actual impact of each member in the team.

[0156] The formula for the Shapley value is:

[0157]

[0158] Among them, v(S) is the team performance of subset S, φ i (v) is the contribution value of trainee i to the overall performance of the team, and N is the set of team members.

[0159] The collaborative feedback generation module generates a personalized collaborative feedback report for each trainee based on these contribution values. The feedback content includes not only the pros and cons of the individual's language performance, but also the trainee's role performance in the team, cooperation efficiency, and impact on the overall success of the team. In this way, the system can provide comprehensive feedback to each trainee to help them understand how to better participate in teamwork.

[0160] In this embodiment, the feedback output mode

[0161] The collaborative feedback generated by the system is synchronously output through the head display device 20, the display screen 30 and the speaker 40, ensuring that each trainee can receive feedback information in a timely manner. Through the prompts in the virtual scene, the trainee can immediately understand his or her performance in the team and the room for improvement. At the same time, the teacher and other students can see the collaborative feedback of each trainee through the display screen 30, which is convenient for subsequent teaching discussions and team performance improvement.

[0162] In this embodiment, the collaborative training process

[0163] The actual operation process of multi-person collaboration training module 13 is as follows:

[0164] 1. Scenario initialization: The system generates collaborative tasks for multiple trainees, and the trainees enter the virtual team scenario through the head display device 20, such as jointly receiving a large tourist group or collaboratively handling tourist complaints;

[0165] 2. Behavior monitoring and scoring: The system monitors each trainee’s individual performance and team collaboration behavior in real time, records key interaction indicators, and generates individual and team scores;

[0166] 3. Behavioral characteristic analysis: The system generates a behavioral characteristic matrix to analyze each trainee’s role and contribution in the team and evaluate their performance in specific tasks;

[0167] 4. Contribution value calculation and feedback generation: The system calculates each trainee’s contribution to the team through the Shapley value and generates a personalized collaborative feedback report;

[0168] 5. Feedback output: The feedback content is presented to the trainee and the teacher through the head display device 20, the display screen 30 and the speaker 40, so that the trainee can improve his performance in real time.

[0169] The present invention can effectively support multiple trainees to participate in teamwork tasks in a virtual scene at the same time through the multi-person collaboration training module 13. This module comprehensively evaluates each member of the team through behavior analysis, collaboration scoring and collaborative feedback mechanism, and generates personalized feedback based on their specific performance.

[0170] In general, the present invention uses virtual reality technology to provide trainees with an immersive teaching environment, and combines the multi-dimensional scoring module 11 and the adaptive feedback module 12 to comprehensively evaluate the trainees' language performance and provide real-time feedback. The device presents virtual scenes and feedback information through a head-mounted display device 20, a display screen 30, and a speaker 40. The multi-dimensional scoring covers multiple language performance dimensions such as pronunciation, grammar, and speaking speed. The adaptive feedback is personalized based on machine learning and Bayesian optimization. In addition, the multi-person collaborative training module 13 supports collaborative tasks of multiple trainees in virtual scenes, and quantifies the team contribution of each trainee through collaborative scoring and Shapley value feedback, thereby achieving a comprehensive evaluation and feedback of teamwork ability.

[0171] Please refer to the attached Figure 5 The present invention also provides a tourism management teaching practice method using the above device, which aims to improve the performance of trainees in language and teamwork by combining virtual reality scenes with intelligent feedback systems. Through this method, trainees can perform immersive language training and collaborative tasks in a virtual environment, and the system can monitor their performance in real time and provide personalized feedback. The following are the specific implementation steps of the method of the present invention.

[0172] S1. Initialize the device

[0173] First, initialize the hardware devices in the device, including the head display device, display screen, speaker and host. The head display device is used for trainees to immerse themselves in the virtual environment, while the display screen and speaker are used for teachers and other students to observe the trainees' operations. The host is responsible for running the virtual reality software and controlling the operation of the scoring and feedback modules.

[0174] S2. Load virtual scene and generate training environment

[0175] After the device is initialized, virtual scenes related to tourism management are loaded into the head-mounted display device to generate a virtual training environment for trainees. This virtual environment simulates various actual work scenarios, such as tour guide explanations, hotel reception, customer complaint handling, etc. When trainees complete the corresponding tasks in the virtual scene, the system automatically monitors their performance.

[0176] S3. Obtain the trainee's performance characteristics and score them

[0177] Based on the trainee's language performance in the virtual scene, the system obtains multi-dimensional performance features, including pronunciation accuracy, speaking speed, grammar usage, vocabulary richness, intonation and emotional expression. Each feature is converted into a feature vector, and then the trainee's comprehensive score is calculated through a multi-dimensional scoring model.

[0178] S4. Use fuzzy comprehensive evaluation method to deal with ambiguity in scoring

[0179] In order to more accurately reflect the trainee's performance, the system uses fuzzy comprehensive evaluation to deal with ambiguity in the scoring process. Each feature score is mapped to a fuzzy set, and the final fuzzy comprehensive score is generated through a weighted comprehensive method. This process allows the system to accommodate a certain amount of ambiguity in the scoring, such as slight deviations in pronunciation or changes in speaking speed, making the final scoring more flexible and realistic.

[0180] S5. Provide real-time feedback based on scoring results

[0181] Based on the comprehensive scoring results of the trainees, the system provides real-time feedback through the adaptive feedback module. The principle and details of the feedback have been introduced in the device section. Specifically:

[0182] The system predicts the trainees’ future performance through the long short-term memory network (LSTM), thus providing support for subsequent training content and feedback optimization.

[0183] The system generates personalized feedback content, and the trainees' performance pros and cons and improvement suggestions are displayed in real time through head-mounted displays, displays and speakers, allowing trainees to make immediate improvements.

[0184] The system uses the Bayesian optimization algorithm to dynamically adjust the content and strategy of feedback to ensure that the feedback can help trainees improve their training results in a timely and effective manner.

[0185] S6. Output final score and improvement suggestions

[0186] After the training, the system outputs the trainee's final score and provides the trainee with complete improvement suggestions. These suggestions are based on their performance throughout the training process and provide a clear direction for the trainee's future learning. The output of the final score is displayed synchronously through the head display device and the display screen, and the teacher can provide further guidance to the trainee based on this score.

[0187] The method further includes a multi-person collaborative training step, which is applicable to a situation where multiple trainees perform team collaboration tasks in the same virtual scene.

[0188] Get individual and team scores: The system generates individual and team average scores based on each trainee's performance in the team. The individual score evaluates the trainee's independent performance, while the team score reflects the cooperation of the entire team. The final score is calculated by combining the individual and team scores.

[0189] Record behavioral characteristics and generate a behavioral characteristic matrix: The system records the behavioral characteristics of each trainee during the collaboration process, such as task completion, communication frequency, contribution to team decision-making, etc. These data are converted into a behavioral characteristic matrix to describe the specific performance of each trainee in the collaboration.

[0190] Calculate the contribution value of trainees and generate collaborative feedback: Based on the behavioral characteristic matrix, the system uses the Shapley value in cooperative game theory to calculate the contribution value of each trainee in the team. The contribution of each trainee is not only reflected in his or her personal performance, but also in his or her impact on the overall success of the team.

[0191] Output collaborative feedback: The system generates collaborative feedback reports based on the contribution value and outputs them through the head-mounted display device and the display screen. The feedback content includes the trainee's role performance in the team, the pros and cons analysis of the collaboration, and improvement suggestions, helping the trainee to improve their teamwork ability in future collaborative tasks.

[0192] Through the above steps, the method of the present invention provides an effective practical auxiliary means for tourism management teaching. The method uses virtual reality technology and intelligent feedback system to enable trainees to conduct multi-dimensional language training and teamwork in a virtual scene. The system helps trainees to fully understand their own performance and make improvements through accurate scoring and feedback mechanisms, thereby improving their actual work ability and teamwork ability.

[0193] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A tourism management teaching practice auxiliary device, characterized in that: include: Head-mounted display device, equipped with virtual reality software for generating virtual scenes related to tourism management; Display screen, used to display the trainees’ interactions and operations in the virtual environment in real time; Speakers for outputting audio generated by the trainee and the virtual environment; The host connects the head-mounted display, display, and speakers. The host contains a processor and memory. The memory stores: A multi-dimensional scoring module is used to comprehensively score trainees based on their pronunciation accuracy, grammar usage, speaking speed and fluency, vocabulary richness, and intonation and emotional expression; Adaptive feedback module, used to provide real-time feedback based on the trainee's performance.

2. A tourism management teaching practice auxiliary device according to claim 1, characterized in that: The multi-dimensional scoring module includes: The input module is used to obtain the trainee's performance characteristics, including pronunciation accuracy, grammar usage, speaking speed and fluency, vocabulary richness, intonation and emotional expression; The scoring module is used to generate a multi-dimensional feature vector and score each feature component to generate a feature vector x = [x1, x2, ..., x n ], where x i is the trainee’s score in the i-th feature dimension, and n is the total number of features; The weighted summation module is used to calculate the comprehensive score based on the feature vector. The comprehensive score calculation formula is: Among them, w i is the weight of the ith feature. The weight is selected based on the preset training goal and actual performance data to ensure that the importance of each dimension in the comprehensive score is reasonably reflected; The fuzzy evaluation module is used to deal with the ambiguity caused by inaccurate pronunciation or intonation fluctuations in the scoring process, and maps the scores of each dimension to fuzzy sets: Among them, u j is the predefined evaluation level, μ(u j ) is the degree of membership, which indicates the performance of the trainee in this evaluation level; The fuzzy evaluation module is used to generate the final fuzzy score through fuzzy comprehensive evaluation. The fuzzy evaluation module performs weighted comprehensive evaluation on the fuzzy scores of each feature. The comprehensive score result is: Where W is the weight vector, is the rating matrix containing each fuzzy rating; Output module, used to output the trainee's final scoring result S fuzzy and use it for the control and adaptive adjustment of subsequent feedback modules.

3. A tourism management teaching practice auxiliary device according to claim 1, characterized in that: The adaptive feedback module comprises: The real-time monitoring module is used to collect the trainee's language performance data in the virtual scene, including pronunciation, speaking speed, grammar usage and emotional expression, and generate time series data {x t }, where x t represents the performance characteristics of the trainee at time point t; A learning path prediction module is used to predict the future performance of the trainee based on the time series data using a long short-term memory network, and the prediction results are used to determine the weak links of the trainee; The feedback generation module is used to generate personalized feedback information through machine learning algorithms based on the output of the learning path prediction module, which is used to classify and identify the problem categories in the trainee's current performance and generate corresponding improvement suggestions based on the classification results; The real-time feedback output module is used to provide the generated personalized feedback to trainees, teachers and other students in real time through the head-mounted display device, display screen and speaker, so as to make immediate improvements and teaching guidance.

4. A tourism management teaching practice auxiliary device according to claim 3, characterized in that: The adaptive feedback module further comprises: Feedback optimization module, which is used to dynamically adjust the frequency and content of feedback based on the trainee's learning performance through the Bayesian optimization algorithm to maximize the trainee's learning effect; The Bayesian optimization algorithm is used to calculate the trainee learning effect function f(θ) according to the feedback system parameter θ, and gradually adjust the parameter θ to find the optimal value θ * = arg max θ f(θ) ensures that trainees receive the most effective feedback at every stage of the training process.

5. A tourism management teaching practice auxiliary device according to claim 3, characterized in that: The machine learning algorithm is a random forest or a support vector machine.

6. A tourism management teaching practice auxiliary device according to claim 1, characterized in that: The memory further stores: Multi-person collaborative training module is used to support collaborative learning and interaction among multiple trainees.

7. A tourism management teaching practice auxiliary device according to claim 6, characterized in that: The multi-person collaborative training module includes: Collaborative scoring sharing module, used to obtain individual scores of multiple trainees in collaborative scenarios and team average rating The final score of each trainee is calculated according to the following formula: Among them, S i is the final score of trainee i, α is the weight parameter, and the weight parameter is used to adjust the balance between individual performance and team performance to evaluate the individual’s contribution to the team; The collaborative behavior analysis module is used to analyze the behavioral characteristics of each trainee in the collaborative process based on their performance in the collaborative scoring sharing module, record the number of interactions, conversation quality, and role of each trainee in the team, and generate a behavioral characteristic matrix: Among them, a ij represents the behavioral score of trainee i for the jth collaborative task, m is the number of team members, and n is the number of collaborative tasks.

8. A tourism management teaching practice auxiliary device according to claim 7, characterized in that: The multi-person collaborative training module further includes: The collaborative feedback generation module is used to quantify the contribution of each trainee according to the Shapley value in cooperative game theory. The calculation formula of the Shapley value is: Among them, v(S) is the team performance of subset S, φ i (v) is the contribution value of trainee i to the overall performance of the team, and N is the set of team members; The collaborative feedback output module is used to output the team contribution feedback of each trainee obtained by calculating the Shapley value. The feedback content includes the analysis of the individual's strengths and weaknesses in the collaborative task and improvement suggestions. The feedback is presented through the display screen and speakers for reference by team members, teachers and other students.

9. A tourism management teaching practice method using the device according to any one of claims 1 to 8, characterized in that: The following steps are involved: Initialize the device, including the head display, display, speaker, and host; Load virtual scenes related to tourism management into the head-mounted display device and generate a virtual training environment for trainees; Obtain the trainee's performance characteristics, including pronunciation accuracy, speaking speed, grammar usage, vocabulary richness, intonation and emotional expression, generate feature vectors, and calculate the trainee's comprehensive score based on a multi-dimensional scoring model; The fuzzy comprehensive evaluation method is used to deal with the fuzziness in the scoring process, each feature score is mapped to a fuzzy set, and the final fuzzy comprehensive score is generated; Based on the scoring results, real-time feedback is provided through the adaptive feedback module, including: Use long short-term memory networks to predict trainees’ future performance; Generate personalized feedback based on the trainee's current performance, which is presented through a display screen, a speaker, and a head-mounted display device; Use Bayesian optimization algorithms to dynamically adjust feedback content and strategies to maximize training results; Output final rating and improvement suggestions.

10. The method according to claim 9, characterized in that The method further includes a multi-person collaborative training step, wherein the multi-person collaborative training step includes: Obtain individual scores and team average scores of multiple trainees in the collaborative scenario, and calculate the final score of each trainee based on the individual score and team score; Record the behavioral characteristics of each trainee during the collaboration process and generate a behavioral characteristic matrix to describe the collaborative performance of each trainee; Calculate the contribution value of each trainee in the team and generate collaborative feedback based on the contribution value; Output collaborative feedback content, including each trainee’s role performance in the team and suggestions for improvement.

Images