Automobile maintenance teaching system combining virtual simulation and intelligent game

Abstract

The invention discloses an automobile maintenance teaching system combining virtual simulation and an intelligent game. The system comprises a user terminal, a server, a database, a virtual simulation module and an intelligent game module. When a student selects a learning mode, the server receives a learning instruction of the user terminal, calls corresponding learning data from the database, calls the virtual simulation module to generate an automobile maintenance virtual teaching scene, and performs task teaching through the user terminal; when a student selects a game mode, the server receives a game instruction of the user terminal and calls the intelligent game module to generate a corresponding AI opponent, meanwhile, the virtual simulation module is called to generate an automobile maintenance virtual competition scene, competition type teaching is carried out through the user terminal to obtain a single task score, and total points are issued to the student. The virtual simulation technology and the intelligent game are combined, personalized teaching is achieved by enhancing interactivity, the learning enthusiasm and motivation of students are improved, and the learning condition is comprehensively evaluated.

Description

Technical Field

[0001] The present invention belongs to the technical field of automobile maintenance virtual simulation and intelligent teaching, and in particular relates to an automobile maintenance teaching system combining virtual simulation and intelligent games. Background Art

[0002] Automobile maintenance teaching plays a vital role in the development of the automobile industry. With the continuous advancement of automobile technology, especially the rapid development of new energy vehicles, higher requirements are placed on the professional quality and skill level of automobile maintenance personnel. In recent years, virtual simulation technology has gradually been applied in the field of automobile maintenance teaching. It provides students with a learning method that simulates a real maintenance environment, allowing students to practice operations in a virtual environment, which improves students' practical ability to a certain extent.

[0003] Most of the existing automobile maintenance virtual simulation software is limited to simulating the operation process in the real working environment, and there are some problems. Huang Yun pointed out in the document "Application Practice and Thinking of Virtual Simulation Technology in Higher Education Courses" that the current virtual simulation software has the following problems: the learning process is monotonous and boring, lacks personalized teaching, and is not attractive enough to students. At the same time, the concept of serious games has also begun to attract attention. Some educational institutions have tried to integrate game modes such as level-breaking into the teaching process, which has improved students' learning interest and participation to a certain extent, but the game mode is still relatively simple and is in its infancy. Summary of the invention

[0004] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art and to provide an automobile maintenance teaching system that combines virtual simulation and intelligent games, thereby combining virtual simulation technology with intelligent games, achieving personalized teaching by enhancing interactivity, and improving students' learning interest and motivation.

[0005] In order to achieve the above-mentioned object, the first object of the present invention is to provide an automobile maintenance teaching system combining virtual simulation and intelligent games, the system comprising a user terminal, a server, a database, a virtual simulation module and an intelligent game module; The user terminal is used to obtain student information and present an operation interface to the student; the operation interface includes a student information window and a mode selection window; the modes include a learning mode and a game mode; the learning mode is used to present a learning task list and learning task details; the game mode is used to generate an AI opponent to conduct competitive teaching for the student; the student information includes the student ID, the student rank, the student's historical record and the student's game preference; the student rank includes low rank, middle rank and high rank; the student's game preference includes little assistance, middle assistance and much assistance; the level of the AI ​​opponent includes low level, middle level and high level; the learning task is set based on the automobile maintenance course; the student rank, the student's game preference and the level of the AI ​​opponent are obtained by using an intelligent fuzzy algorithm; When the trainee selects the learning mode in the mode selection window, the user terminal obtains the learning task selected by the trainee from the learning list and sends a learning instruction to the server; the server receives the learning instruction from the user terminal and retrieves the corresponding learning data from the database according to the learning task selected by the trainee, and at the same time calls the virtual simulation module to generate a virtual teaching scene for automobile maintenance, and presents it to the trainee through the user terminal for task teaching; When the student selects the game mode, the user terminal sends a game command to the server; the server receives the game command from the user terminal and calls the intelligent game module to generate the corresponding AI opponent, retrieves the fault data from the database according to the student's rank and the AI ​​opponent, and calls the virtual simulation module to generate a virtual competition scene for automobile maintenance, which is presented to the student through the user terminal for competitive teaching to obtain the single task results and issue total points to the student; The server records the total points of students after each competitive teaching and uses it to improve the students' ranks and issue rewards; The database is used to store student information, learning tasks, learning data, fault data and competitive teaching data.

[0006] As a preferred technical solution, the virtual simulation module includes an environment construction module and an interaction design module; The environment construction module uses 3D modeling and physical engine technology to construct a car maintenance scene including a car model, a tool library and various car faults; The interaction design module is used to implement interactive actions in the automobile maintenance scene.

[0007] As a preferred technical solution, the intelligent game module includes an AI opponent generation module, a competition teaching module and a score calculation module; The opponent generation module uses an intelligent fuzzy algorithm to generate a corresponding AI opponent; The competition teaching module is used to judge the interactive operations of trainees in the virtual competition scene of automobile maintenance and score them to obtain the single task results; The points calculation module issues total points based on the students' individual task scores.

[0008] As a preferred technical solution, the intelligent fuzzy algorithm input variables are the language variables of the student's rank and the student's game preference, and the output variable is the language variable of the AI ​​opponent's level; the intelligent fuzzy algorithm obtains the fuzzy set of the output language variable based on the fuzzy set of the input language variable based on the set fuzzy control rules; The linguistic variables of the student's level include three fuzzy sets of low level, middle level and high level, and the fuzzy sets are defined by using a trapezoidal membership function; The language variables of the students' game preferences include three fuzzy sets: less assistance, medium assistance and more assistance, and the fuzzy sets are defined using a trapezoidal membership function; The linguistic variables of the AI ​​opponent level include three fuzzy sets of low level, medium level and high level, and the fuzzy sets are defined by using a trapezoidal membership function.

[0009] As a preferred technical solution, the opponent generation module uses the centroid method to perform defuzzification processing to obtain the level value of the AI ​​opponent, specifically:

[0010] in, AI Score is the level value of the AI ​​opponent, x It is the exact value of the domain corresponding to the membership degree of the fuzzy set of the output language variable; μ ( x ) is the membership degree of the fuzzy set of output linguistic variables obtained through fuzzy reasoning.

[0011] As a preferred technical solution, the score calculation module issues total scores based on the student's individual task scores, and the process is as follows: Determine whether the student has completed the competitive teaching within the end time of the AI ​​opponent and whether the single task score exceeds the score threshold; if not, no points reward will be issued; If the score is satisfied, then the AI ​​difficulty bonus score, time bonus score and single task score are calculated and added up to get the total score of the student's competitive teaching; The AI ​​difficulty bonus points are obtained by multiplying the difficulty coefficient set according to the AI ​​opponent level by the single task score; The time bonus points are obtained based on the difference between the student's end time and the AI ​​opponent's end time multiplied by the points per unit time; The single task score is the difference between the student's single task score and the score threshold.

[0012] As a preferred technical solution, the process of improving the student's rank is: The server converts the total points of the students after each competitive teaching into single task skill advancement value according to the task conversion rate and accumulates them; When the accumulated single-task skill advancement value reaches or exceeds a certain level of student rank, the student rank will be upgraded to that level; Rewards will be issued when students’ ranks are upgraded; the rewards include virtual rewards or physical rewards.

[0013] As a preferred technical solution, the task conversion rate is obtained in the following manner: Obtaining the competition difficulty and fault difficulty of the virtual competition scene of automobile maintenance, and using fuzzy algorithm to construct language variables of competition difficulty and fault difficulty; the language variable of competition difficulty includes three fuzzy sets of easy, difficult and extremely difficult; the language variable of fault difficulty includes three fuzzy sets of low, medium and high; Based on logic and experience, fuzzy rules are constructed, and the linguistic variables of the difficulty of the competition and the difficulty of the fault are used to infer the linguistic variables of the task conversion rate; the linguistic variables of the task conversion rate include three fuzzy sets of low conversion rate, medium conversion rate and high conversion rate; The linguistic variables of task conversion rate were converted into task conversion rate using the center of gravity method.

[0014] The second object of the present invention is to provide an automobile maintenance teaching method combining virtual simulation and intelligent games, which is applied to the above-mentioned automobile maintenance teaching system and includes the following steps: Deploy the automobile maintenance teaching system, input student information and initialize it; The trainee logs into the automobile maintenance teaching system through the user terminal and selects a corresponding mode; the mode includes a learning mode and a game mode; The server determines the mode selected by the trainee. If it is a learning mode, the server retrieves the corresponding learning data from the database according to the learning task selected by the trainee, and calls the virtual simulation module to generate a virtual teaching scene for automobile maintenance, which is presented to the trainee through the user terminal for task teaching. If it is a game mode, the server calls the intelligent game module to generate the corresponding AI opponent, retrieves the fault data from the database according to the trainee's rank and the AI ​​opponent, and calls the virtual simulation module to generate a virtual competition scene for automobile maintenance, which is presented to the trainee through the user terminal for competition-style teaching. After the task teaching is completed, the server records the students’ learning situation and data and stores them in the database; After the competitive teaching is completed, the server will record and store the students' learning situation and data in the database. At the same time, the total points will be issued and recorded according to the students' learning situation. When the total points accumulate to a certain level, the students' ranks will be automatically upgraded and rewards will be issued.

[0015] Compared with the prior art, the present invention has the following advantages and beneficial effects: The present invention provides an automobile maintenance teaching system combining virtual simulation and intelligent games, aiming to solve the problems existing in the prior art. First, the present application combines virtual simulation with intelligent games through virtual simulation modules and intelligent game modules, creating a learning environment for students that is both realistic and full of fun and challenges, effectively improving the students' interest in learning. Secondly, the system dynamically adjusts the difficulty of AI opponents according to the students' ranks, students' historical records and students' game preferences with the help of intelligent fuzzy algorithms, realizes personalized teaching by enhancing competitiveness and interactivity, and meets the learning needs of different students. At the same time, the system designs incentives for points rewards and rank upgrades. When students complete competitive teaching, they can get points. By accumulating points, they can improve their ranks and get corresponding rewards, which encourages students to continue to maintain their passion for learning and enhance their motivation for learning. Finally, the system comprehensively considers the speed and accuracy of students completing tasks and the difficulty coefficient of AI opponents and other multi-dimensional indicators to give corresponding points, and conducts a comprehensive and objective evaluation of the students' learning effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 The overall framework diagram of an automobile maintenance teaching system combining virtual simulation and intelligent games in an embodiment of the present invention.

[0018] Figure 2 4 is a flow chart of total integral calculation in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0020] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0021] like Figure 1 As shown, this embodiment is an automobile maintenance teaching system combining virtual simulation and intelligent games, including a user terminal, a server, a database, a virtual simulation module and an intelligent game module.

[0022] The user terminal is used to obtain student information and present an operation interface to the student; the operation interface includes a student information window and a mode selection window, etc.; the modes include learning mode and game mode; the learning mode is used to present a list of learning tasks and details of learning tasks; the game mode is used to generate an AI opponent to conduct competitive teaching for the student; the student information includes the student ID, student rank, student historical record and student game preference, etc.; the student rank includes low rank, middle rank and high rank, etc.; the student game preference includes little assistance, middle assistance and much assistance, etc.; the level of the AI ​​opponent includes low level, middle level and high level, etc.; the learning task is set based on the automobile maintenance course; the student rank, the student game preference and the level of the AI ​​opponent are obtained by using an intelligent fuzzy algorithm; When the trainee selects the learning mode in the mode selection window, the user terminal obtains the learning task selected by the trainee from the learning list and sends a learning instruction to the server; the server receives the learning instruction from the user terminal and retrieves the corresponding learning data from the database according to the learning task selected by the trainee, and at the same time calls the virtual simulation module to generate a virtual teaching scene for automobile maintenance, and presents it to the trainee through the user terminal for task teaching; When the student selects the game mode, the user terminal sends a game command to the server; the server receives the game command from the user terminal and calls the intelligent game module to generate the corresponding AI opponent, retrieves the fault data from the database according to the student's rank and the AI ​​opponent, and calls the virtual simulation module to generate a virtual competition scene for automobile maintenance, which is presented to the student through the user terminal for competitive teaching to obtain the single task results and issue total points to the student; The server records the total points of students after each competitive teaching and uses it to improve the students' ranks and issue rewards; The database is used to store student information, learning tasks, learning data, fault data, and competitive teaching data.

[0023] Furthermore, the virtual simulation module includes an environment construction module and an interaction design module; The environment construction module uses 3D modeling and physical engine technology to construct an automobile maintenance scene that includes a car model, a tool library and various car faults; the interaction design module is used to implement interactive actions in the automobile maintenance scene, such as tool selection, parts disassembly, fault detection, etc.

[0024] Furthermore, the intelligent game module includes an opponent generation module, a competition teaching module and a score calculation module; Among them, the opponent generation module uses an intelligent fuzzy algorithm to generate the corresponding AI opponent; the competition teaching module is used to judge the students' interactive operations in the virtual automobile maintenance competition scene and score them to obtain single task results; the point calculation module issues total points based on the students' single task results.

[0025] Furthermore, the input variables of the intelligent fuzzy algorithm are the language variables of the student's rank and the student's game preference, and the output variables are the language variables of the AI ​​opponent's level; the intelligent fuzzy algorithm obtains the fuzzy set of the output language variable based on the fuzzy set of the input language variable based on the set fuzzy control rule. Among them, the language variables of the student's rank include three fuzzy sets of low rank, middle rank and high rank, and the fuzzy set is defined by the trapezoidal membership function; the language variables of the student's game preference include three fuzzy sets of less assistance, medium assistance and more assistance, and the fuzzy set is defined by the trapezoidal membership function; the language variables of the AI ​​opponent's level include three fuzzy sets of low level, middle level and high level, and the fuzzy set is defined by the trapezoidal membership function.

[0026] In this embodiment, the domain of the language variables of the trainee's level is set to 1-7 levels according to the auto repair professional skill level, and the language variables of the trainee's level are divided into three fuzzy sets of low level, middle level and high level. The trapezoidal membership function is used to fuzzify the trainee's level. The membership functions of the three fuzzy sets of the student's level language variables are respectively: μ_low level (r) = { 1, if 1 ≤ r ≤ 2; 3 - r, if 2<r ≤ 3; 0, if r> 3 }; μ_middle position (r) = { 0, if r ≤ 1; r - 1, if 1 ≤ r<2; 1, if 2 ≤ r ≤ 4; 5 - r, if 4<r ≤ 5; 0, if r> 5 }; μ_high_rank(r) ={ 0, if r<4; r - 4, if 4 ≤ r<5; 1, if 5 ≤ r ≤ 6; 7 - r, if 6 <r ≤ 7 }; Among them, r is the specific domain value of the student's rank, that is, the actual rank value of the student's rank.

[0027] In this embodiment, the student game preference is defined as the situation in which the student needs assistance during the competitive teaching process. The domain of the language variable of the student game preference is set to 0-10 times, and the language variable of the student game preference is divided into three fuzzy sets: less assistance, medium assistance, and more assistance. The trapezoidal membership function is used to fuzzify the student game preference. The membership functions of the three fuzzy sets of the student game preference are: μ_less-assist(as) = ​​{ 1, if 0 ≤ as ≤ 1; (2- as) / 1, if 1<as ≤ 2; 0,if as> 2 }; μ_midassist(as) = ​​{ 0, if as ≤ 1; (as -1) / 2,if 1 <as ≤ 3; 1,if 3 <as ≤ 4; (5 - as) / 1, if 4<as ≤ 5; 0,if as> 5 }; μ_multi-assist(as) = ​​{ 0, if as ≤ 4; (as -4) / 2, if 4 <as ≤ 6; 1, if 6 <as ≤10 }; Among them, as is the specific domain value of the student's game preference, that is, the number of assists selected by the student.

[0028] In this embodiment, the domain of the language variable of the AI ​​opponent level is set to 1-21, and the language variable of the AI ​​opponent level is divided into three fuzzy sets: low, medium and high. The membership function is used to fuzzify them. The membership functions of the three fuzzy sets of the AI ​​opponent level are: μ_primary(gr) ={ 1, if 1 ≤ gr ≤ 3; (7-gr) / 4,if 3<gr ≤ 7; 0,if gr> 7 }; μ_intermediate(gr) ={ 0, if gr ≤ 6; (gr - 6) / 3,if 6 <gr ≤ 9; 1,if 9 <gr ≤ 12; (15-gr) / 3,if 12<gr ≤ 15; 0,if gr> 15 }; μ_Advanced(gr) = { 0, if gr ≤ 14; (gr -14) / 3,if 14 <gr ≤ 17; 1, if 17 <gr ≤ 21 }; Among them, gr is the specific domain value of the AI ​​opponent level, that is, the level value of the AI ​​opponent level.

[0029] In this embodiment, the constructed fuzzy control rule is: 1) If the student's rank is low and the student's game preference is more assist, the AI ​​opponent level is beginner.

[0030] 2) If the student's rank is low and the student's game preference is medium assist, the AI ​​opponent level is beginner.

[0031] 3) If the student's rank is low and the student's game preference is less assistance, then the AI ​​opponent level is intermediate.

[0032] 4) If the student's rank is mid-rank and the student's game preference is more assist, the AI ​​opponent level is beginner.

[0033] 5) If the student's rank is mid-rank and the student's game preference is mid-assist, then the AI ​​opponent level is mid-level.

[0034] 6) If the student's rank is mid-rank and the student's game preference is less assistance, then the AI ​​opponent level is advanced.

[0035] 7) If the student's rank is high and the student's game preference is more assist, then the AI ​​opponent level is intermediate.

[0036] 8) If the student rank is high and the student game preference is medium assist, then the AI ​​opponent level is advanced.

[0037] 9) If the student's rank is high and the student's game preference is less assistance, then the AI ​​opponent level is advanced.

[0038] Furthermore, defuzzification is the process of converting fuzzy sets into precise values; commonly used defuzzification methods include maximum method, average method, weighted average method, center method and centroid method. In this application, the opponent generation module uses the centroid method to perform defuzzification processing to obtain the level value of the AI ​​opponent, and the formula is:

[0039] in, AI Score is the level value of the AI ​​opponent, x It is the exact value of the domain corresponding to the membership degree of the fuzzy set of the output language variable; μ ( x ) is the membership degree of the fuzzy set of output linguistic variables obtained through fuzzy reasoning.

[0040] Further, such as Figure 2 As shown, the points calculation module issues total points based on the student's individual task scores. The process is as follows: Determine whether the student has completed the competitive teaching within the end time of the AI ​​opponent and whether the single task score exceeds the score threshold; if not, no points reward will be issued; If the score is satisfied, then the AI ​​difficulty bonus score, time bonus score and single task score are calculated and added up to get the total score of the student's competitive teaching; Among them, the AI ​​difficulty bonus points are obtained by multiplying the difficulty coefficient set according to the AI ​​opponent level by the single task score; since the AI ​​opponent levels are low, medium and advanced, a difficulty coefficient is assigned to each level to calculate and determine the AI ​​difficulty bonus points.

[0041] In this embodiment, the low-level difficulty coefficient is: d1=0.2; the intermediate-level difficulty coefficient is: d2=0.3; the advanced-level difficulty coefficient is: d3=0.5; then the AI ​​difficulty bonus score = single task score*corresponding difficulty coefficient.

[0042] Time bonus points are obtained based on the difference between the student's end time and the AI ​​opponent's end time multiplied by the points per unit time. Let the AI ​​opponent's end time be t0; if the student finishes the competitive teaching in a shorter time, he will get additional time bonus points. Let each unit time point be r, then time bonus points = (t0-t)×r, t is the student's end time.

[0043] The score of a single task is the difference between the student's single task score and the score threshold. Let the score threshold be Y, and the part of the student's single task score that exceeds the threshold will be used as an additional reward, then the score of a single task = TS-Y, where TS is the score of a single task.

[0044] Furthermore, in order to objectively reflect the students' auto repair skill level, the total points of the students after each competitive teaching are accumulated to improve the students' grades. The process is as follows: The server converts the total points of the students after each competitive teaching into single task skill advancement value according to the task conversion rate and accumulates them; When the accumulated single-task skill advancement value reaches or exceeds a certain level of student rank, the student rank will be upgraded to that level; Rewards will be given out when students’ ranks are upgraded; rewards include virtual rewards or physical rewards, etc.

[0045] Furthermore, the task conversion rate is related to the difficulty of the virtual competition scene of automobile maintenance and the difficulty of the fault, and is determined as follows: The competition difficulty and fault difficulty of the automobile maintenance virtual competition scene are obtained, and the fuzzy algorithm is used to construct the language variables of the competition difficulty and fault difficulty; among them, the language variables of the competition difficulty include three fuzzy sets: easy, difficult and extremely difficult; the language variables of the fault difficulty include three fuzzy sets: low, medium and high.

[0046] In this embodiment, the fuzzy set of the competition difficulty language variable and the fuzzy set of the fault difficulty language variable are represented by a trapezoidal membership function. The domain of the language variable of the competition difficulty (System Difficulty) is set to 1-10, and the membership functions of the three fuzzy sets are respectively: μ_easy(sd) = { 1, if 1 ≤ sd ≤ 3; 4 - sd, if 3 <sd ≤ 4; 0, if sd<1 or sd>4 }; μ_difficulty(sd) = { 0, if sd ≤ 2 or sd ≥ 8; (sd - 2) / 2, if 2 <sd ≤ 4; 1, if 4 <sd ≤ 6; (8 - sd) / 2, if 6 <sd<8 }; μ_very difficult (sd) = { 0, if sd ≤ 6; (sd - 6) / 1, if 6 <sd ≤ 7; 1, if 7 <sd ≤ 10 }.

[0047] Among them, sd is the specific domain value of the difficulty of the competition, that is, the difficulty value of the difficulty of the competition.

[0048] The domain of the linguistic variable of Fault Type Difficulty is set to 1-6, and the membership functions of the three fuzzy sets are: μ_lower(ftd) = { 1, if ftd ≤ 2; (3 - ftd) / 2,if 1<ftd ≤ 3; 0,if ftd> 3 }; μ_medium(ftd) = { 0, if ftd ≤ 2; (ftd - 2) / 2,if 2 <ftd ≤ 4; (6 - ftd) / 2,if 4<ftd ≤ 6; 0,if ftd> 6 }; μ_high(ftd) = { 0,if ftd ≤ 4; (ftd - 4) / 2,if 4 <ftd ≤ 6 }.

[0049] Among them, ftd is the specific domain value of the fault type difficulty, that is, the type difficulty value of the fault type difficulty.

[0050] Fuzzy control rules are constructed based on logic and experience, and the linguistic variables of task conversion rate are inferred using the linguistic variables of competition difficulty and fault difficulty. Among them, the linguistic variables of task conversion rate include three fuzzy sets of low conversion rate, medium conversion rate and high conversion rate.

[0051] In this embodiment, the domain of the linguistic variable of the task conversion rate (TaskR) is set to 0.5-2, and the membership functions of its three fuzzy sets are: μ_low conversion rate (tr) = { 1, if 0.5 ≤ tr ≤ 1; 2 - tr, if 12 }; μ_ conversion rate (tr) = { 0, if tr ≤ 0.5; (tr - 0.5) / 0.5, if 0.5 <tr ≤ 1; 1,if 1 <tr ≤ 1.5; (2 - tr) / 0.5, if 1.52 }; μ_high conversion rate (tr) = { 0, if tr ≤ 1; tr - 1 , if 1 <tr ≤ 2 }.

[0052] Among them, tr is the specific domain value of the task conversion rate, that is, the conversion value of the task conversion rate.

[0053] Use IF-THEN method to construct fuzzy control rules: IF system difficulty is easy AND fault type difficulty is low THEN task conversion rate is low conversion rate; IF system difficulty is easy AND fault type difficulty is medium THEN task conversion rate is medium conversion rate; IF system difficulty is easy AND fault type difficulty is high THEN task conversion rate is medium conversion rate; IF the system difficulty is difficult AND the fault type difficulty is low THEN the task conversion rate is medium conversion rate; IF the system difficulty is difficult AND the fault type difficulty is medium THEN the task conversion rate is medium conversion rate; IF system difficulty is difficult AND fault type difficulty is high THEN task conversion rate is high conversion rate; IF the system difficulty is extremely difficult AND the fault type difficulty is low THEN the task conversion rate is medium conversion rate; IF the system difficulty is extremely difficult AND the fault type difficulty is medium THEN the task conversion rate is high conversion rate; IF system difficulty is extremely difficult AND fault type difficulty is high THEN task conversion rate is high conversion rate.

[0054] Finally, the fuzzy set of the task conversion rate linguistic variables is converted into the task conversion rate using the centroid method. The formula is:

[0055] Among them, in the fuzzy processing of task conversion rate (TaskR), x is the exact value of the domain corresponding to the membership of the fuzzy set of the output language variable, μ ( x ) is the membership degree of the output linguistic variable fuzzy set obtained through the fuzzy control rules.

[0056] In this application, the rank values of the trainee ranks are set to 1-7 levels with reference to the automotive repair vocational skill levels. Therefore, when the accumulated single-task skill advancement value of each trainee exceeds the rank value of a certain level of trainee rank, the trainee is promoted to that level. The rules for rank promotion in this embodiment are as follows: Rank 1, 500 < E ≤ 1000, number of learning vehicle models = 1; Rank 2, 1001 < E ≤ 3000, number of learning vehicle models = 1; Rank 3, 3001 < E ≤ 6000, number of learning vehicle models = 1; Rank 4, 6001 < E ≤ 10000, 2 ≤ number of learning vehicle models ≤ 3; Rank 5, 10001 < E ≤ 15000, 2 ≤ number of learning vehicle models ≤ 3; Rank 6, 15001 < E ≤ 20000, 2 ≤ number of learning vehicle models ≤ 3; Rank 7, E ≥ 20001, number of learning vehicle models > 3.

[0057] Based on the trainee rank and points, the system can provide corresponding rewards and incentives, such as virtual medals, physical prizes, etc., to increase the learning motivation and stickiness of the trainees.

[0058] It should be noted that in the implementation manner of the automotive repair teaching system combining virtual simulation and intelligent games in the above embodiment, the logical division of each program module is only for illustration. In actual application, according to needs, for example, considering the configuration requirements of the corresponding hardware or the convenience of software implementation, the above functions can be assigned to different program modules to complete, that is, the internal structure of the automotive repair teaching system combining virtual simulation and intelligent games is divided into different program modules to complete all or part of the functions described above.

[0059] Embodiment 2 Based on the automotive repair teaching system combining virtual simulation and intelligent games in the above embodiment, this embodiment provides an automotive repair teaching method, including the following steps: Deploy the automotive repair teaching system, input trainee information and initialize it; The trainee logs in to the automotive repair teaching system through the user terminal and selects the corresponding mode; the modes include learning mode and game mode; The server determines the mode selected by the trainee. If it is a learning mode, the server retrieves the corresponding learning data from the database according to the learning task selected by the trainee, and calls the virtual simulation module to generate a virtual teaching scene for automobile maintenance, which is presented to the trainee through the user terminal for task teaching. If it is a game mode, the server calls the intelligent game module to generate the corresponding AI opponent, retrieves the fault data from the database according to the trainee's rank and the AI ​​opponent, and calls the virtual simulation module to generate a virtual competition scene for automobile maintenance, which is presented to the trainee through the user terminal for competition-style teaching. After the task teaching is completed, the server records the students’ learning situation and data and stores them in the database; After the competitive teaching is completed, the server will record and store the students' learning situation and data in the database. At the same time, the total points will be issued and recorded according to the students' learning situation. When the total points accumulate to a certain level, the students' ranks will be automatically upgraded and rewards will be issued.

[0060] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0061] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. An automobile maintenance teaching system combining virtual simulation and intelligent games, characterized in that: The system includes a user terminal, a server, a database, a virtual simulation module and an intelligent game module; The user terminal is used to obtain student information and present an operation interface to the student; the operation interface includes a student information window and a mode selection window; the modes include a learning mode and a game mode; the learning mode is used to present a learning task list and learning task details; the game mode is used to generate an AI opponent to conduct competitive teaching for the student; the student information includes the student ID, the student rank, the student's historical record and the student's game preference; the student rank includes low rank, middle rank and high rank; the student's game preference includes little assistance, middle assistance and much assistance; the level of the AI ​​opponent includes low level, middle level and high level; the learning task is set based on the automobile maintenance course; the student rank, the student's game preference and the level of the AI ​​opponent are obtained by using an intelligent fuzzy algorithm; When the trainee selects the learning mode in the mode selection window, the user terminal obtains the learning task selected by the trainee from the learning list and sends a learning instruction to the server; the server receives the learning instruction from the user terminal and retrieves the corresponding learning data from the database according to the learning task selected by the trainee, and at the same time calls the virtual simulation module to generate a virtual teaching scene for automobile maintenance, and presents it to the trainee through the user terminal for task teaching; When the student selects the game mode, the user terminal sends a game command to the server; the server receives the game command from the user terminal and calls the intelligent game module to generate the corresponding AI opponent, retrieves the fault data from the database according to the student's rank and the AI ​​opponent, and calls the virtual simulation module to generate a virtual competition scene for automobile maintenance, which is presented to the student through the user terminal for competitive teaching to obtain the single task results and issue total points to the student; The server records the total points of students after each competitive teaching and uses it to improve the students' ranks and issue rewards; The database is used to store student information, learning tasks, learning data, fault data and competitive teaching data.

2. The automobile maintenance teaching system according to claim 1, characterized in that: The virtual simulation module includes an environment construction module and an interaction design module; The environment construction module uses 3D modeling and physical engine technology to construct a car maintenance scene including a car model, a tool library and various car faults; The interaction design module is used to implement interactive actions in the automobile maintenance scene.

3. The automobile maintenance teaching system combining virtual simulation and intelligent games according to claim 1 is characterized in that: The intelligent game module includes an AI opponent generation module, a competition teaching module and a score calculation module; The opponent generation module uses an intelligent fuzzy algorithm to generate a corresponding AI opponent; The competition teaching module is used to judge the interactive operations of trainees in the virtual competition scene of automobile maintenance and score them to obtain the single task results; The points calculation module issues total points based on the students' individual task scores.

4. The automobile maintenance teaching system according to claim 3, characterized in that: The input variables of the intelligent fuzzy algorithm are the language variables of the student's rank and the student's game preference, and the output variables are the language variables of the AI ​​opponent's level; the intelligent fuzzy algorithm obtains the fuzzy set of the output language variables based on the fuzzy set of the input language variables based on the set fuzzy control rules; The language variables of the student's level include three fuzzy sets of low level, middle level and high level, and the fuzzy sets are defined by using a trapezoidal membership function; The language variables of the students' game preferences include three fuzzy sets: less assistance, medium assistance and more assistance, and the fuzzy sets are defined by using a trapezoidal membership function; The linguistic variables of the AI ​​opponent level include three fuzzy sets of low level, medium level and high level, and the fuzzy sets are defined by using a trapezoidal membership function.

5. The automobile maintenance teaching system according to claim 4, characterized in that: The opponent generation module uses the centroid method to perform defuzzification processing to obtain the level value of the AI ​​opponent, specifically: in, AI Score is the level value of the AI ​​opponent, x is the exact value of the domain corresponding to the membership degree of the fuzzy set of the output language variable; μ ( x ) is the membership degree of the fuzzy set of output linguistic variables obtained through fuzzy reasoning.

6. The automobile maintenance teaching system according to claim 3, characterized in that: The points calculation module issues total points based on the student's individual task scores, and the process is as follows: Determine whether the student has completed the competitive teaching within the end time of the AI ​​opponent and whether the single task score exceeds the score threshold; if not, no points reward will be issued; If the score is satisfied, then the AI ​​difficulty bonus score, time bonus score and single task score are calculated and added up to get the total score of the student's competitive teaching; The AI ​​difficulty bonus points are obtained by multiplying the difficulty coefficient set according to the AI ​​opponent level by the single task score; The time bonus points are obtained based on the difference between the student's end time and the AI ​​opponent's end time multiplied by the points per unit time; The single task score is the difference between the student's single task score and the score threshold.

7. The automobile maintenance teaching system according to claim 1, characterized in that: The process of improving the student's rank is as follows: The server converts the total points of the students after each competitive teaching into single task skill advancement value according to the task conversion rate and accumulates them; When the accumulated single-task skill advancement value reaches or exceeds a certain level of student rank, the student rank will be upgraded to that level; Rewards will be issued when students’ ranks are upgraded; the rewards include virtual rewards or physical rewards.

8. The automobile maintenance teaching system according to claim 7, characterized in that: The task conversion rate is obtained as follows: Obtaining the competition difficulty and fault difficulty of the virtual competition scene of automobile maintenance, and using fuzzy algorithm to construct language variables of competition difficulty and fault difficulty; the language variable of competition difficulty includes three fuzzy sets of easy, difficult and extremely difficult; the language variable of fault difficulty includes three fuzzy sets of low, medium and high; Based on logic and experience, fuzzy rules are constructed, and the linguistic variables of the difficulty of the competition and the difficulty of the fault are used to infer the linguistic variables of the task conversion rate; the linguistic variables of the task conversion rate include three fuzzy sets of low conversion rate, medium conversion rate and high conversion rate; The linguistic variables of task conversion rate were converted into task conversion rate using the center of gravity method.

9. A vehicle maintenance teaching method combining virtual simulation and intelligent games, characterized in that: The automobile maintenance teaching system applied to claim 1 comprises the following steps: Deploy the automobile maintenance teaching system, enter the trainee information and initialize it; The trainee logs into the automobile maintenance teaching system through the user terminal and selects a corresponding mode; the mode includes a learning mode and a game mode; The server determines the mode selected by the trainee. If it is a learning mode, the server retrieves the corresponding learning data from the database according to the learning task selected by the trainee, and calls the virtual simulation module to generate a virtual teaching scene for automobile maintenance, which is presented to the trainee through the user terminal for task teaching. If it is a game mode, the server calls the intelligent game module to generate the corresponding AI opponent, retrieves the fault data from the database according to the trainee's rank and the AI ​​opponent, and calls the virtual simulation module to generate a virtual competition scene for automobile maintenance, which is presented to the trainee through the user terminal for competition-style teaching. After the task teaching is completed, the server records the students’ learning situation and data and stores them in the database; After the competitive teaching is completed, the server will record and store the students' learning situation and data in the database. At the same time, the total points will be issued and recorded according to the students' learning situation. When the total points accumulate to a certain level, the students' ranks will be automatically upgraded and rewards will be issued.

Images