Practical training course development method, system and platform combined with virtual reality

Abstract

The invention relates to a practical training course development method, system and platform combined with virtual reality, and relates to the technical field of virtual reality, and the method comprises the steps: receiving a VR practical training course number selected by a user, and obtaining a first associated knowledge set from a knowledge base; analyzing personal proficiency and configuring a learning portrait based on the user identity information; performing group proficiency analysis on the learning portrait; performing weakness analysis according to the group and individual proficiency to obtain a weakness coefficient; screening a second associated knowledge set; and matching a corresponding model from the VR knowledge model library, and sending the model to a user side for practical training learning. The technical problem that in the prior art, VR training course display content is uniform, personalized matching is not carried out for weak knowledge points of students, and consequently the utilization efficiency of VR knowledge models is not high is solved, and the purposes that according to the mastery degree difference of the students for the knowledge points, the VR knowledge models are matched in a targeted mode to carry out personalized training display, and the use efficiency of the VR knowledge models is improved are achieved. And the VR practical training efficiency and the knowledge model utilization rate are improved.

Description

Technical Field

[0001] The present invention relates to the field of virtual reality technology, and in particular to a training course development method, system and platform combined with virtual reality. Background Art

[0002] With the development of virtual reality technology, introducing VR into practical training has become an important means to improve teaching effectiveness. In the prior art, the VR models corresponding to the relevant knowledge points of the practical training courses are generally pre-built and displayed uniformly during the teaching process. However, since VR scene generation requires high computing power, and the degree of mastery of knowledge points by different students in actual teaching varies greatly, it is difficult to take into account the learning needs of all students by using unified VR teaching content. Some VR knowledge models will not significantly improve students' learning effects, resulting in low efficiency in the use of VR teaching resources. Summary of the invention

[0003] The present invention aims to solve the technical problem that the VR practical training course display content in the prior art is unified and no personalized matching is performed for students' weak knowledge points, resulting in low efficiency in utilizing VR knowledge models. The present invention provides a practical training course development method, system and platform combined with virtual reality to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a training course development method combined with virtual reality, including: receiving a VR training course number selected by a user end, inputting the number into a knowledge base for indexing, and obtaining a first associated knowledge set, wherein the knowledge base is a database in which pre-configured knowledge is associated with the course number and stored; according to user identity information, traversing the first associated knowledge set to perform personal proficiency analysis, and obtaining a personal proficiency set, wherein the personal proficiency set corresponds one-to-one with the first associated knowledge set; according to user identity information, traversing the first associated knowledge set to perform learning portrait configuration, and obtaining a learning portrait set, wherein the learning portrait set corresponds one-to-one with the first associated knowledge set; traversing the learning portrait set and the first associated knowledge set to perform Perform group proficiency analysis to obtain a group proficiency set, wherein the group proficiency set corresponds one-to-one to the first associated knowledge set; according to the group proficiency set and the individual proficiency set, traverse the first associated knowledge set to perform weakness analysis to obtain a weakness coefficient set, wherein the weakness coefficient set corresponds one-to-one to the first associated knowledge set; based on the weakness coefficient set, filter a second associated knowledge set whose weakness coefficient is greater than or equal to the weakness coefficient threshold from the first associated knowledge set; according to the second associated knowledge set, match the associated VR knowledge model from the VR knowledge model library and send it to the user-side VR display device for practical training and learning, wherein the VR knowledge model library is a database for storing pre-configured VR knowledge models and knowledge associations.

[0006] In a second aspect, the present invention provides a training course development system combined with virtual reality, including: a course indexing module, which is used to receive the VR training course number selected by the user end, input the number into the knowledge base for indexing, and obtain a first associated knowledge set, wherein the knowledge base is a database in which pre-configured knowledge is associated with the course number and stored; a personal analysis module, which is used to traverse the first associated knowledge set according to the user identity information to perform personal proficiency analysis, and obtain a personal proficiency set, wherein the personal proficiency set corresponds one-to-one with the first associated knowledge set; a portrait configuration module, which is used to traverse the first associated knowledge set according to the user identity information to perform learning portrait configuration, and obtain a learning portrait set, wherein the learning portrait set corresponds one-to-one with the first associated knowledge set; a group analysis module, which is used to traverse the learning portrait set and the first associated knowledge set to perform learning portrait configuration, and obtain a learning portrait set, wherein the learning portrait set corresponds one-to-one with the first associated knowledge set; A group proficiency analysis is performed on the first associated knowledge set to obtain a group proficiency set, wherein the group proficiency set corresponds one-to-one to the first associated knowledge set; a weakness identification module is used to traverse the first associated knowledge set to perform weakness analysis according to the group proficiency set and the individual proficiency set to obtain a weakness coefficient set, wherein the weakness coefficient set corresponds one-to-one to the first associated knowledge set; a knowledge screening module is used to screen, from the first associated knowledge set, a second associated knowledge set whose weakness coefficient is greater than or equal to a weakness coefficient threshold based on the weakness coefficient set; a VR model matching module is used to match an associated VR knowledge model from a VR knowledge model library according to the second associated knowledge set and send it to a user-side VR display device for practical training and learning, wherein the VR knowledge model library is a database for storing pre-configured VR knowledge models and knowledge associations.

[0007] In a third aspect, the present application provides a practical training course development platform combined with virtual reality, including: a processor; a memory for storing processor executable instructions; wherein the processor is used to execute the practical training course development method combined with virtual reality provided in the present application.

[0008] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and the computer program is used to execute the training course development method combined with virtual reality provided by the present application.

[0009] The beneficial effects of the present invention are:

[0010] The VR training course number selected by the user is received, and the first associated knowledge set related to the course is obtained by indexing in a pre-configured knowledge base, thereby achieving the purpose of determining relevant knowledge points according to the course selected by the student; according to the user identity information, the first associated knowledge set is traversed to perform personal proficiency analysis and learning portrait configuration, and a personal proficiency set and a learning portrait set corresponding to the knowledge points are obtained, thereby achieving the analysis of the knowledge point mastery from the student's personal perspective; the learning portrait set and the first associated knowledge set are traversed to perform group proficiency analysis, and a group proficiency set corresponding to the knowledge points is obtained, thereby achieving the analysis of the knowledge point mastery from the group perspective; according to the group proficiency set and the personal proficiency set, the first associated knowledge set is traversed to perform weakness analysis, and a weakness coefficient set corresponding to the knowledge points is obtained, thereby achieving the calculation of the weakness of each knowledge point from both the individual and group perspectives; based on the weakness coefficient set, a second associated knowledge set with a weakness coefficient greater than or equal to a threshold is screened from the first associated knowledge set to determine the weak knowledge points that the student urgently needs to strengthen; according to the second associated knowledge set, the associated VR knowledge model is matched in the pre-configured VR knowledge model library, and sent to the student's VR device for key training learning, thereby achieving targeted strengthening of weak knowledge points.

[0011] By making full use of the associated configuration of the knowledge base and the VR knowledge model library, combining the analysis and comparison of the mastery of knowledge points by groups and individuals, and calculating the weakness of knowledge points, we can accurately identify the weaknesses of students' actual learning, and conduct personalized VR training matching and display, effectively improving the efficiency of VR training and the utilization rate of knowledge models. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flow chart of a method for developing a practical training course combined with virtual reality provided by the present invention;

[0013] Figure 2 A structural diagram of a practical training course development system combined with virtual reality provided by the present invention;

[0014] Figure 3 A schematic diagram of the structure of a practical training course development platform combined with virtual reality provided by the present invention;

[0015] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0016] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0017] Course index module 11, personal analysis module 12, portrait configuration module 13, group analysis module 14, weakness identification module 15, knowledge screening module 16, VR model matching module 17, practical training course development platform 200, memory 210, processor 220, first computer program 211, computer readable storage medium 300, second computer program 311. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0020] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0021] Embodiment 1:

[0022] like Figure 1 As shown, the embodiment of the present invention provides a training course development method combined with virtual reality, including:

[0023] S100: Receive the VR training course number selected by the user, input it into the knowledge base for indexing, and obtain a first associated knowledge set, wherein the knowledge base is a database that stores pre-configured knowledge in association with the course number.

[0024] Specifically, the user end provides a selection interface for VR training courses, which lists the optional course information. When the user selects a VR training course, the user end will generate a corresponding VR training course number. The VR training course number is the unique identifier of the course, which is used for subsequent knowledge retrieval in the knowledge base. The knowledge base is a pre-configured database that stores the correspondence between VR training course numbers and specific knowledge points. This correspondence is organized in the form of a data table, and each VR training course number can be associated with multiple knowledge points. For example, a VR training course number for CNC technology is associated with multiple knowledge points such as "safety operating procedures", "CNC code writing", and "processing technology".

[0025] After receiving the VR training course number, all knowledge points related to the number are retrieved in the knowledge base through a query operation. The retrieval process is implemented using a database query statement, taking the VR training course number as the query condition, traversing the association table in the knowledge base, and obtaining the first associated knowledge set. For example, when the VR training course number is "NC001", by searching the number in the knowledge base, a set containing multiple knowledge points, namely the first associated knowledge set, is obtained. Each knowledge point in this set is directly related to this course, providing basic data for subsequent learning analysis.

[0026] By pre-establishing and storing the correspondence between courses and knowledge points, course-related knowledge content can be quickly and accurately obtained, avoiding the workload of repeated retrieval and manual screening, while providing a reliable data foundation for subsequent personalized learning analysis.

[0027] S200: According to the user identity information, traverse the first associated knowledge set to perform personal proficiency analysis to obtain a personal proficiency set, wherein the personal proficiency set corresponds to the first associated knowledge set one by one.

[0028] Specifically, the user identity information includes the user's unique identification code, learning records and other data. Traversing the first associated knowledge set means reading each knowledge point in the set one by one. For each knowledge point, personal proficiency analysis is performed in combination with the user identity information to obtain the user's mastery level of the knowledge point.

[0029] For each knowledge point in the first associated knowledge set, the assessment data related to the knowledge point is extracted from the user's historical assessment records. By statistically analyzing these assessment data, the user's personal proficiency value for the knowledge point is calculated, reflecting the user's actual mastery of the knowledge point. For example, when the first associated knowledge set contains the knowledge point of "CNC machine tool operation steps", the user's performance records on this knowledge point in past assessments are searched, and the user's accuracy rate in related test questions and practical assessments is analyzed to obtain a value representing proficiency. The personal proficiency set is the final result of the traversal analysis, which stores the user's personal proficiency value for each knowledge point in the first associated knowledge set. This set corresponds one-to-one to the knowledge points in the first associated knowledge set, that is, each knowledge point has a corresponding personal proficiency value.

[0030] By obtaining a set of personal proficiency that characterizes the user's mastery of each knowledge point, it is possible to accurately quantify the user's actual mastery level of each knowledge point, providing a key basis for subsequent identification of weak knowledge points and personalized VR content push, thereby improving the pertinence and efficiency of VR training.

[0031] S300: According to the user identity information, traverse the first associated knowledge set to configure a learning portrait, and obtain a learning portrait set, wherein the learning portrait set corresponds one-to-one to the first associated knowledge set.

[0032] Specifically, first, obtain the basic user portrait, including two basic dimensions: user education history and user age. User education history reflects the user's learning background, including information such as education level and professional direction, and user age is used as a reference indicator of learning ability. Subsequently, in the process of traversing the first associated knowledge set, for each knowledge point, the historical learning frequency of the corresponding knowledge point of the user is retrieved based on the user identity information. The historical learning frequency reflects the frequency of the user's exposure to the knowledge point in the past learning process. This data can characterize the user's familiarity with the knowledge point. For example, when the knowledge point "Basics of CNC Programming" exists in the first associated knowledge set, extract the number of times and duration of the user's past learning of the knowledge point, and comprehensively calculate the historical learning frequency. For each knowledge point, the three data items of user education history, user age and historical learning frequency are combined to form a learning portrait of the knowledge point. This portrait describes the learning characteristics of the user at this knowledge point. The learning portraits of all knowledge points together constitute a learning portrait set.

[0033] By combining basic user characteristics and learning behavior data, a multi-dimensional learning feature description is constructed, which provides a reliable classification basis for subsequent group proficiency analysis and helps to more accurately identify user groups with similar learning characteristics.

[0034] S400: traverse the learning portrait set and the first associated knowledge set to perform group proficiency analysis to obtain a group proficiency set, wherein the group proficiency set corresponds one-to-one to the first associated knowledge set.

[0035] Specifically, the learning portrait set and the first associated knowledge set are traversed, and the overall mastery level of each knowledge point is evaluated by comparing user groups with similar learning characteristics.

[0036] When traversing the learning portrait set, for the learning portrait of each knowledge point in the first associated knowledge set, first extract the characteristic data such as user education history, user age and historical learning frequency contained therein. These characteristic data are used as screening conditions to find user groups with similar learning characteristics. Then, use the extracted characteristic data as the retrieval condition to perform group screening, screen out user sets that are relatively close in terms of education background, age group and learning frequency, and count the mastery of this knowledge point by all users in the user set to obtain the group proficiency of this knowledge point. For example, for the knowledge point of "Basics of CNC Programming", screen out user groups with similar mechanical professional backgrounds, similar age groups, and similar learning investment levels, count the assessment performance of the user group on this knowledge point, and obtain the group proficiency of "Basics of CNC Programming". Subsequently, the group proficiency of each knowledge point is summarized to obtain a group proficiency set.

[0037] By obtaining the group proficiency set of user groups with similar learning characteristics, we can accurately evaluate the overall mastery level of user groups with similar learning characteristics on various knowledge points, provide important reference data for subsequent personalized learning analysis, and help better identify users' learning differences.

[0038] S500: According to the group proficiency set and the individual proficiency set, traverse the first associated knowledge set to perform weakness analysis to obtain a weakness coefficient set, wherein the weakness coefficient set corresponds one-to-one to the first associated knowledge set.

[0039] Specifically, by analyzing and comparing individual proficiency and group proficiency, we can find out the weak links in users' mastery of knowledge points, and provide a basis for the screening of key knowledge points in VR training.

[0040] First, for each knowledge point in the first associated knowledge set, the corresponding individual proficiency value and group proficiency value are extracted from the individual proficiency set and the group proficiency set. Then, the individual proficiency value and the group proficiency value are input into the pre-trained weakness analysis model, which evaluates the mastery level of the knowledge point according to the individual proficiency and the group proficiency, and obtains the weakness coefficient of the corresponding knowledge point. Specifically, first, a batch of sample data is extracted from the historical learning record database, each sample contains knowledge points, individual proficiency, group proficiency and the manually marked weakness of the knowledge point; then, a machine learning algorithm, such as logistic regression, decision tree, neural network, etc., is selected to construct a weakness analysis model, and the processed sample data is randomly divided into a training set and a test set, and the training set data is used to train and optimize the model, and the test set data is used to evaluate the generalization performance of the model. By repeatedly adjusting the model parameters, optimizing the objective function, etc., the prediction accuracy of the model is continuously improved; after training and optimization, a mature weakness analysis model is obtained. The input of the model is the knowledge point and the corresponding two features of individual proficiency and group proficiency. The output is a weakness coefficient between 0 and 1. The closer the weakness coefficient is to 1, the weaker the knowledge point is for the user. In practical applications, the individual proficiency and group proficiency of each knowledge point are extracted from the individual proficiency set and the group proficiency set, and input into the trained weakness analysis model to obtain the corresponding weakness coefficient, and finally summarize to obtain the weakness coefficient set.

[0041] By constructing a weakness analysis model, a comprehensive analysis of individual learning situations and group learning trends is achieved. The targeted reinforcement needs of each knowledge point for users are quantified in the form of predicted values ​​of the weakness of knowledge points, providing a direct basis for the screening of subsequent VR training knowledge points.

[0042] S600: Based on the weak coefficient set, a second associated knowledge set having a weak coefficient greater than or equal to a weak coefficient threshold is selected from the first associated knowledge set.

[0043] Specifically, after obtaining the weak coefficient set, according to the preset weak coefficient threshold, key knowledge points with targeted significance for user learning are screened out from the first associated knowledge set to form a second associated knowledge set, so as to prepare for the generation of subsequent VR training content.

[0044] First, set the weak coefficient threshold. This threshold can be determined based on historical learning data and teaching practice experience, and represents a critical value of the degree of weakness of the knowledge point. When the weak coefficient of a certain knowledge point is greater than or equal to the threshold, it is considered that the user has obvious learning weaknesses in this knowledge point, and needs to be strengthened through VR training. Then, traverse each weak coefficient in the weak coefficient set and compare it with the weak coefficient threshold. If the weak coefficient is greater than or equal to the weak coefficient threshold, the knowledge point corresponding to the weak coefficient is extracted from the first associated knowledge set and added to the second associated knowledge set; if the weak coefficient is less than the weak coefficient threshold, it means that the user has mastered this knowledge point more proficiently, and it is temporarily not the focus of VR training, and is removed from the first associated knowledge set. When all the knowledge points in the first associated knowledge set are screened as above, a complete second associated knowledge set is obtained. The size of this set is less than or equal to the first associated knowledge set, and only contains knowledge points where the user has obvious weaknesses in learning. Compared with the first associated knowledge set, the second associated knowledge set focuses more on learning weaknesses and can guide VR training to generate more targeted teaching content. For example, assuming that the first associated knowledge set contains knowledge points A, B, C, and D, and its corresponding weakness coefficient set is [0.3, 0.8, 0.5, 0.9], and the weakness coefficient threshold is set to 0.6, the second associated knowledge set obtained after screening is {B, D}, that is, the weakness coefficients of knowledge points B and D reach or exceed the threshold, and need to be strengthened in VR training.

[0045] By using the weakness coefficient threshold to filter the first associated knowledge set, we obtain the second associated knowledge set that focuses on the user's learning weaknesses, providing a more accurate and efficient knowledge point range for subsequent VR training content generation. While improving the targeted learning, it can also reduce unnecessary waste of computing resources.

[0046] S700: According to the second associated knowledge set, matching associated VR knowledge models from a VR knowledge model library is sent to a user-side VR display device for practical training and learning, wherein the VR knowledge model library is a database for storing pre-configured VR knowledge models and knowledge associations.

[0047] Specifically, after obtaining the second associated knowledge set, the VR knowledge model corresponding to each knowledge point in the second associated knowledge set is matched and extracted from the pre-built VR knowledge model library, and sent to the VR display device on the user side for the user to carry out targeted VR training and learning.

[0048] First, access the pre-built VR knowledge model library. The model library is a database that stores a large number of VR knowledge models, each of which is associated with one or more knowledge points. These VR knowledge models are various types of VR teaching content, such as VR teaching scenes, VR experimental operations, VR concept demonstrations, etc. Through vivid and realistic VR technical means, abstract knowledge points are transformed into intuitive sensory experiences, which are convenient for students to understand and master. Then, traverse each knowledge point in the second associated knowledge set and perform matching queries in the VR knowledge model library. By comparing the association relationship between the knowledge point and the VR knowledge model, one or more VR knowledge models corresponding to the current knowledge point are extracted from the VR knowledge model library.

[0049] Next, the VR knowledge model extracted by matching is sent to the VR display device on the user side through network transmission. The VR display device can be a terminal device with VR display function, such as a VR headset, a VR all-in-one machine, a smart phone, etc. After that, the user accesses and browses the VR knowledge model sent from the server side through the VR display device, and conducts VR practical training and learning for their weak knowledge points. With the immersive and interactive characteristics of the VR model, users can directly observe the concrete display of knowledge points in the virtual environment, and operate the experimental steps related to the knowledge points to obtain an immersive learning experience, thereby deepening their understanding and mastery of weak knowledge points.

[0050] By utilizing the pre-built VR knowledge model library, corresponding VR teaching content is generated for matching the weak knowledge points in the second related knowledge set, and the content is sent to the user end for display, so that users can carry out targeted immersive VR learning, significantly improve students' learning effects on weak knowledge points, and improve the utilization efficiency of VR teaching resources.

[0051] Furthermore, the embodiment of the present application also includes:

[0052] S210: extracting first associated knowledge from the first associated knowledge set;

[0053] S220: Retrieving a first historical assessment record data set including the first associated knowledge according to the user identity information;

[0054] S230: Counting the percentage of the first related knowledge in the first historical assessment record data set that is correctly determined, and setting it as the personal proficiency of the first related knowledge;

[0055] S240: Add the first associated knowledge personal proficiency into the personal proficiency set.

[0056] In a feasible implementation, first, knowledge points are extracted one by one from the first associated knowledge set as the first associated knowledge. The first associated knowledge is one of the elements of the first associated knowledge set, representing a knowledge point that is closely related to the course currently being studied by the user. Then, based on the user's identity information, the first historical assessment record data set containing the first associated knowledge of the user is retrieved from the learning record database. The user identity information may be identification information such as the user's unique ID, name, and student number. The first historical assessment record data set contains all the user's learning record data such as tests, exercises, and exams involving the first associated knowledge in the past period of time, reflecting the user's learning and mastery of the first associated knowledge.

[0057] Subsequently, a statistical analysis is performed on the first historical assessment record data set to determine whether the user's answer to the first related knowledge in each historical assessment record is correct, and the proportion of the number of records with correct answers to the total number of records is calculated. This ratio value is the user's personal proficiency in the first related knowledge, which quantitatively represents the user's mastery of the knowledge point. The higher the personal proficiency, the more accurately the user can apply the knowledge point in past learning and the more solid the mastery. Afterwards, the calculated personal proficiency of the first related knowledge is added to the personal proficiency set. The personal proficiency set is a set with the same structure and equal size as the first related knowledge set, which is used to store the user's personal proficiency for each related knowledge point. Whenever the personal proficiency of a knowledge point is calculated, it is added to the corresponding position of the set to ensure that the personal proficiency corresponds to the knowledge point one by one.

[0058] By analyzing the user's personal proficiency in the first associated knowledge, after traversing all knowledge points in the first associated knowledge set, a complete personal proficiency set is obtained, which comprehensively reflects the user's personal mastery of the current knowledge points learned, and provides individual dimension data support for subsequent group proficiency analysis, weak knowledge point determination and other steps.

[0059] Furthermore, the embodiment of the present application also includes:

[0060] S310: Obtaining a basic user portrait, wherein the basic user portrait includes the user's education history and the user's age;

[0061] S320: extracting first associated knowledge from the first associated knowledge set;

[0062] S330: Retrieving the historical learning frequency of the first associated knowledge according to the user identity information;

[0063] S340: Add the user's education history, the user's age and the historical learning frequency into the first associated knowledge learning portrait, and add it into the learning portrait set.

[0064] In a feasible implementation, by obtaining the learning portrait of the user at each knowledge point in the first associated knowledge set, a learning portrait set corresponding to each knowledge point is formed. The learning portrait is a comprehensive description of the characteristic attributes exhibited by the user in the learning process of a certain knowledge point. The learning portrait can be used to analyze the user's learning characteristics in a more three-dimensional manner.

[0065] First, obtain the basic user portrait. The basic user portrait is a feature that describes the basic learning attributes of the user, including the user's education history and the user's age. Among them, the user's education history reflects the user's educational level, professional background and other basic learning conditions, and the user's age reflects the user's cognitive ability, learning acceptance and other physiological characteristics. By obtaining the basic user portrait, the user's learning characteristics can be grasped from a macro level. Then, the knowledge points are extracted one by one from the first associated knowledge set as the first associated knowledge. Subsequently, according to the user's identity information, the user's historical learning frequency on the first associated knowledge is retrieved from the learning record database. The historical learning frequency reflects the frequency of the user's learning of the first associated knowledge in the past period of time, indicating the user's learning investment in the knowledge point, and is obtained by counting the number of times the user visits the learning resources related to the knowledge point and the number of times the user completes the related exercises of the knowledge point. Afterwards, the three attributes of the user's education history, user age and the first associated knowledge historical learning frequency are summarized to form the user's learning portrait on the first associated knowledge, and the learning portrait is added to the learning portrait set. The learning portrait set is a set with the same structure and size as the first associated knowledge set, which is used to store the user's learning portrait on each associated knowledge point. Whenever a learning portrait of a knowledge point is constructed, it is added to the corresponding position of the collection to ensure that the learning portrait corresponds to the knowledge point one by one.

[0066] After traversing all the knowledge points in the first associated knowledge set, a complete learning portrait set is obtained. The learning portrait set describes the user's learning characteristics at each knowledge point from multiple dimensions such as educational background, age characteristics, and learning behavior. These portrait data complement each other with personal proficiency data and together constitute a comprehensive description of the user's learning status, providing a data foundation for subsequent group learning analysis, personalized learning guidance and other applications.

[0067] Furthermore, the embodiment of the present application also includes:

[0068] S410: extracting the first associated knowledge learning portrait from the learning portrait set, wherein the first associated knowledge learning portrait includes the user's education history, the user's age, and the historical learning frequency;

[0069] S420: taking the user's education history, the user's age and the historical learning frequency as portrait constraints, collecting a second historical assessment record data set including the first associated knowledge for the first-level same-cluster portrait user;

[0070] S430: Using the first-level cluster portrait as a portrait constraint, collecting a third historical assessment record data set of the second-level cluster portrait users including the first associated knowledge

[0071] S440: Counting the percentage of the first associated knowledge in the third historical assessment record data set that is correctly determined, and setting it as the second-level group proficiency of the first associated knowledge;

[0072] S450: Counting the percentage of the first associated knowledge that is correctly determined in the second historical assessment record data set, and setting it as the first-level group proficiency of the first associated knowledge;

[0073] S460: Calculate the average of the second-level group proficiency of the first associated knowledge and the first-level group proficiency of the first associated knowledge, set it as the first associated knowledge group proficiency, and add it to the group proficiency set.

[0074] In a preferred embodiment, based on the learning profile set and the first associated knowledge set, a group proficiency set is obtained by analyzing the overall mastery of each knowledge point by a group with similar learning characteristics to the target user. Compared with individual proficiency, group proficiency can more comprehensively and objectively evaluate the difficulty and degree of mastery of knowledge points.

[0075] First, the learning portrait of the first associated knowledge is extracted from the learning portrait set as the learning portrait of the first associated knowledge. The learning portrait of the first associated knowledge contains three attributes: user education history, user age and historical learning frequency, which describes the learning characteristics of the target user on the first associated knowledge. Then, with the user education history, user age and historical learning frequency in the learning portrait of the first associated knowledge as constraints, a group of users with similar learning characteristics to the target user are collected from the learning record database, who are similar to the target user in age, education background and learning behavior, as the first-level cluster portrait users. The historical assessment data of the first-level cluster portrait users on the first associated knowledge are extracted and summarized to form a second historical assessment record data set. This data set reflects the assessment performance of a group of users with similar learning characteristics to the target user on the first associated knowledge. In order to further expand the scope of reference users and improve the representativeness of group proficiency, based on the first-level cluster portrait users, users with similar learning characteristics to the first-level cluster portrait users are collected, who are similar to the first-level cluster portrait users in age, education background and learning behavior, as the second-level cluster portrait users. At the same time, the historical assessment data of the second-level cluster portrait users on the first associated knowledge are extracted and summarized to form the third historical assessment record data set.

[0076] Afterwards, the third historical assessment record data set is statistically analyzed to determine whether the second-level clustered profile users have answered the first related knowledge correctly in each historical assessment record, and the proportion of the number of records with correct answers to the total number of records is calculated. This proportion value is the second-level group proficiency of the first related knowledge, which evaluates the overall mastery of the first related knowledge by the group with similar learning characteristics to the target user from the perspective of a larger sample. Similarly, the second historical assessment record data set is statistically analyzed to calculate the proportion of the first-level user group answering correctly on the first related knowledge, and the first-level group proficiency of the first related knowledge is obtained, which reflects the overall mastery of the first related knowledge by the group with the closest learning characteristics to the target user. Afterwards, the group proficiency at the first and second levels is comprehensively considered, and the arithmetic mean of the two is calculated to obtain the group proficiency of the first related knowledge, and it is added to the group proficiency set. The group proficiency set is a set with the same structure and size as the first related knowledge set, which is used to store the group proficiency of each related knowledge point. Whenever the group proficiency of a knowledge point is calculated, it is added to the corresponding position of the set to ensure that the group proficiency corresponds to the knowledge point one by one.

[0077] Based on the personal learning portrait, we build primary and secondary cluster groups with similar learning characteristics to the target users, conduct a group assessment of the knowledge points, and obtain the group proficiency. After traversing all the knowledge points, a complete group proficiency set is formed, which provides a more scientific and comprehensive basis for the subsequent judgment of weak knowledge points and the push of VR training resources.

[0078] Furthermore, the embodiment of the present application also includes:

[0079] S510: Processing the first associated knowledge group proficiency and the first associated knowledge individual proficiency of the first associated knowledge through a weight distribution network to obtain a first group proficiency weight and a first individual proficiency weight;

[0080] S520: Constructing a weak coefficient evaluation function:

[0081] f(x1, x2) = w1log a x1+w2log a x2

[0082] Among them, x1 represents individual proficiency, x2 represents group proficiency, w1 represents individual proficiency weight, w2 represents group proficiency weight, a represents adjustment factor, 0<a<1, f(x1, x2) represents the coefficient of weak associated knowledge;

[0083] S530: According to the weakness coefficient evaluation function, a weakness coefficient analysis is performed on the first group proficiency weight, the first individual proficiency weight, the first associated knowledge group proficiency and the first associated knowledge individual proficiency to obtain a first associated knowledge weakness coefficient, and add it to the weakness coefficient set.

[0084] In a preferred embodiment, the two factors of group proficiency and individual proficiency are comprehensively considered to quantitatively evaluate the weakness of each associated knowledge point for the target user and generate a set of weakness coefficients. The weights of individual and group factors are determined by using a weight distribution network, a weakness coefficient evaluation function is introduced, and a weakness analysis mechanism is established.

[0085] First, for the first associated knowledge point, the group proficiency data and individual proficiency data of the knowledge point are extracted from the group proficiency set and the individual proficiency set, namely the first associated knowledge group proficiency and the first associated knowledge individual proficiency, and input into the weight distribution network for processing. The weight distribution network is a pre-trained neural network model that can learn the relative importance of individual factors and group factors to the level of knowledge mastery. Through network calculation, the weight coefficient of the first associated knowledge group proficiency and the weight coefficient of the first associated knowledge individual proficiency are obtained, which are recorded as the first group proficiency weight and the first individual proficiency weight respectively. The sum of these two weight coefficients is 1, which reflects the comparison of the influence of individual and group factors.

[0086] Then, the weak coefficient evaluation function is constructed as: f(x1, x2) = w1log a x1+w2log a x2. This function uses a double logarithmic weighting form, with individual proficiency and group proficiency as independent variables, individual proficiency weight and group proficiency weight as corresponding weight coefficients, and log takes a as the base (0<a<1). The two components are weighted and summed to obtain the weakness coefficient f(x1, x2). Among them, the independent variable x1 represents individual proficiency, and the independent variable x2 represents group proficiency; the weight w1 represents the individual proficiency weight, and w2 represents the group proficiency weight; a is the adjustment factor, and its value is between 0 and 1. Through logarithmic transformation, this function amplifies the low value range of the independent variable, making the evaluation result more sensitive to the low value of proficiency, and can more prominently reflect the weakness of the knowledge point.

[0087] Afterwards, using the constructed weakness coefficient evaluation function, the first associated knowledge group proficiency, the first associated knowledge individual proficiency, and the corresponding first group proficiency weight and first individual proficiency weight of the first associated knowledge are substituted into the weakness coefficient evaluation function for calculation, and the weakness coefficient of the knowledge point, that is, the first associated knowledge point weakness coefficient, can be obtained. The generated weakness coefficient is a value between 0 and 1. The closer it is to 1, the weaker the target user's mastery of the knowledge point is, and the more it needs to be strengthened through VR training.

[0088] By traversing all knowledge points in the first associated knowledge set and executing repeatedly, a set of weak coefficients corresponding to each knowledge point can be obtained. This set combines the two evaluation dimensions of individual absolute level and group relative level. The weak degree is reasonably quantified through the design of weighted logarithmic function, which can be used as a direct basis for screening VR training knowledge points. Compared with a single individual proficiency or group proficiency, the weak coefficient can more comprehensively and accurately identify the knowledge points that target users need to focus on most.

[0089] Furthermore, the embodiment of the present application also includes:

[0090] S511: Configuring a group proficiency record data set and an individual proficiency record data set;

[0091] S512: Perform subjective weight distribution based on the group proficiency record data set and the individual proficiency record data set to obtain a group proficiency weight identification data set and an individual proficiency weight identification data set;

[0092] S513: Using the group proficiency weight identification dataset and the individual proficiency weight identification dataset as supervision, and using the group proficiency record dataset and the individual proficiency record dataset as input, train a BP neural network to generate the weight distribution network.

[0093] In a preferred embodiment, in order to construct a weight distribution network, first, a batch of user learning records are extracted from the historical learning database, and the group proficiency data and individual proficiency data therein are summarized and sorted to form two data sets, respectively, to obtain a group proficiency record data set and an individual proficiency record data set. Among them, each record of the group proficiency record data set contains the group proficiency value of a knowledge point, and each record of the individual proficiency record data set contains the individual proficiency value of a user at a certain knowledge point. Then, on the basis of the obtained group proficiency record data set and the individual proficiency record data set, an educational expert is invited to mark each of the records with a subjective weight. That is, the expert subjectively judges the relative importance of group proficiency and individual proficiency in each record based on his or her own teaching experience and understanding of the learning process, and gives the weight coefficients of the two proficiencies. For example, for a certain record, if the expert believes that the group factor is dominant, a larger group proficiency weight coefficient, such as 0.8, can be given, and the individual proficiency weight coefficient is 0.2. By marking all records in the two data sets, a group proficiency weight identification data set and an individual proficiency weight identification data set corresponding to the original data set can be obtained. Subsequently, BP neural network was selected as the basic structure of the weight distribution network. BP neural network has strong nonlinear fitting ability. Through back propagation algorithm training, it can automatically learn the complex mapping relationship from input to output. With group proficiency record data set and individual proficiency record data set as input, and corresponding group proficiency weight identification data set and individual proficiency weight identification data set as expected output, through repeated iterations, the network parameters are adjusted and optimized to obtain BP neural network, which provides support for weak coefficient analysis.

[0094] Furthermore, the embodiment of the present application also includes:

[0095] S5121: Send the group proficiency record data set, the first group proficiency record data of the individual proficiency record data set, and the first individual proficiency record data to a plurality of importance evaluation nodes whose information is independent of each other, to obtain a plurality of group proficiency importance scores and a plurality of individual proficiency importance scores;

[0096] S5122: Add the plurality of group proficiency importance scores and the plurality of individual proficiency importance scores to obtain a total importance score;

[0097] S5123: Add the plurality of group proficiency importance scores to obtain a total group proficiency importance score;

[0098] S5124: Add the individual proficiency importance scores to obtain the sum of the individual proficiency importance scores;

[0099] S5125: Calculate the ratio of the sum of the group proficiency importance scores to the sum of the importance scores, and set it as the first group proficiency weight identification data;

[0100] S5126: Calculate the ratio of the sum of the individual proficiency importance scores to the sum of the importance scores, and set it as the first individual proficiency weight identification data.

[0101] In a preferred embodiment, first, the first group proficiency record data is taken from the group proficiency record data set, and the first individual proficiency record data is taken from the individual proficiency record data set, and these two record data are sent to several importance evaluation nodes. Each importance evaluation node represents an expert user, and each importance evaluation node is independent of each other and cannot exchange information or influence each other. Each expert gives a group proficiency importance score and an individual proficiency importance score to the two received record data according to his own judgment. The score range is 1 to 10 points, and the higher the score, the more important the proficiency is considered. Then, the score data returned by all importance evaluation nodes are collected, the group proficiency importance scores given by all nodes are summed up, and the individual proficiency importance scores given by all nodes are summed up. The sum of the two is obtained to obtain the sum of importance scores, which reflects the judgment of all experts on the overall importance of the two types of proficiency.

[0102] Subsequently, the group proficiency importance scores given by all nodes are summed up separately to obtain the sum of group proficiency importance scores, which reflects the overall judgment of all experts on the importance of group proficiency. At the same time, the individual proficiency importance scores given by all nodes are summed up separately to obtain the sum of individual proficiency importance scores, which reflects the overall judgment of all experts on the importance of individual proficiency. Afterwards, the ratio of the sum of group proficiency importance scores to the sum of importance scores is calculated, and it is used as the group proficiency weight identification data corresponding to the first group proficiency record, that is, the first group proficiency weight identification data, which reflects the importance of group proficiency, and the value is between 0 and 1. At the same time, the ratio of the sum of individual proficiency importance scores to the sum of importance scores is calculated, and it is used as the individual proficiency weight identification data corresponding to the first individual proficiency record, that is, the first individual proficiency weight identification data, which reflects the importance of individual proficiency, and the value is between 0 and 1. The sum of the individual proficiency weight and the group proficiency weight is always equal to 1.

[0103] By performing weight distribution determination on each record in the group proficiency record dataset and the individual proficiency record dataset, we obtain a group proficiency weight identification dataset and an individual proficiency weight identification dataset that correspond one-to-one to the two original datasets, providing high-quality label data for subsequent training of the weight distribution network.

[0104] The practical training course development method combined with virtual reality provided by the embodiment of the present invention has at least the following technical effects:

[0105] Receive the VR training course number selected by the user end, input it into the knowledge base for indexing, and obtain the first associated knowledge set, wherein the knowledge base is a database that stores pre-configured knowledge in association with the course number, laying the foundation for the subsequent analysis of students' mastery of these knowledge points. According to the user identity information, traverse the first associated knowledge set to perform personal proficiency analysis and obtain a personal proficiency set, wherein the personal proficiency set corresponds one-to-one with the first associated knowledge set, so as to evaluate the knowledge mastery from an individual perspective. According to the user identity information, traverse the first associated knowledge set to perform learning portrait configuration and obtain a learning portrait set, wherein the learning portrait set corresponds one-to-one with the first associated knowledge set, providing a basis for more learning characteristics for the subsequent analysis of students' weak knowledge points. Traverse the learning portrait set and the first associated knowledge set to perform group proficiency analysis and obtain a group proficiency set, wherein the group proficiency set corresponds one-to-one with the first associated knowledge set, so as to evaluate the knowledge mastery from a group perspective. According to the group proficiency set and the individual proficiency set, the first associated knowledge set is traversed to perform weakness analysis to obtain a weakness coefficient set, wherein the weakness coefficient set corresponds to the first associated knowledge set one by one, and evaluates whether the student's mastery of each knowledge point is weak. Based on the weakness coefficient set, a second associated knowledge set with a weakness coefficient greater than or equal to the weakness coefficient threshold is screened from the first associated knowledge set to determine the student's key weak knowledge points. According to the second associated knowledge set, the associated VR knowledge model is matched from the VR knowledge model library and sent to the user-side VR display device for practical training and learning, wherein the VR knowledge model library is a database for storing pre-configured VR knowledge models and knowledge associations, so as to achieve the purpose of strengthening training on students' weak knowledge points and help students improve their mastery of weak knowledge points. By constructing an association mechanism between the knowledge base and the VR knowledge model library, the identification of students' weak knowledge points and VR training are organically combined to achieve targeted training, thereby achieving the purpose of improving VR resource utilization efficiency and student learning effects.

[0106] Embodiment 2:

[0107] like Figure 2 As shown, based on the same inventive concept of the practical training course development method combined with virtual reality provided in Embodiment 1, the embodiment of the present invention also provides a practical training course development system combined with virtual reality, including:

[0108] The course indexing module 11 is used to receive the VR training course number selected by the user end, input it into the knowledge base for indexing, and obtain a first associated knowledge set, wherein the knowledge base is a database in which pre-configured knowledge is associated with the course number and stored;

[0109] A personal analysis module 12, configured to traverse the first associated knowledge set to perform personal proficiency analysis according to user identity information to obtain a personal proficiency set, wherein the personal proficiency set corresponds to the first associated knowledge set one by one;

[0110] A portrait configuration module 13, configured to traverse the first associated knowledge set to configure a learning portrait according to the user identity information, and obtain a learning portrait set, wherein the learning portrait set corresponds to the first associated knowledge set in a one-to-one manner;

[0111] A group analysis module 14, configured to traverse the learning profile set and the first associated knowledge set to perform group proficiency analysis to obtain a group proficiency set, wherein the group proficiency set corresponds one-to-one to the first associated knowledge set;

[0112] A weakness identification module 15 is used to traverse the first associated knowledge set to perform weakness analysis according to the group proficiency set and the individual proficiency set to obtain a weakness coefficient set, wherein the weakness coefficient set corresponds to the first associated knowledge set in a one-to-one manner;

[0113] A knowledge screening module 16, configured to screen, based on the weak coefficient set, a second associated knowledge set having a weak coefficient greater than or equal to a weak coefficient threshold from the first associated knowledge set;

[0114] The VR model matching module 17 is used to match the associated VR knowledge model from the VR knowledge model library according to the second associated knowledge set and send it to the user-side VR display device for practical training and learning, wherein the VR knowledge model library is a database for storing pre-configured VR knowledge models and knowledge associations.

[0115] Furthermore, the personal analysis module 12 includes the following execution steps:

[0116] Extracting first associated knowledge from the first associated knowledge set;

[0117] Retrieving a first historical assessment record data set including the first associated knowledge according to the user identity information;

[0118] Counting the percentage of the first related knowledge that is correctly judged in the first historical assessment record data set, and setting it as the personal proficiency of the first related knowledge;

[0119] The first associated knowledge personal proficiency is added to the personal proficiency set.

[0120] Furthermore, the portrait configuration module 13 includes the following execution steps:

[0121] Obtaining a basic user profile, wherein the basic user profile includes the user's education history and the user's age;

[0122] Extracting first associated knowledge from the first associated knowledge set;

[0123] Retrieving the historical learning frequency including the first associated knowledge according to the user identity information;

[0124] The user's educational history, the user's age and the historical learning frequency are added to the first associated knowledge learning portrait, and added to the learning portrait set.

[0125] Furthermore, the group analysis module 14 includes the following execution steps:

[0126] Extracting the first associated knowledge learning portrait from the learning portrait set, wherein the first associated knowledge learning portrait includes the user's education history, the user's age, and the historical learning frequency;

[0127] Taking the user's education history, the user's age and the historical learning frequency as profile constraints, collecting a second historical assessment record data set of the first-level cluster profile users including the first associated knowledge;

[0128] Using the first-level cluster portrait as a portrait constraint, collect the third historical assessment record data set of the second-level cluster portrait users including the first associated knowledge

[0129] Counting the percentage of the first associated knowledge that is correctly determined in the third historical assessment record data set, and setting it as the second-level group proficiency of the first associated knowledge;

[0130] Counting the percentage of the first associated knowledge that is correctly judged in the second historical assessment record data set, and setting it as the first-level group proficiency of the first associated knowledge;

[0131] The average of the second-level group proficiency of the first associated knowledge and the first-level group proficiency of the first associated knowledge is calculated, set as the first associated knowledge group proficiency, and added into the group proficiency set.

[0132] Furthermore, the weakness identification module 15 includes the following execution steps:

[0133] Processing the first associated knowledge group proficiency and the first associated knowledge individual proficiency of the first associated knowledge through a weight distribution network to obtain a first group proficiency weight and a first individual proficiency weight;

[0134] Construct a weakness coefficient evaluation function:

[0135] f(x1, x2) = w1log a x1+w2log a x2

[0136] Among them, x1 represents individual proficiency, x2 represents group proficiency, w1 represents individual proficiency weight, w2 represents group proficiency weight, a represents adjustment factor, 0<a<1, f(x1, x2) represents the coefficient of weak associated knowledge;

[0137] According to the weakness coefficient evaluation function, a weakness coefficient analysis is performed on the first group proficiency weight, the first individual proficiency weight, the first associated knowledge group proficiency and the first associated knowledge individual proficiency to obtain a first associated knowledge weakness coefficient, which is added to the weakness coefficient set.

[0138] Furthermore, the weakness identification module 15 further includes the following execution steps:

[0139] Configure group proficiency record data set and individual proficiency record data set;

[0140] Performing subjective weight distribution based on the group proficiency record data set and the individual proficiency record data set to obtain a group proficiency weight identification data set and an individual proficiency weight identification data set;

[0141] The group proficiency weight identification dataset and the individual proficiency weight identification dataset are used as supervision, and the group proficiency record dataset and the individual proficiency record dataset are used as input to train a BP neural network to generate the weight distribution network.

[0142] Furthermore, the weakness identification module 15 further includes the following execution steps:

[0143] Sending the group proficiency record data set, the first group proficiency record data of the individual proficiency record data set, and the first individual proficiency record data to a plurality of importance evaluation nodes whose information is independent of each other, to obtain a plurality of group proficiency importance scores and a plurality of individual proficiency importance scores;

[0144] Adding the plurality of group proficiency importance scores and the plurality of individual proficiency importance scores to obtain a total importance score;

[0145] Adding the plurality of group proficiency importance scores to obtain a total group proficiency importance score;

[0146] Adding the individual proficiency importance scores to obtain a total of the individual proficiency importance scores;

[0147] Calculate the ratio of the sum of the group proficiency importance scores to the sum of the importance scores, and set it as the first group proficiency weight identification data;

[0148] The ratio of the sum of the individual proficiency importance scores to the sum of the importance scores is calculated and set as the first individual proficiency weight identification data.

[0149] Embodiment three:

[0150] See also Figure 3 , Figure 3 Schematic diagram of an embodiment of a training course development platform combined with virtual reality provided by an embodiment of the present invention. Figure 3 As shown, the practical training course development platform 200 provided in an embodiment of the present invention includes a memory 210, a processor 220, and a first computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the first computer program 211, a practical training course development method combined with virtual reality is implemented.

[0151] Embodiment 4:

[0152] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 300 on which a second computer program 311 is stored. When the second computer program 311 is executed by a processor, a training course development method combined with virtual reality is implemented.

[0153] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0154] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0155] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0156] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0158] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0159] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technology, the present invention is also intended to include these changes and variations.

Claims

1. A training course development method combining virtual reality, characterized in that: include: Receive the VR training course number selected by the user, input it into the knowledge base for indexing, and obtain a first associated knowledge set, wherein the knowledge base is a database in which pre-configured knowledge is associated with the course number and stored; According to the user identity information, traverse the first associated knowledge set to perform personal proficiency analysis to obtain a personal proficiency set, wherein the personal proficiency set corresponds to the first associated knowledge set in one-to-one correspondence; According to the user identity information, traverse the first associated knowledge set to perform learning profile configuration to obtain a learning profile set, wherein the learning profile set corresponds to the first associated knowledge set in a one-to-one manner; Traversing the learning profile set and the first associated knowledge set to perform group proficiency analysis to obtain a group proficiency set, wherein the group proficiency set corresponds to the first associated knowledge set one by one; According to the group proficiency set and the individual proficiency set, traverse the first associated knowledge set to perform weakness analysis to obtain a weakness coefficient set, wherein the weakness coefficient set corresponds to the first associated knowledge set in one-to-one correspondence; Based on the weak coefficient set, screening a second associated knowledge set whose weak coefficient is greater than or equal to a weak coefficient threshold from the first associated knowledge set; According to the second associated knowledge set, the associated VR knowledge model is matched from the VR knowledge model library and sent to the user-side VR display device for practical training and learning, wherein the VR knowledge model library is a database for storing pre-configured VR knowledge models and knowledge associations.

2. The method according to claim 1, characterized in that According to the user identity information, the first associated knowledge set is traversed to perform personal proficiency analysis to obtain a personal proficiency set, including: Extracting first associated knowledge from the first associated knowledge set; Retrieving a first historical assessment record data set including the first associated knowledge according to the user identity information; Counting the percentage of the first related knowledge that is correctly judged in the first historical assessment record data set, and setting it as the personal proficiency of the first related knowledge; The first associated knowledge personal proficiency is added to the personal proficiency set.

3. The method according to claim 1, characterized in that According to the user identity information, traversing the first associated knowledge set to configure a learning profile, and obtaining a learning profile set, includes: Obtaining a basic user profile, wherein the basic user profile includes the user's education history and the user's age; Extracting first associated knowledge from the first associated knowledge set; Retrieving the historical learning frequency including the first associated knowledge according to the user identity information; The user's educational history, the user's age and the historical learning frequency are added to the first associated knowledge learning portrait, and added to the learning portrait set.

4. The method according to claim 3, characterized in that Traversing the learning profile set and the first associated knowledge set to perform group proficiency analysis to obtain a group proficiency set, including: Extracting the first associated knowledge learning portrait from the learning portrait set, wherein the first associated knowledge learning portrait includes the user's education history, the user's age, and the historical learning frequency; Taking the user's education history, the user's age and the historical learning frequency as profile constraints, collecting a second historical assessment record data set of the first-level cluster profile users including the first associated knowledge; Using the first-level cluster portrait as a portrait constraint, collect the third historical assessment record data set of the second-level cluster portrait users including the first associated knowledge Counting the percentage of the first associated knowledge that is correctly determined in the third historical assessment record data set, and setting it as the second-level group proficiency of the first associated knowledge; Counting the percentage of the first associated knowledge that is correctly judged in the second historical assessment record data set, and setting it as the first-level group proficiency of the first associated knowledge; The average of the second-level group proficiency of the first associated knowledge and the first-level group proficiency of the first associated knowledge is calculated, set as the first associated knowledge group proficiency, and added into the group proficiency set.

5. The method according to claim 1, characterized in that According to the group proficiency set and the individual proficiency set, traversing the first associated knowledge set to perform weakness analysis to obtain a weakness coefficient set includes: Processing the first associated knowledge group proficiency and the first associated knowledge individual proficiency of the first associated knowledge through a weight distribution network to obtain a first group proficiency weight and a first individual proficiency weight; Construct a weakness coefficient evaluation function: f(x1,x2)=w1log a x1+w2log a x2 Among them, x1 represents individual proficiency, x2 represents group proficiency, w1 represents individual proficiency weight, w2 represents group proficiency weight, a represents adjustment factor, 0<a<1, f(x1, x2) represents the coefficient of weak associated knowledge; According to the weakness coefficient evaluation function, a weakness coefficient analysis is performed on the first group proficiency weight, the first individual proficiency weight, the first associated knowledge group proficiency and the first associated knowledge individual proficiency to obtain a first associated knowledge weakness coefficient, which is added to the weakness coefficient set.

6. The method according to claim 5, characterized in that The weight distribution network construction step includes: Configure group proficiency record data set and individual proficiency record data set; Performing subjective weight distribution based on the group proficiency record data set and the individual proficiency record data set to obtain a group proficiency weight identification data set and an individual proficiency weight identification data set; The group proficiency weight identification dataset and the individual proficiency weight identification dataset are used as supervision, and the group proficiency record dataset and the individual proficiency record dataset are used as input to train a BP neural network to generate the weight distribution network.

7. The method according to claim 6, characterized in that The method of performing subjective weight distribution based on the group proficiency record data set and the individual proficiency record data set to obtain a group proficiency weight identification data set and an individual proficiency weight identification data set includes: Sending the group proficiency record data set, the first group proficiency record data of the individual proficiency record data set, and the first individual proficiency record data to a plurality of importance evaluation nodes whose information is independent of each other, to obtain a plurality of group proficiency importance scores and a plurality of individual proficiency importance scores; Adding the plurality of group proficiency importance scores and the plurality of individual proficiency importance scores to obtain a total importance score; Adding the plurality of group proficiency importance scores to obtain a total group proficiency importance score; Adding the individual proficiency importance scores to obtain a total of the individual proficiency importance scores; Calculate the ratio of the sum of the group proficiency importance scores to the sum of the importance scores, and set it as the first group proficiency weight identification data; The ratio of the sum of the individual proficiency importance scores to the sum of the importance scores is calculated and set as the first individual proficiency weight identification data.

8. A training course development system combined with virtual reality, characterized in that: The method for developing a training course combined with virtual reality according to any one of claims 1 to 7 comprises: A course index module, the course index module is used to receive the VR training course number selected by the user end, input it into the knowledge base for indexing, and obtain a first associated knowledge set, wherein the knowledge base is a database in which pre-configured knowledge is associated with the course number and stored; A personal analysis module, the personal analysis module is used to traverse the first associated knowledge set to perform personal proficiency analysis according to user identity information to obtain a personal proficiency set, wherein the personal proficiency set corresponds to the first associated knowledge set one by one; A portrait configuration module, the portrait configuration module is used to traverse the first associated knowledge set to perform learning portrait configuration according to the user identity information, and obtain a learning portrait set, wherein the learning portrait set corresponds to the first associated knowledge set one by one; A group analysis module, the group analysis module is used to traverse the learning portrait set and the first associated knowledge set to perform group proficiency analysis to obtain a group proficiency set, wherein the group proficiency set corresponds to the first associated knowledge set one by one; A weakness identification module, the weakness identification module is used to traverse the first associated knowledge set to perform weakness analysis according to the group proficiency set and the individual proficiency set, and obtain a weakness coefficient set, wherein the weakness coefficient set corresponds to the first associated knowledge set in a one-to-one manner; a knowledge screening module, the knowledge screening module being used to screen, based on the weak coefficient set, a second associated knowledge set having a weak coefficient greater than or equal to a weak coefficient threshold from the first associated knowledge set; A VR model matching module is used to match the associated VR knowledge model from the VR knowledge model library according to the second associated knowledge set and send it to the user-side VR display device for practical training and learning, wherein the VR knowledge model library is a database for storing pre-configured VR knowledge models and knowledge associations.

9. A training course development platform combined with virtual reality, characterized by: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the training course development method combined with virtual reality as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the method for developing a practical training course combined with virtual reality as described in any one of claims 1 to 7 is implemented.

Images