College music immersive teaching interaction and learning feedback method and system

Abstract

The present application relates to the technical field of music teaching, and more particularly to a college music immersive teaching interaction and learning feedback method and system, which comprises setting a teaching situation plan, collecting operation behavior data and reaction time consumption data, facilitating subsequent analysis of teaching problems; through time matching and verification of operation behavior and reaction time consumption data, and comparison with preset standards, learning response abnormal situations can be quickly identified; by comparing historical normal and current abnormal stage operation behavior data, the key nodes of operation behavior deviation are located, providing key entry points for developing targeted teaching strategies and solving learning problems; by analyzing the changes in the dispersion degree of class student reaction time consumption before and after learning response abnormalities, evolution characteristics are formed, and differences in class learning state are grasped, so as to adjust the teaching rhythm and mode; through the development of instant teaching feedback instructions, appropriate feedback can be given to students in a timely manner according to specific problems and overall conditions.

Description

Technical Field

[0001] This invention relates to the field of music teaching technology, and in particular to interactive and learning feedback methods and systems for immersive music teaching in colleges and universities. Background Technology

[0002] University music courses encompass various teaching methods, including music theory and sight-singing, demanding high levels of student participation and immediate feedback. Current classroom teaching models primarily rely on teacher lectures and demonstrations, supplemented by multimedia equipment for audio and video materials. Some institutions have introduced digital teaching platforms for homework submission and evaluation, which can enrich the presentation of teaching content to some extent. However, classroom interaction remains mainly limited to teacher-student Q&A or group discussions, resulting in a limited range of student participation methods and hindering the creation of an immersive learning experience.

[0003] However, existing technologies have fundamental limitations in the teaching process: teachers mainly rely on classroom observation and homework analysis to grasp students' learning status, lacking structured methods for collecting and quantifying students' real-time operational behavior; when phenomena such as delayed student responses, increased error rates, or divergent group reaction speeds occur in the classroom, teachers cannot obtain timely quantitative representations of these abnormal states, resulting in teaching feedback lagging behind actual learning progress; furthermore, existing teaching systems lack an interactive response logic verification mechanism based on real-time student behavior data, failing to automatically identify abnormal learning responses during the classroom process, and lacking the ability to jointly analyze the degree of deviation in student behavior patterns and the evolution characteristics of group dispersion under abnormal states, leading to insufficient precision and real-time nature of teaching intervention, thus restricting the interactivity of college music classrooms and the objectivity of teaching effectiveness evaluation. Therefore, this invention proposes a method and system for interactive and learning feedback in immersive college music teaching. Summary of the Invention

[0004] The purpose of this invention is to solve the problems in the background art, and to propose a method and system for interactive and learning feedback in immersive music teaching in colleges and universities.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of this invention provides a method for interactive and feedback learning in immersive music teaching at universities, including: S1. Pre-set a teaching scenario plan and continuously capture the operational behavior data of students in music interactive tasks and the reaction time data corresponding to each operation during the teaching process; S2. Match and verify the captured operation behavior data and response time data in chronological order. If the verification shows that the degree of consistency between the two in time sequence is lower than the preset interactive response logic standard, it is determined that there is an abnormal learning response in the current classroom. S3. Under the premise that there is an abnormal learning response, the interactive trajectory backtracking algorithm is used to compare the student's operational behavior data in the historical normal learning stage with the current abnormal stage, and to filter out the key operational behavior nodes where the operational behavior deviates. S4. Analyze the evolution of the dispersion of response time data among different students in the same class before and after the occurrence of abnormal learning response situations, forming the dispersion evolution characteristics. S5. By jointly utilizing the selected key operational behavior nodes and discreteness evolution characteristics, formulate and issue real-time teaching feedback instructions for the current teaching situation.

[0006] Further, S1 includes: The pre-set teaching scenario plan includes teaching themes divided into teaching stages and pre-set expectations for the response characteristics that students should exhibit at each stage; The interactive teaching terminal records in real time the operation categories, position coordinates of the operation on the screen, and the time when the operation occurs, corresponding to the click, swipe, and performance trigger actions completed by students, thereby forming operation behavior data; Meanwhile, for the teaching content segments obtained from the teaching scenario plan, the time interval between the end of the complete playback of each teaching content segment and the student's first effective operation through the teaching interactive terminal is measured and used as the response time data.

[0007] Further, S2 includes: The operation behavior data and response time data are aligned using a preset time window to construct a time sequence combination in which operation events and response events occur in pairs; The actual response delay duration and the actual operational correctness are extracted from each timing combination as actual response features for comparison. The actual response characteristics are compared one by one with the expected response delay range and expected operational correctness specified in the preset interactive response logic standard to determine whether there are any abnormal learning response situations in the current classroom.

[0008] Furthermore, the preset interactive response logic standard is established in advance by collecting operational behavior data and response time data generated by multiple students in the same teaching situation during normal teaching operations in the past, extracting the expected response delay range and expected operation correctness between different operation categories and their corresponding response delays, and formulating the interactive response logic standard based on the extracted expected response delay range and expected operation correctness.

[0009] Further, S3 includes: Using the moment when the learning response to abnormal situations is identified as the dividing point, the operational behavior data is divided into operational behavior sequences in the historical normal phase and operational behavior sequences in the current abnormal phase. Each operation event is treated as an operation behavior node, and a directed behavior chain network is constructed with the time interval between adjacent operation events and the operation type correlation degree as edges. Each edge is assigned a time interval attribute and an operation type correlation degree attribute. The time interval is the difference between the timestamp of the next operation event and the timestamp of the previous operation event. The operation type correlation degree is determined according to the preset correlation category pair. If the operation categories of two operation events belong to the correlation category pair, the correlation degree is 1; otherwise, the correlation degree is 0. Behavioral chain analysis is performed on the operational behavior sequences of the historical normal phase and the operational behavior sequences of the current abnormal phase, thereby constructing the behavioral node transfer relationship network of the historical normal phase and the behavioral node transfer relationship network of the current abnormal phase.

[0010] Furthermore, S3 also includes: The behavior node transfer relationship network of the current abnormal phase is compared with the behavior node transfer relationship network of the historical normal phase at the node level. The comparison includes: finding operation behavior node pairs that exist in both behavior node transfer relationship networks and determining whether the change in the transfer probability of the operation behavior node pair exceeds the predetermined probability change threshold; and finding new operation behavior nodes that only appear in the behavior node transfer relationship network of the current abnormal phase. Operational behavior nodes that meet any of the comparison conditions, i.e., the change in transfer probability exceeds the preset probability change threshold, or are newly added operational behavior nodes, are identified as key operational behavior nodes where the operational behavior has deviated.

[0011] Further, S4 includes: Before and after the occurrence of abnormal learning response, data samples of the reaction time of each student in the class were collected in multiple different time windows. Using the reaction time data samples collected from each student, the standard deviation or interquartile range of the reaction time data in the whole class is calculated, thus forming a time series of dispersion index that reflects the degree of dispersion of reaction speed within the class. Analyze the time series variation of this dispersion index before and after the occurrence of abnormal situations in the learning response; The determination is made based on the changing trend of the dispersion index time series, the discrimination result is obtained, and the discrimination result is used as the dispersion evolution feature.

[0012] Further, S5 includes: Based on the type of teaching content or the interaction stage in which the selected key operational behavior nodes are associated in the interaction process, the intervention targets for implementing teaching interventions are determined. At the same time, based on the differentiation of students' reaction speed within the class as reflected by the characteristics of dispersion evolution, immediate teaching feedback instructions are formulated for the intervention targets. Send the immediate teaching feedback instruction to the teaching presentation terminal.

[0013] Furthermore, the real-time teaching feedback instructions include at least one of the following types: differentiated prompts for individuals, collaborative difficulty adjustment instructions for groups, and rhythm control instructions for the whole class; the execution methods of the real-time teaching feedback instructions include: real-time overlay of visual guidance information on the teaching content presentation interface, adjustment of the playback speed or pitch of the music demonstration segment, or triggering a vibration prompt device.

[0014] The second aspect of this invention provides a college music immersion teaching interaction and learning feedback system, comprising: Teaching Context Data Capture Module: A set of teaching context plans are pre-set, and the module continuously captures the operational behavior data of students in music interactive tasks and the reaction time data corresponding to each operation during the teaching process; Learning response anomaly verification module: The captured operation behavior data and response time data are matched and verified in chronological order. If the verification shows that the degree of consistency between the two in time sequence is lower than the preset interactive response logic standard, it is determined that there is an abnormal learning response in the current classroom. Abnormal Operation Node Backtracking Module: Under the premise that an abnormal learning response is identified, the interaction trajectory backtracking algorithm is used to compare the student's operation behavior data in the historical normal learning stage with the current abnormal stage, and to filter out the key operation behavior nodes where the operation behavior deviated. Student Response Dispersion Analysis Module: Analyzes the dispersion of response time data among different students in the same class before and after the occurrence of abnormal learning response situations, forming dispersion evolution characteristics; The real-time teaching feedback formulation module combines the selected key operational behavior nodes and discrete evolution characteristics to formulate and issue real-time teaching feedback instructions for the current teaching context.

[0015] Compared with existing technologies, the beneficial effects of the present invention in providing an interactive and feedback method and system for immersive music teaching in colleges and universities are as follows: 1) By pre-setting teaching scenario plans, a clear framework and goal guidance are provided for teaching, so that teaching can be carried out in an orderly manner. Continuous capture of student operation behavior data and response time data can be obtained, and students' performance in music interactive tasks can be fully recorded, providing rich and real basic data for subsequent analysis, thereby gaining a deeper understanding of students' learning process and status. 2) By matching and verifying the operational behavior data and the response time data in chronological order, and by comparing them with the preset interactive response logic standard, abnormal learning response situations can be detected in a timely and accurate manner. This makes it easier for teachers to quickly detect problems in teaching, avoid the accumulation of problems that affect teaching effectiveness, and provide a clear direction for subsequent targeted solutions. 3) By using the interactive trajectory backtracking algorithm to compare historical normal and current abnormal operational behavior data, key operational behavior nodes are screened out, and the root cause of the problem is accurately located. This allows teachers to clearly understand the steps in which students deviate, providing key evidence for developing effective teaching intervention measures and improving the pertinence and effectiveness of teaching feedback. 4) By analyzing the evolution of the dispersion of student response time data before and after abnormal learning responses, and forming the dispersion evolution characteristics, we can grasp the changes in the class's learning status from an overall perspective, understand the differentiation of students' response speed, help teachers fully understand the teaching situation, and provide macro-level reference for adjusting teaching strategies. 5) By combining key operational behavior nodes and discrete evolution characteristics, timely teaching feedback instructions can be formulated and issued. Based on specific problems and the overall status of students, appropriate feedback can be given in a timely manner, which can quickly adjust the teaching pace and direction, meet the learning needs of different students, improve teaching quality and student learning outcomes, and achieve personalized and precise teaching. Attached Figure Description

[0016] Figure 1 This is a flowchart of the interactive and learning feedback method for immersive music teaching in colleges and universities proposed in this invention.

[0017] Figure 2 This is a block diagram of the interactive and learning feedback system for immersive music teaching in universities proposed in this invention. Detailed Implementation

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

[0019] Please see Figure 1 This invention provides a method for interactive and feedback learning in immersive music teaching in universities, including: S1. Pre-set a teaching scenario plan and continuously capture the operational behavior data of students in music interactive tasks and the reaction time data corresponding to each operation during the teaching process; S2. Match and verify the captured operation behavior data and response time data in chronological order. If the verification shows that the degree of consistency between the two in time sequence is lower than the preset interactive response logic standard, it is determined that there is an abnormal learning response in the current classroom. S3. Under the premise that there is an abnormal learning response, the interactive trajectory backtracking algorithm is used to compare the student's operational behavior data in the historical normal learning stage with the current abnormal stage, and to filter out the key operational behavior nodes where the operational behavior deviates. S4. Analyze the evolution of the dispersion of response time data among different students in the same class before and after the occurrence of abnormal learning response situations, forming the dispersion evolution characteristics. S5. By jointly utilizing the selected key operational behavior nodes and discrete evolution characteristics, formulate and issue real-time teaching feedback instructions for the current teaching situation, so as to change the presentation method or interactive difficulty level of subsequent teaching content.

[0020] In this embodiment of the invention, the detailed implementation steps of S1, which pre-sets a teaching scenario plan and continuously captures the operational behavior data of students in the music interaction task and the reaction time data corresponding to each operation, include: S11. The pre-set teaching scenario plan includes teaching themes divided by teaching stages and pre-set expectations for the response characteristics that students should present at each stage; Specifically, before the start of teaching, the teacher sets up a teaching scenario plan through the teaching scenario control unit. The teaching scenario control unit is a functional component responsible for storing and managing the teaching scenario plan, preset interactive response logic standards, and teaching themes and response characteristic parameters for each stage. The teaching scenario plan is divided into multiple consecutive teaching stages according to the time process of classroom teaching. Each teaching stage corresponds to a specific teaching theme, such as the rhythm imitation stage, pitch recognition stage, or melody singing stage. For each teaching theme, based on the type and difficulty level of the music skills involved, pre-configured response characteristics are set for the students to exhibit at that stage. These response characteristic presets characterize the operational response level that students should achieve when completing the interactive teaching tasks at that stage, including two dimensions: operational speed requirements and operational accuracy requirements. Different response characteristic presets can be configured for different teaching stages. For example, the response speed requirement for the rhythm imitation stage is higher than that for the pitch recognition stage. All teaching stages, their corresponding teaching themes, and response characteristic presets together constitute a complete teaching scenario plan and are stored in the teaching scenario control unit.

[0021] S12. Using the teaching interactive terminal, record in real time the operation category, position coordinates of the operation on the screen, and the time when the operation occurs, corresponding to the click action, swipe action, and performance trigger action completed by the student, thereby forming operation behavior data.

[0022] S13. At the same time, for the teaching content segments obtained from the teaching scenario plan, the time interval between the end of the complete playback of each teaching content segment and the student's first effective operation through the teaching interactive terminal is measured and used as the response time data.

[0023] In this embodiment of the invention, step S2 matches and verifies the captured operational behavior data and response time data in chronological order. If the verification shows that the temporal consistency between the two is lower than the preset interactive response logic standard, then it is determined that there is an abnormal learning response situation in the current classroom. The detailed implementation steps include: S21. Align the operation behavior data and response time data using a preset time window to construct a time sequence combination in which operation events and response events occur in pairs, including: The continuously collected operation behavior data stream and response time data stream are segmented and aligned using fixed-length time windows. The length of each time window is preset according to the interactive rhythm of the teaching content, for example, 3 seconds or 5 seconds. Within a time window, the end signal of the teaching content playback sent by the music content presentation unit is identified, and this end signal is used as the starting reference point of the time window. The music content presentation unit is a functional component responsible for playing music materials, demonstration audio, and teaching segments according to the instructions of the teaching context control unit. Subsequently, the first valid operation signal received by the teaching interaction terminal within the time window is monitored. The system associates the first valid operation signal with the starting reference point, forming a pair of operation events and response events. The operation event records the operation category and operation coordinates, while the response event records the reaction time from the starting reference point to the generation of the first valid operation signal. If multiple valid operations exist within a time window, the first valid operation signal is paired with the starting reference point, and subsequent valid operations are assigned to adjacent time windows. By traversing all time windows, the discrete operation behavior data and reaction time data are transformed into a series of operation-response timing combinations arranged in chronological order. Each combination contains an operation event and a uniquely corresponding response event.

[0024] S22. Extract the actual response delay duration and the actual operational correctness from each timing combination as actual response features for comparison. Specifically, for each completed operation-response timing combination, a feature extraction operation is performed; the response time value is directly read from the response events of the timing combination and marked as the actual response delay duration; based on the operation category and operation coordinates recorded in the operation events of the operation-response timing combination, it is compared with the standard operation plan preset for the teaching content segment in the current teaching context; the standard operation plan specifies the operation category and operation coordinate range that the correct operation should meet; it is determined whether the actual operation matches the standard operation. If it matches completely, the correctness of the operation is recorded as 100%; if it matches partially, a percentage is calculated based on the degree of matching, for example, if the operation category is correct but the operation coordinate deviation is within the allowable range, it is recorded as 80%; if it does not match completely, it is recorded as 0%; the calculated percentage value is the actual operation correctness; the actual response delay duration and the actual operation correctness are combined to form the actual response feature of the timing combination.

[0025] S23. Compare the actual response characteristics with the expected response delay range and expected operational correctness specified in the preset interactive response logic standards one by one to determine whether there are any abnormal learning response situations in the current classroom, including: The preset interactive response logic standard corresponding to the current teaching stage is read from the teaching context control unit. This standard specifies two parameters for the current teaching topic: expected response delay interval and expected operation correctness. It is understood that the expected response delay interval and expected operation correctness are specific quantitative implementations of the preset response characteristics, used for comparison with the actual response characteristics collected in real time. The expected response delay interval consists of a lower limit and an upper limit, for example, a lower limit of 1 second and an upper limit of 3 seconds. The expected operation correctness is a percentage threshold, for example, 80%. The actual response delay duration extracted from the actual response features is compared with the expected response delay interval. The judgment rules are as follows: If the actual response delay duration is within the expected response delay interval (including the endpoint) and the actual operation correctness is greater than or equal to the expected operation correctness, then the actual response features of the operation-response timing combination are judged to meet the preset interactive response logic standard, the learning response is normal, and no abnormal judgment is triggered; conversely, if the actual response delay duration is less than the lower limit of the expected response delay interval or greater than the upper limit of the expected response delay interval, or the actual operation correctness is lower than the expected operation correctness, then the actual response features of the timing combination are judged to not meet the preset interactive response logic standard, and an abnormal learning response situation is confirmed; where, the timing matching degree refers to the comprehensive result of the matching between the actual response delay duration and the expected response delay interval, and the matching between the actual operation correctness and the expected operation correctness.

[0026] It is understood that the preset interactive response logic standard is established in advance by collecting operational behavior data and response time data generated by multiple students in the same teaching situation during normal teaching operations in the past, extracting the expected response delay range and expected operation correctness between different operation categories and their corresponding response delays, and formulating the interactive response logic standard based on the extracted expected response delay range and expected operation correctness. Specifically, teaching data is collected from previous normal teaching periods. This data comes from the operational behavior and response time data of students in the same teaching context across multiple classes and teaching cycles. After collection, the teaching data is categorized according to teaching themes, with data belonging to the same theme grouped into the same dataset. For each dataset, the response time for each valid operation is calculated, and the distribution range of all response times is determined. The middle 80% of the concentrated distribution range is taken as the expected response delay range for that teaching theme, for example, from the 10th percentile to the 90th percentile. Simultaneously, the accuracy of each operation in the same dataset is calculated, and the average or median of all accuracy values ​​is calculated. This accuracy value is then rounded down to the nearest integer and used as the expected accuracy of the operation for that teaching theme. For example, if the average accuracy is 85%, the expected accuracy is set to 85% or 80%. Each teaching theme is associated with and stored in relation to its corresponding expected response delay range and expected accuracy, forming a preset interactive response logic standard for that teaching theme.

[0027] In this embodiment of the invention, S3, under the premise of identifying an abnormal learning response, uses an interaction trajectory backtracking algorithm to compare the student's operational behavior data during the historical normal learning phase with the current abnormal phase, and filters out the key operational behavior nodes where the operational behavior deviates. The specific implementation method is as follows: S31. Using the moment when the learning response to abnormal situations is identified as the dividing point, the operational behavior data is divided into the operational behavior sequence of the historical normal stage and the operational behavior sequence of the current abnormal stage.

[0028] S32. Take each operation event as an operation behavior node, and construct a directed behavior chain network with the time interval between adjacent operation events and the operation type correlation degree as edges. Each edge is assigned a time interval attribute and an operation type correlation degree attribute. The time interval is the difference between the timestamp of the next operation event and the timestamp of the previous operation event. The operation type correlation degree is determined according to the preset correlation category pair. If the operation categories of two operation events belong to the correlation category pair, the correlation degree is 1, otherwise it is 0.

[0029] S33. Perform behavior chain analysis on the operation behavior sequence of the historical normal stage and the operation behavior sequence of the current abnormal stage respectively, so as to construct the behavior node transfer relationship network of the historical normal stage and the behavior node transfer relationship network of the current abnormal stage.

[0030] S34. Compare the behavior node transfer relationship network of the current abnormal phase with the behavior node transfer relationship network of the historical normal phase at the node level. The comparison includes: finding the operation behavior node pairs that exist in both behavior node transfer relationship networks and determining that the change in the transfer probability of the operation behavior node pairs exceeds the predetermined probability change threshold; and finding new operation behavior nodes that only appear in the behavior node transfer relationship network of the current abnormal phase. The change in transition probability is defined as the absolute value of the difference between the probability of transitioning from action node A to action node B in the historical normal phase's action node transition relationship network and the probability of transitioning from the same action node A to the same action node B in the current abnormal phase's action node transition relationship network. This difference is obtained as follows: The historical transition probability value is obtained by counting the number of times action node B appears after action node A in the historical normal phase's action behavior sequence and dividing this number by the total number of times action node A appears. Similarly, the current transition probability value is obtained by counting the number of times action node B appears after action node A in the current abnormal phase's action behavior sequence and dividing this number by the total number of times action node A appears in this phase. The change in transition probability is obtained by subtracting the historical transition probability value from the current transition probability value and taking the absolute value. It should be noted that the behavior node transfer relationship network of the current abnormal phase is compared with the behavior node transfer relationship network of the historical normal phase at the node level. This comparison operation is performed in parallel along two dimensions: the first dimension targets the common operation behavior node pairs in both behavior node transfer relationship networks; for each pair of operation behavior nodes, i.e., the directed edge from the previous node to the next node, the transfer probability value of that edge is read from both the behavior node transfer relationship network of the historical normal phase and the behavior node transfer relationship network of the current abnormal phase, the absolute difference between the two transfer probability values ​​is calculated, i.e., the magnitude of the transfer probability change, and this magnitude of the transfer probability change is compared with a preset probability change threshold; the preset probability... The probability change threshold is a fixed threshold; if the absolute difference exceeds this probability change threshold, the operation behavior node pair is marked as a connection that has undergone significant change; the second dimension focuses on the operation behavior node itself in the operation behavior node transfer relationship network; all operation behavior nodes in the current abnormal stage's operation behavior node transfer relationship network are traversed, and each operation behavior node is checked to see if it exists in the historical normal stage's operation behavior node transfer relationship network; if an operation behavior node only appears in the current abnormal stage's operation behavior node transfer relationship network, but there is no corresponding operation behavior node in the historical normal stage's operation behavior node transfer relationship network, then the operation behavior node is marked as a newly added operation behavior node; the comparison results of the two dimensions together constitute the output of the node-level comparison.

[0031] S35. Any operation behavior node that meets any comparison condition, i.e., the change in the transfer probability exceeds the preset probability change threshold, or is a newly added operation behavior node, is identified as a key operation behavior node in which the operation behavior has deviated.

[0032] In this embodiment of the invention, the specific implementation method for analyzing the dispersion of response time data among different students within the same class before and after the occurrence of abnormal learning response situations, forming dispersion evolution characteristics, includes: S41. Before and after the occurrence of abnormal learning response, collect data samples of the reaction time of each student in the class within multiple different time windows.

[0033] S42. Using the collected reaction time data samples of each student, calculate the standard deviation or interquartile range of the reaction time data in the whole class, thereby forming a time series of dispersion index that reflects the degree of dispersion of reaction speed within the class. Specifically, multiple consecutive time windows are set before and after the moment when an abnormal learning response occurs. For example, based on the moment the abnormal situation is identified, three time windows are taken forward, each with a length of 30 seconds, labeled T-3, T-2, and T-1; and three time windows are taken backward, labeled T+1, T+2, and T+3. Within each time window, all response time data generated by each student in the class are collected. If a student performs multiple valid actions within a time window, the average of their multiple response times is taken as the representative value for that student in that time window. If a student does not perform any valid actions within a time window, the student's response time within that time window is marked as a missing value and excluded from subsequent calculations. For each time window, a set of representative response time values ​​for all valid students in the class is collected, the size of which is equal to the number of valid students in the class. This set of representative response time values ​​is then discretized. The dispersion calculation is as follows: If the standard deviation method is used, first calculate the arithmetic mean of the set, then calculate the sum of squares of the deviations of each representative value from the mean, divide by the number of valid students, and then take the square root to obtain the standard deviation value; if the interquartile range method is used, arrange the representative values ​​in the set of representative values ​​of reaction time in ascending order, find the third quartile and the first quartile, and calculate the difference between the two as the interquartile range; if the standard deviation or interquartile range value is larger, it indicates that the students' reaction speed is more dispersed; if the standard deviation or interquartile range value is smaller, it indicates that the students' reaction speed is more concentrated; repeat the calculation for each time window to obtain the dispersion value corresponding to that window; arrange all time windows in chronological order, and arrange the corresponding dispersion values ​​in sequence to form a dispersion index time series, for example [T-3: 0.52, T-2: 0.55, T-1: 0.58, T+1: 0.72, T+2: 0.81, T+3: 0.89].

[0034] S43. Analyze the trend of the dispersion index time series before and after the occurrence of abnormal situations in the learning response, including: Using the moment of identification of abnormal situations in the learning response as the dividing line, the time series of the dispersion index is divided into a pre-abnormality subsequence and a post-abnormality subsequence. The pre-abnormality subsequence contains the dispersion values ​​corresponding to three time windows: T-3, T-2, and T-1, while the post-abnormality subsequence contains the dispersion values ​​corresponding to three time windows: T+1, T+2, and T+3. The dispersion differences between adjacent time windows in the pre-abnormality subsequence (e.g., the difference between T-2 and T-1, and the difference between T-1 and T-2) and the dispersion differences between adjacent time windows in the post-abnormality subsequence are calculated respectively. The dispersion is analyzed... The change in the sign of the difference indicates the trend of dispersion. If the dispersion difference of the subsequence before the anomaly is generally close to zero or alternates between positive and negative, it indicates that the dispersion was relatively stable before the anomaly. If the dispersion difference of the subsequence after the anomaly is consistently positive, it indicates that the dispersion continued to increase after the anomaly occurred. If the dispersion difference of the subsequence after the anomaly is consistently negative, it indicates that the dispersion continued to decrease. At the same time, the overall offset of the subsequence after the anomaly relative to the subsequence before the anomaly is calculated, which is the average dispersion of each time window after the anomaly minus the average dispersion of each time window before the anomaly, to obtain the quantitative value of the change amplitude.

[0035] S44. Based on the trend of the time series of the dispersion index, make a judgment and obtain the discrimination result, that is, determine whether the dispersion of students' reaction speed in the class shows the characteristics of increased differentiation, maintenance of the original distribution pattern, or convergence and uniformity, and use the discrimination result as the dispersion evolution characteristic. Specifically, based on the trend of the dispersion index time series, the dispersion evolution characteristics are output according to the following judgment rules: First, if the dispersion difference between adjacent time windows in the subsequence after the anomaly is continuously positive, and the average dispersion of each time window after the anomaly is greater than the average dispersion of each time window before the anomaly, and the change amplitude exceeds the preset dispersion change threshold, then the dispersion degree is judged to show a change characteristic of increased differentiation; increased differentiation indicates that the reaction speed of some students in the class has slowed down significantly while that of other students remains normal or speeds up, and the gap between students is widening; Secondly, if the dispersion difference between adjacent time windows in the post-anomaly subsequence is continuously negative, and the average dispersion of each time window after the anomaly is less than the average dispersion of each time window before the anomaly, and the change exceeds the preset dispersion change threshold, then the dispersion is judged to exhibit a convergent and uniform change characteristic. The dispersion change threshold is used to determine whether the dispersion change is significant. This threshold is a preset percentage value, such as 0.2 (20%), which can be adjusted according to the sensitivity requirements of the teaching scenario; the higher the sensitivity, the lower the threshold setting. Convergence and uniformity indicate that the reaction speeds of students in the class are approaching the same level, with slower students accelerating or faster students slowing down, and the gap narrowing. Small; if the dispersion difference in the subsequence after the anomaly fluctuates between positive and negative, or the change amplitude does not exceed the preset dispersion difference fluctuation threshold, then it is determined that the dispersion maintains the original distribution pattern, that is, the abnormal event has not had a substantial impact on the dispersion of reaction speed within the class; among which, the dispersion difference fluctuation threshold is used to determine whether the alternation of positive and negative dispersion differences between adjacent time windows in the subsequence after the anomaly is a fluctuation. The dispersion difference fluctuation threshold is set to 1, that is, as long as there is a sign change, it is considered a fluctuation; after the determination is completed, the determination result, that is, the differentiation intensifies, the original distribution pattern is maintained, or the convergence tends to be consistent, together with the corresponding dispersion value sequence, is packaged into dispersion evolution feature data.

[0036] In this embodiment of the invention, the detailed implementation steps of S5, which combines the selected key operational behavior nodes and discreteness evolution characteristics to formulate and issue real-time teaching feedback instructions for the current teaching situation, include: S51. Based on the teaching content type or interactive stage associated with the selected key operational behavior nodes in the interactive process, determine the intervention targets for implementing teaching intervention; where the teaching content type comes from the teaching scenario plan, and the interactive stage corresponds to different operating areas of the teaching interactive terminal.

[0037] S52. At the same time, based on the differentiation of students' reaction speed within the class as reflected by the characteristics of dispersion evolution, immediate teaching feedback instructions are formulated for the intervention targets. Among them, the real-time teaching feedback instruction is a set of control commands used to adjust the teaching process in real time; it is issued to the corresponding execution mechanism through the teaching presentation terminal; the real-time teaching feedback instruction contains three core fields: the time of feedback issuance, the form of feedback content, and the adjustment range of interaction difficulty; Specifically, firstly, the feedback strategy is determined based on the category of the dispersion evolution characteristics: the selected key operational behavior nodes are used as intervention targets, while the output dispersion evolution characteristics are received; when formulating immediate teaching feedback instructions, the feedback strategy is determined based on the category of dispersion evolution characteristics; if the dispersion evolution characteristics indicate increased differentiation, it is determined that some students in the class have fallen behind in the current teaching situation, and a differentiated feedback strategy is required, that is, issuing different instructions to different student groups; if the dispersion evolution characteristics indicate maintaining the original distribution pattern, it is determined that the anomaly has not yet had a significant impact on the class as a whole, and a general feedback strategy can be adopted; if the dispersion evolution characteristics indicate convergence and uniformity, it is determined that the anomaly may be self-correcting, and a mild auxiliary feedback strategy is adopted. Secondly, determine the feedback issuance time: The feedback issuance time field specifies the time when the instruction takes effect; this time is set to be triggered immediately when the precursor characteristics of the next key operation behavior node are identified in the current student group, that is, when two consecutive students show an increasing trend of response delay or the operation error type matches the key operation behavior node. Secondly, based on the type of the intervention target, i.e., the key operational behavior node, the specific form of feedback content is determined: according to the category of dispersion evolution characteristics and the type of key operational behavior node, one or more execution methods are selected from the preset feedback form library; among which, the execution methods include, but are not limited to: visual guidance information superimposed on the teaching content presentation interface in real time, such as highlighting the correct operation area or dynamic arrow guidance; adjusting the playback speed or pitch of the music demonstration segment, such as reducing the playback speed to 80% of the original speed to reduce the difficulty of operation; triggering vibration prompt devices, such as providing short vibration feedback when students make mistakes; in the case of increased group differentiation, differentiated feedback content can be pushed to different students at the same time; among which, the immediate teaching feedback instructions include at least one of the following types: differentiated prompt instructions for individuals, instructions for adjusting the difficulty of group collaboration, and rhythm control instructions for the whole class; Finally, determine the adjustment range of the interaction difficulty: The interaction difficulty adjustment range field specifies the proportion of difficulty adjustment for subsequent teaching content segments; based on the change range value in the dispersion evolution characteristics, the interaction difficulty is reduced or increased proportionally. For example, when the differentiation intensifies and the change range is large, the interaction difficulty of subsequent teaching content segments is reduced by two levels; when the original distribution pattern is maintained, the interaction difficulty is reduced by one level; when convergence tends to be consistent, the original interaction difficulty is maintained or increased by one level. The three parameters of feedback delivery time, feedback content presentation format, and interaction difficulty adjustment range are combined and encoded to generate real-time teaching feedback instructions.

[0038] S53. Send the real-time teaching feedback instruction to the teaching presentation terminal to drive the presentation components on the teaching presentation terminal to perform operations such as content switching, reducing the difficulty level, or enhancing the prompting effect in subsequent teaching sessions.

[0039] Please see Figure 2 This invention provides an interactive and feedback-based music immersion teaching system for universities, comprising: Teaching Context Data Capture Module: A set of teaching context plans are pre-set, and the module continuously captures the operational behavior data of students in music interactive tasks and the reaction time data corresponding to each operation during the teaching process; Learning response anomaly verification module: The captured operation behavior data and response time data are matched and verified in chronological order. If the verification shows that the degree of consistency between the two in time sequence is lower than the preset interactive response logic standard, it is determined that there is an abnormal learning response in the current classroom. Abnormal Operation Node Backtracking Module: Under the premise that an abnormal learning response is identified, the interaction trajectory backtracking algorithm is used to compare the student's operation behavior data in the historical normal learning stage with the current abnormal stage, and to filter out the key operation behavior nodes where the operation behavior deviated. Student Response Dispersion Analysis Module: Analyzes the dispersion of response time data among different students in the same class before and after the occurrence of abnormal learning response situations, forming dispersion evolution characteristics; The real-time teaching feedback formulation module combines the selected key operational behavior nodes and discrete evolution characteristics to formulate and issue real-time teaching feedback instructions for the current teaching context.

[0040] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0041] It should be noted that all formulas in this manual are calculated by removing dimensions and taking their numerical values. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0042] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for interactive and feedback learning in immersive music teaching in universities, characterized by: include: S1. Pre-set a teaching scenario plan and continuously capture the operational behavior data of students in music interactive tasks and the reaction time data corresponding to each operation during the teaching process; S2. Match and verify the captured operation behavior data and response time data in chronological order. If the verification shows that the degree of consistency between the two in time sequence is lower than the preset interactive response logic standard, it is determined that there is an abnormal learning response in the current classroom. S3. Under the premise that there is an abnormal learning response, the interactive trajectory backtracking algorithm is used to compare the student's operational behavior data in the historical normal learning stage with the current abnormal stage, and to filter out the key operational behavior nodes where the operational behavior deviates. S4. Analyze the evolution of the dispersion of response time data among different students in the same class before and after the occurrence of abnormal learning response situations, forming the dispersion evolution characteristics. S5. By jointly utilizing the selected key operational behavior nodes and discreteness evolution characteristics, formulate and issue real-time teaching feedback instructions for the current teaching situation.

2. The interactive and learning feedback method for immersive music teaching in universities according to claim 1, characterized in that, S1 includes: The pre-set teaching scenario plan includes teaching themes divided into teaching stages and pre-set expectations for the response characteristics that students should exhibit at each stage; The interactive teaching terminal records in real time the operation categories, position coordinates of the operation on the screen, and the time when the operation occurs, corresponding to the click, swipe, and performance trigger actions completed by students, thereby forming operation behavior data; Meanwhile, for the teaching content segments obtained from the teaching scenario plan, the time interval between the end of the complete playback of each teaching content segment and the student's first effective operation through the teaching interactive terminal is measured and used as the response time data.

3. The interactive and learning feedback method for immersive music teaching in universities according to claim 1, characterized in that, S2 includes: The operation behavior data and response time data are aligned using a preset time window to construct a time sequence combination in which operation events and response events occur in pairs; The actual response delay duration and the actual operational correctness are extracted from each timing combination as actual response features for comparison. The actual response characteristics are compared one by one with the expected response delay range and expected operational correctness specified in the preset interactive response logic standard to determine whether there are any abnormal learning response situations in the current classroom.

4. The interactive and learning feedback method for immersive music teaching in universities according to claim 3, characterized in that, The preset interactive response logic standard is established in advance by collecting operational behavior data and response time data generated by multiple students in the same teaching situation during normal teaching operations, extracting the expected response delay range and expected operation correctness between different operation categories and their corresponding response delays, and formulating the interactive response logic standard based on the extracted expected response delay range and expected operation correctness.

5. The interactive and learning feedback method for immersive music teaching in universities according to claim 1, characterized in that, S3 includes: Using the moment when the learning response to abnormal situations is identified as the dividing point, the operational behavior data is divided into operational behavior sequences in the historical normal phase and operational behavior sequences in the current abnormal phase. Each operation event is treated as an operation behavior node, and a directed behavior chain network is constructed with the time interval between adjacent operation events and the operation type correlation degree as edges. Each edge is assigned a time interval attribute and an operation type correlation degree attribute. The time interval is the difference between the timestamp of the next operation event and the timestamp of the previous operation event. The operation type correlation degree is determined according to the preset correlation category pair. If the operation categories of two operation events belong to the correlation category pair, the correlation degree is 1; otherwise, the correlation degree is 0. Behavioral chain analysis is performed on the operational behavior sequences of the historical normal phase and the operational behavior sequences of the current abnormal phase, thereby constructing the behavioral node transfer relationship network of the historical normal phase and the behavioral node transfer relationship network of the current abnormal phase.

6. The interactive and learning feedback method for immersive music teaching in universities according to claim 5, characterized in that, S3 further includes: The behavior node transfer relationship network of the current abnormal phase is compared with the behavior node transfer relationship network of the historical normal phase at the node level. The comparison includes: finding operation behavior node pairs that exist in both behavior node transfer relationship networks and determining whether the change in the transfer probability of the operation behavior node pair exceeds the predetermined probability change threshold; and finding new operation behavior nodes that only appear in the behavior node transfer relationship network of the current abnormal phase. Operational behavior nodes that meet any of the comparison conditions, i.e., the change in transfer probability exceeds the preset probability change threshold, or are newly added operational behavior nodes, are identified as key operational behavior nodes where the operational behavior has deviated.

7. The interactive and learning feedback method for immersive music teaching in universities according to claim 1, characterized in that, S4 includes: Before and after the occurrence of abnormal learning response, data samples of the reaction time of each student in the class were collected in multiple different time windows. Using the reaction time data samples collected from each student, the standard deviation or interquartile range of the reaction time data in the whole class is calculated, thus forming a time series of dispersion index that reflects the degree of dispersion of reaction speed within the class. Analyze the time series variation of this dispersion index before and after the occurrence of abnormal situations in the learning response; The determination is made based on the changing trend of the dispersion index time series, the discrimination result is obtained, and the discrimination result is used as the dispersion evolution feature.

8. The interactive and learning feedback method for immersive music teaching in universities according to claim 1, characterized in that, S5 includes: Based on the type of teaching content or the interaction stage in which the selected key operational behavior nodes are associated in the interaction process, the intervention targets for implementing teaching interventions are determined. At the same time, based on the differentiation of students' reaction speed within the class as reflected by the characteristics of dispersion evolution, immediate teaching feedback instructions are formulated for the intervention targets. Send the immediate teaching feedback instruction to the teaching presentation terminal.

9. The interactive and learning feedback method for immersive music teaching in universities according to claim 1, characterized in that, The real-time teaching feedback instructions include at least one of the following types: differentiated prompts for individuals, collaborative difficulty adjustment instructions for groups, and rhythm control instructions for the whole class; the execution methods of the real-time teaching feedback instructions include: real-time overlay of visual guidance information on the teaching content presentation interface, adjustment of the playback speed or pitch of the music demonstration segment, or triggering a vibration prompt device.

10. A college music immersive teaching interactive and learning feedback system, characterized in that, The system, applied to the interactive and learning feedback method for immersive music teaching in universities as described in any one of claims 1-9, comprises: Teaching Context Data Capture Module: A set of teaching context plans are pre-set, and the module continuously captures the operational behavior data of students in music interactive tasks and the reaction time data corresponding to each operation during the teaching process; Learning response anomaly verification module: The captured operation behavior data and response time data are matched and verified in chronological order. If the verification shows that the degree of consistency between the two in time sequence is lower than the preset interactive response logic standard, it is determined that there is an abnormal learning response in the current classroom. Abnormal Operation Node Backtracking Module: Under the premise that an abnormal learning response is identified, the interaction trajectory backtracking algorithm is used to compare the student's operation behavior data in the historical normal learning stage with the current abnormal stage, and to filter out the key operation behavior nodes where the operation behavior deviated. Student Response Dispersion Analysis Module: Analyzes the dispersion of response time data among different students in the same class before and after the occurrence of abnormal learning response situations, forming dispersion evolution characteristics; The real-time teaching feedback formulation module combines the selected key operational behavior nodes and discrete evolution characteristics to formulate and issue real-time teaching feedback instructions for the current teaching context.

Images