Interactive teaching system and method for art education

Abstract

The invention relates to the technical field of interactive teaching, in particular to an art education interactive teaching system and method, and the system comprises a drawing behavior track module, a teaching task deviation diagnosis module, a teaching target adjustment module, and a teaching effect trend analysis module. According to the invention, by extracting the stroke track, the coloring area boundary and the line starting and ending points, combining the track change and revocation times, dynamically capturing the student operation habit and the copy key change, analyzing the association between the drawing target and the task state, and combining the progress deviation and the task proportion, the copy mastering degree monitoring performance is improved, and the problem of insufficient mastering degree is identified in time; task paths and target configuration are dynamically adjusted, target distribution and matching are optimized, task distribution flexibility and rationality are improved, the completion rate and behavior trend are analyzed through task records, accuracy change key nodes are identified, teaching strategy adjustment basis is defined, interaction teaching pertinence and efficiency are enhanced, deviation is reduced, and teaching efficiency is improved. And dynamic feedback and accurate adjustment are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of interactive teaching, and in particular to an interactive teaching system and method for art education. Background Art

[0002] The interactive teaching technology field realizes the interaction between teachers and students through computer systems, hardware and software platforms. The core is to promote information flow and feedback based on human-computer interaction methods, covering functions such as courseware design, real-time answers and resource management. Combined with touch devices, voice recognition and graphics processing tools, it provides multi-dimensional content display and interactive operations, especially focusing on the operation accuracy and feedback response of students in the copying process, dynamically assisting teachers to adjust teaching strategies and improve students' ability to grasp painting elements.

[0003] Among them, the interactive teaching system for art education is designed specifically for art teaching, covering digital teaching content, virtual stroke operation, color simulation and creative process analysis. Through touch device input operation and digital color management tool to select color, the graphics rendering module dynamically simulates the painting process, and organizes and calls teaching resources through the course management module. In copying teaching, the system captures students' brushstroke paths and color selection behaviors in real time, analyzes their restoration of the target work, and assists teachers to dynamically adjust teaching focus and target requirements according to changes in students' grasp of painting, thereby improving the pertinence and effectiveness of teaching.

[0004] Existing technologies achieve basic interaction through touch devices, voice recognition modules, and graphics processing tools, but lack dynamic processing capabilities when capturing and classifying painting behavior characteristics, and cannot clearly analyze behavioral changes in students' operations, resulting in delayed and vague feedback. Existing technologies rely on static parameter settings and cannot dynamically adjust task paths based on students' deviations during the copying process, resulting in an insufficient match between teaching objectives and students' actual operating levels. In addition, existing technologies evaluate teaching effectiveness through static result analysis, lacking real-time extraction and analysis of copying task trends and operating behaviors, affecting the flexible adjustment of teaching strategies, thereby reducing the scientific nature of resource allocation and course optimization, and making it difficult to meet the precise teaching needs of dynamic task adjustment and improved student painting mastery. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an interactive teaching system and method for art education.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an art education interactive teaching system comprises: The painting behavior trajectory module is based on students' painting behavior. It extracts brushstroke trajectories, coloring area boundaries, line starting points and end points, analyzes trajectory continuity and coloring coverage ratio, analyzes trajectory changes and the number of undoes, and performs filtering and segmentation classification to obtain painting behavior trajectory classification data. The teaching task deviation diagnosis module analyzes the association between the painting stage goal and the task status based on the painting behavior trajectory classification data, compares the progress deviation value and the task ratio, generates a task status parameter set, combines the target operation record, evaluates the task deviation status and problem type, extracts the key items of the problem type, and establishes the teaching problem type result; The teaching goal adjustment module adjusts the task operation path and the target distribution parameters based on the teaching problem type results, matches the task deviation state with the painting stage target, obtains the teaching goal setting data, combines the distribution relationship between the targets and the task adjustment path, optimizes the teaching task allocation and stage division, and establishes a target adjustment relationship diagram; The teaching effect trend analysis module extracts the stage task execution records based on the target adjustment relationship diagram, analyzes the task completion rate and behavior change trend data, compares the painting behavior status with the task target progress, extracts the key nodes of the trend change and the task association status, and establishes a teaching effect design adjustment plan.

[0007] As a further solution of the present invention, the step of obtaining the classification data of the painting behavior trajectory is specifically as follows: Based on the students' painting behavior, the starting point coordinates, end point coordinates and continuous trajectory point data of the painting stroke trajectory are extracted, the length and direction changes of the trajectory are analyzed, and a set of trajectory point change parameters is generated; Based on the trajectory point change parameter set, the smoothness and breakpoints between trajectory points are analyzed using the formula: ; The continuity score of the pen trajectory is calculated; in, represents the continuity score of the pen trajectory, Representative The angle between the trajectory points, Represents the length change between trajectory points, represents the smoothness weight, represents the length change weight, represents the total number of trajectory points; The brushstroke trajectory continuity score is called, combined with the density parameters of the starting point and the end point, the low-scoring trajectory segments are filtered and classified into segments, the trajectory segments are segmented and classified by reading the scoring threshold, and the attribution of the classified trajectory segments is adjusted to obtain the painting behavior trajectory classification data.

[0008] As a further solution of the present invention, the step of obtaining the task status parameter set is specifically as follows: Based on the painting behavior trajectory classification data, extract the time attribute and spatial position information of each trajectory point, identify the time difference and distance between adjacent points, divide the time interval and displacement range interval, analyze the trajectory length and the number of trajectory points, and obtain trajectory interval data; Based on the trajectory interval data, the number of task operations and the target number of operations in each interval are counted, the difference between the number of operations corresponding to the trajectory point and the target number is identified, the task completion ratio is analyzed, the task completion status is marked, and the task progress deviation data is obtained; Based on the task progress deviation data, the deviation change trend in the trajectory interval is analyzed, the deviation interval and the corresponding task are extracted, the deviation value and the task completion ratio are matched, the deviation impact parameters and the task execution state parameters are evaluated, and the task state parameter set is obtained.

[0009] As a further solution of the present invention, the steps of obtaining the teaching question type results are specifically as follows: Screening the task status records in the task status parameter set, comparing the task status deviation values ​​with the reference values ​​of the target operation records item by item, screening the tasks whose deviation values ​​are higher than the reference values, and generating a data set of task deviation degrees; Based on the data set of the task deviation degree, the problem types corresponding to the deviation values ​​are classified, and the key parameters of the problems in the classification are analyzed, using the formula: ; Calculate the key parameter values ​​of the problem type; in, Represents the key parameter value of the problem type, represents the current parameter value of the deviation record, represents the target reference value, Represents the total number of deviation records, represents the weight adjustment coefficient, Represents the impact factor value of the problem type record, Represents the total number of factors affecting the problem type; Based on the key parameter values ​​of the question type, the parameter set is integrated according to the question type, and the logical correlation and influence pattern are analyzed, and used as a logical judgment standard to generate teaching question type results.

[0010] As a further solution of the present invention, the step of acquiring the teaching objective setting data is specifically as follows: Based on the teaching problem type results, data parameters of task deviation status are extracted and grouped, the characteristics of target parameters of the painting stage are identified, the corresponding relationship between task deviation and stage target parameters is calculated, the deviation status matching priority is adjusted, and the association information between task deviation and stage target is obtained; Based on the task deviation and stage target association information, the task operation path is extracted and the target parameter distribution is calculated, the operation parameters in the task path are matched, the path parameters are dynamically adjusted, the weights in the operation path are allocated, the execution order of the task path is adjusted, and the optimized path and target distribution parameters are obtained; Based on the optimization path and target distribution parameters, the task execution order in the distribution parameters is extracted, the target path of the painting stage is adjusted and redistributed, the execution parameter order of the task path is optimized, and the teaching target setting data is obtained in combination with the operation weight of the target distribution.

[0011] As a further solution of the present invention, the step of obtaining the target adjustment relationship diagram is specifically as follows: Extracting key features from the teaching target setting data, analyzing the distribution relationship between targets, using distribution parameters to count the spacing and distribution patterns of teaching targets, calculating the standard deviation of target distribution and analyzing the correlation between targets, and obtaining distribution relationship parameters between targets; According to the distribution relationship parameters between the targets, combined with the similarity parameters and adjustment weights between the targets, the task allocation path is optimized through the formula: ; Get the total optimization value of task adjustment; in, represents the total optimization value of task adjustment, represents the similarity between targets, represents the distribution distance between targets, Represents the weight coefficient of task adjustment, represents the target quantity; According to the total optimization value of the task adjustment, the teaching task is carried out in stages, the stage goals are grouped using the distribution relationship parameters and the adjustment path, the distribution ratio of the number of goals in each group is analyzed, the stages of the goals are gradually adjusted and matched, and a goal adjustment relationship diagram is generated.

[0012] As a further solution of the present invention, the steps for obtaining the teaching effect design adjustment plan are specifically as follows: Based on the target adjustment relationship diagram, extract the task completion ratio and behavior change trend data, compare the behavior status with the task target process, analyze the change of the task completion ratio in sections, identify the correlation between the change of the task completion ratio and the key features of the behavior trend, and obtain the matching relationship between the task completion ratio and the behavior trend; Based on the matching relationship between the task completion ratio and the behavior trend, combined with the key nodes of the task process, the correlation analysis of the stage process goals is carried out, and the key nodes of the trend change and the task correlation status are extracted. The formula is used: ; Calculate and obtain the matching status value of the trend change and the task; in, Represents the matching status value of trend change and task, Represents the cumulative value of the change in task completion rate, The standard deviation value representing the trend of behavior change, Represents the weight of the stage task progress, is the dynamic adjustment coefficient; According to the matching status value of the trend change and the task, and based on the completion of the task objectives, the matching status data is extracted, the task status of the differentiated stages is compared and analyzed, the correlation weights between the staged teaching tasks and the behavioral changes are adjusted, and a teaching effect design adjustment plan is established.

[0013] An interactive teaching method for art education, which is executed based on the above-mentioned interactive teaching system for art education, comprises the following steps: S1: Based on the students’ painting behavior, we extract the brush stroke trajectory, the boundary of the coloring area, the starting point and end point of the line, analyze the length and direction changes of the path, classify the trajectory features by segments, extract the boundary contour of the closed area, classify the features based on the pixel coverage ratio, and generate the distribution results of the painting trajectory features; S2: Based on the distribution result of the painting trajectory feature, extract the associated trajectory path, compare the direction change value and the target offset, analyze the coverage characteristics of the unfinished area, analyze the path density and direction distribution, extract the associated data of the target insufficient coverage area and the path offset, classify the path offset area, and obtain the characteristics of the painting target deviation area; S3: Based on the deviation area characteristics of the drawing target, the direction offset value and trajectory length of the path node are adjusted, the distribution relationship between the nodes is corrected, the coverage range is compared with the operation parameters of the target, the task trajectory is matched and optimized with the adjusted target distribution, and a stage target adjustment path diagram is generated; S4: Based on the stage target adjustment path diagram, compare the distance and distribution changes between nodes, calculate the path association value within the coverage range of the target node, extract the offset parameters and trajectory adjustment results of the node distribution changes, screen the coverage data of the key change nodes, and establish a teaching effect design adjustment plan.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by extracting the stroke trajectory, the boundary of the coloring area and the starting and ending points of the lines, and combining the trajectory changes and the number of cancellations, the characteristic dynamics of the painting behavior are clarified, the students' operating habits and the key changes in the copying process are accurately captured, and the association between the painting stage goal and the task state is analyzed, and the progress deviation value is compared with the task ratio. The monitorability of the students' mastery of the copying task is improved, and the key problems caused by the lack of mastery of the students in the copying process can be quickly identified, and the task deviation state is matched with the dynamic adjustment operation path of the painting stage goal, and the distribution and association of the teaching objectives are further optimized. The adaptability of the task operation path and the configuration of the teaching objectives is ensured, and the flexibility and rationality of the task allocation are improved. In the extraction of the task execution record, by analyzing the task completion ratio and the behavior change trend, the trend change key nodes of the student's copying accuracy and the task association state are identified, and a clear basis is provided for the adjustment of teaching strategies and the optimization of target. By clarifying the student behavior dynamics, accurately evaluating the task state, optimizing the target adjustment path, extracting the key change trend and other multi-dimensional operations, the pertinence and efficiency of the interaction in the art copying teaching are strengthened, and the deviation in the task allocation and target adjustment is reduced, and a solid foundation is laid for the realization of dynamic feedback and precise adjustment in the copying process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a system flow chart of the present invention; Figure 2 A flow chart of the painting behavior trajectory classification data in the present invention; Figure 3 It is a flowchart of the task state parameter set in the present invention; Figure 4 A flow chart of the results of the teaching problem types in the present invention; Figure 5 A flow chart for setting data for the teaching objectives in the present invention; Figure 6 A flow chart of a target adjustment relationship diagram in the present invention; Figure 7 The present invention is a flow chart of the teaching effect design adjustment program. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] See also Figure 1 The present invention provides a technical solution: an art education interactive teaching system comprising: The painting behavior trajectory module is based on students' painting behavior. It extracts brushstroke trajectories, coloring area boundaries, line starting points and end points, analyzes trajectory continuity and coloring coverage ratio, analyzes trajectory changes and the number of undoes, and performs filtering and segmentation classification to obtain painting behavior trajectory classification data. In the process of copying paintings, the original image must first be accurately captured and digitized, and the original image must be converted into a standardized data format, including information such as resolution, color value, and line boundaries. Next, the students' painting behavior is recorded, and the trajectory data of each stroke is collected through the device to obtain information such as the starting point, end point, curvature, thickness, and speed of the line during the painting process. Based on these data, the difference between the image drawn by the students and the original image can be compared. By analyzing the continuity of the trajectory, if the student's drawing path has frequent breakpoints or deviates from the original image, this means that the continuity of the painting process is insufficient and needs to be improved. The comparison of the boundaries of the colored area and the coverage ratio can evaluate the accuracy and completeness of the students' coloring. For example, if the student's colored area is 10% less than the original picture, it means that the coloring is incomplete and some details are missing. The number of undos reflects the frequency of students correcting mistakes during the drawing process. Too many undos indicate that the student's control is weak, resulting in frequent corrections. All data will be screened and filtered to exclude irrelevant factors, and then segmented analysis will be performed to extract the key stages of the drawing process, form the drawing behavior data of each stage, and compare it with the standard of the original picture, and finally obtain an accurate classification data of the drawing behavior trajectory; Table 1 Analysis data of students’ painting behavior trajectory student Number of trajectory continuity breakpoints Color coverage ratio (%) Number of undos (times) Student A 12 85 8 Student B 5 92 3 Table 1 lists the trajectory analysis data of Student A and Student B during the painting copying process. Student A has more breakpoints in his trajectory, a slightly lower color coverage ratio, and relatively more undo times, while Student B's overall performance is relatively stable.

[0019] The teaching task deviation diagnosis module analyzes the association between the painting stage goal and the task status based on the classification data of the painting behavior trajectory, compares the progress deviation value with the task ratio, generates a task status parameter set, combines the target operation record, evaluates the task deviation status and problem type, extracts the key items of the problem type, and establishes the teaching problem type results; In the process of copying tasks, it is necessary to first clarify the painting goals, such as "accurately copy the outline of the original image" or "the degree of matching between the colored area and the original image". According to the students' painting behavior data, the completion of the task at each stage is calculated and compared with the original image to obtain the progress deviation value. For example, in the copying process, if the deviation between the outline drawn by the student and the original image is greater than 2 mm, it can be considered that the painting progress at this stage deviates from the target. The relationship between the progress deviation and the task ratio can be compared by calculating the ratio of the student's painting completion to the preset target completion. For example, in the outline drawing task, the original image requires 100% of the outline lines to be completed. If the student completes 95%, the deviation value is 5%. Based on these deviation values, combined with the students' target operation records, the task deviation status is evaluated. For example, if the deviation value continues to increase, it may be necessary to further analyze the student's painting skills to find out the reason. If the deviation value is small and stable, it means that the student has copied the original image well. By extracting different types of painting problems, such as "outline lines are not aligned" or "uneven coloring", targeted improvement suggestions can be provided for teaching and a basis for optimizing the status of the task; Table 2 Results of student task deviation analysis student Profile deviation (mm) Color deviation (%) Main question types Student A 3.2 15 Outline misalignment Student B 1.1 5 Insufficient paint coverage As shown in Table 2, the contour deviation value of Student A is relatively high, and the main problem is that the contour lines are not aligned; while the overall deviation of Student B is smaller, and the problem is relatively minor, which is manifested in insufficient color coverage.

[0020] The teaching goal adjustment module is based on the teaching problem type results. By matching the task deviation status with the painting stage goal, it adjusts the task operation path and the goal distribution parameters to obtain the teaching goal setting data. It combines the distribution relationship between the goals and the task adjustment path to optimize the teaching task allocation and stage division, and establish a goal adjustment relationship diagram. According to the actual situation of the copying task, the painting task goal is matched with the student's deviation status. For example, if the student has obvious deviations in the "outline drawing" stage, but is close to the original picture goal in the "coloring" stage, the task path can be adjusted to give the student more time and guidance to help him correct the error in outline drawing. In order to better optimize the task goals, the relationship between the goals can be graphically represented to form a goal adjustment relationship diagram. For example, there is a certain dependency between the "outline drawing" goal and the "coloring" goal. If the former is not completed, the task difficulty and proportion of the latter should also be adjusted accordingly. Through this goal distribution relationship diagram, teachers can more effectively adjust teaching strategies to ensure the achievement of each task goal and enable students to copy the original picture more accurately. In actual operation, the task path can be dynamically adjusted according to the real-time feedback of the painting behavior. For example, if the student has a high degree of completion in the coloring stage, the difficulty of the next stage task can be increased. If the student encounters difficulties in the outline drawing stage, the task goal can be decomposed to provide more detailed guidance; Table 3 Suggestions for adjusting teaching objectives student Current stage deviation analysis Adjustment suggestions Target Priority Adjustment Student A High deviation in outline and medium deviation in coloring Increase outline drawing practice and reduce complex coloring tasks Prioritize Outline Drawing Student B Good outline and low color deviation Increase the difficulty of coloring tasks and add detail requirements Coloring and detail optimization are equally important Table 3 gives the goal adjustment suggestions for Student A and Student B in the painting task. Student A needs to focus on strengthening outline drawing training, while Student B can further increase the task difficulty of the coloring stage and optimize the detail performance.

[0021] The teaching effect trend analysis module extracts the stage task execution records based on the target adjustment relationship diagram, analyzes the task completion rate and behavior change trend data, compares the painting behavior status with the task target process, extracts the trend change key nodes and task association status, and establishes the teaching effect design adjustment plan; When extracting task records in the implementation phase, the completion rate needs to be extracted from the execution data of each task first. For example, if a student has completed 80% of the outline drawing and 50% of the coloring area, the task completion rate will reflect the overall progress of the student in the painting process. In the trend analysis of the change of the painting behavior state, the focus is on whether the student has obvious error correction fluctuations or behavior stagnation during the task process. For example, in the outline drawing stage, if the student retreats and corrects the line many times, it means that there is a large uncertainty or error. The teacher can adjust the teaching strategy based on this data to prevent the student from continuing to be affected by these errors during the coloring process. By comparing the painting state with the task goal process, it is possible to identify which task stages have large deviations and which links have potential for improvement, so as to propose adjustment plans in time. For example, if the student shows significant error fluctuations in the detail modification stage, the teacher can adjust the detail complexity of the task and gradually guide the student to reach the predetermined goal. By comparing the differences between the original picture and the student's work, the key trend nodes can be extracted to help students improve their painting skills and complete high-quality copying tasks.

[0022] The painting behavior trajectory classification data includes the brush stroke trajectory type, coloring area range, and line boundary information. The task status parameter set includes task progress deviation, task completion ratio, and task status identification. The teaching problem type results include deviation status classification, task problem category, and problem priority. The teaching goal setting data includes goal adjustment path, stage goal distribution, and task parameter configuration. The goal adjustment relationship diagram includes task allocation model, goal association path, and stage division relationship. The teaching effect design adjustment plan includes behavior trend nodes, task execution status, and course optimization guidelines.

[0023] See also Figure 2 ,The steps for obtaining the classification data of the painting behavior trajectory are as follows: Based on the students' painting behavior, the starting point coordinates, end point coordinates and continuous trajectory point data of the painting stroke trajectory are extracted, the length and direction changes of the trajectory are analyzed, and a set of trajectory point change parameters is generated; By recording the two-dimensional coordinate values ​​of the starting point and end point of each brush stroke in the painting behavior, the brush stroke trajectory points are grouped using the continuity characteristics of the strokes. For each segment of the trajectory, the Euclidean distance between the trajectory points is calculated point by point. The calculation method is to obtain the actual distance between the two points by summing the squares of the coordinate differences and then taking the square root. At the same time, the direction changes between adjacent trajectory points are recorded, and the angle is calculated by the vectors between the trajectory points to obtain a trajectory direction parameter set. In each direction parameter set, trajectory points with obvious direction changes are selected as segmentation marks to generate a multi-segment trajectory segment set. On this basis, the overall continuity characteristics of the trajectory are further analyzed, the density distribution of the trajectory is defined by the density of the trajectory points, the average distance and direction changes of each point in each segment of the trajectory are recorded, and a set of distance changes and direction changes between trajectory points is formed. The continuity parameters of the trajectory are generated by calculating the statistical characteristics of the set, and the respective characteristic values ​​are extracted according to the data change law of each segment of the trajectory to construct a brush stroke trajectory continuity parameter set, while retaining the two-dimensional coordinate data of the original starting point, end point and complete trajectory point.

[0024] Based on the trajectory point change parameter set, the smoothness and breakpoints between trajectory points are analyzed using the formula: ; The continuity score of the pen trajectory is calculated; in, represents the continuity score of the pen trajectory, Representative The angle between the trajectory points, Represents the length change between trajectory points, represents the smoothness weight, represents the length change weight, represents the total number of trajectory points; The benefit of the formula is that it combines two different trajectory characteristics into a continuous score by comprehensively analyzing the angle change and length change between trajectory points. and The introduction of allows the formula to be adjusted according to the characteristics of specific painting behavior on the impact of smoothness or length changes, which improves the flexibility of the analysis; Representative The direction angle between the trajectory points is calculated by the coordinate vector difference of the trajectory points; Represents the Euclidean distance between adjacent trajectory points, which is calculated by taking the square root of the sum of the squared coordinate differences of the trajectory points; and They represent the weights of angle change and length change respectively. By adjusting the weight ratio, specific trajectory characteristics can be highlighted; represents the trajectory continuity score, which is normalized by summing the weighted ratio of the angle change and length change between all trajectory points and dividing it by the total number of trajectory points; Represents the total number of trajectory points. Normalization is used to avoid the influence of different trajectory lengths on the score. Substituting specific parameters, the trajectory point coordinates are (1, 1), (2, 3), (3, 6), the angle changes are 20°, 40°, 60°, and the length changes are 2, 3, 4, respectively. The weight parameter , ; Substitute into the formula: ; The result shows that the continuity score of the trajectory is 33.8, which can be used to further classify the trajectory characteristics and for subsequent painting behavior analysis.

[0025] Call the brushstroke trajectory continuity score, combine the density parameters of the start and end points, filter the low-scoring trajectory segments and classify them into segments, segment and classify the trajectory segments by reading the score threshold, and adjust the attribution of the classified trajectory segments to obtain the painting behavior trajectory classification data; First, the trajectory score is divided into intervals, and low-scoring trajectory segments and high-scoring trajectory segments are defined based on the score intervals. The low-scoring trajectory segments are removed from the data set, and further analysis is performed on the high-scoring trajectory segments. The distance distribution between each trajectory point is recorded through the density parameter of the trajectory segment. The high-scoring trajectory segments are subdivided into dense trajectory segments and sparse trajectory segments according to the density of the trajectory points. The dense trajectory segments are further classified by analyzing the concentration of the direction changes of the trajectory points, and the sparse trajectory segments are classified by analyzing the discreteness of the direction changes. In the classification process, the classification mark is generated by combining the trajectory continuity score and the density distribution parameter. The direction change parameters of each trajectory are further classified and labeled. The classification results are combined with the trajectory score threshold, and the classification labels of the high-scoring dense trajectory segments and the high-scoring sparse trajectory segments are output to obtain the classification data of the painting behavior trajectory.

[0026] See also Figure 3 , the specific steps for obtaining the task status parameter set are: Based on the classification data of painting behavior trajectories, the time attribute and spatial position information of each trajectory point are extracted, the time difference and distance between adjacent points are identified, the time interval and displacement range are divided, the trajectory length and the number of trajectory points are analyzed, and the trajectory interval data is obtained; By collecting the timestamp of each trajectory point in the painting process and the spatial position information in the plane coordinate system, a time-space attribute pair is formed. At the same time, adjacent trajectory points are compared one by one, and the time difference and spatial distance between adjacent points are calculated. The judgment threshold of the time difference is set by the formula to distinguish different trajectory behaviors of fast movement and slow drawing. Each pair of trajectory points is divided into several intervals according to the time difference and distance distribution. For the time interval, after counting the time difference of all adjacent points, the time interval interval is divided according to the quartile method. At the same time, the displacement range of the interval is calculated with reference to the trajectory length. The interval parameters are set in combination with the actual length of the strokes commonly used in painting operations. When analyzing the trajectory length, the length of the line connecting the trajectory points is accumulated and calculated, and combined with the distribution density of the trajectory points, the distribution characteristics of the trajectories in different intervals are refined. For the analysis of the number of trajectory points, the trajectory information of different density areas is classified and marked according to the time difference and density between the trajectory points to obtain the trajectory interval data.

[0027] Based on the trajectory interval data, the number of task operations and the target number of operations in each interval are counted, the difference between the number of operations corresponding to the trajectory point and the target number is identified, the task completion ratio is analyzed, the task completion status is marked, and the task progress deviation data is obtained; The painting behavior in each trajectory interval is mapped through the corresponding task setting, and the specific number of operation tasks is extracted. The number of task operations is obtained through the matching results of the trajectory point and the target figure. By detecting whether the coverage range of each trajectory point overlaps with the preset painting area in the target figure point by point, it is determined whether it constitutes a valid task operation and accumulated statistics are performed. The target operation number is calculated by partition according to the teaching goal setting in the painting teaching and the drawing completion requirements of the target figure. For example, for the stroke operation of a specific figure, the ratio of the covered trajectory length to the expected stroke length of the teaching needs to be counted, and then added to the target operation number of the current interval in turn. When the difference between the corresponding operation number and the target number of the trajectory point is identified, it is directly marked by the difference between the operation number and the target number, and the task completion ratio is analyzed. The ratio of the operation number in each interval to the target number is calculated, and the task completion status is marked according to the preset completion status classification rules. For example, when the completion ratio is lower than a fixed threshold, it is marked as unfinished, otherwise it is marked as completed, and then the task progress deviation data is obtained.

[0028] Based on the task progress deviation data, the deviation change trend in the trajectory interval is analyzed, the deviation interval and the corresponding task are extracted, the deviation value and the task completion ratio are matched, the deviation impact parameters and the task execution status parameters are evaluated, and the task status parameter set is obtained; The trajectory interval data is analyzed through time series, and the change direction and rate of the deviation value are determined in combination with the time span of each trajectory interval. For example, the change amplitude of the task completion rate and the gradient of the increase or decrease of the deviation value are statistically analyzed in multiple continuous intervals, and marked as the deviation change trend. When extracting the deviation interval, the continuous interval with a deviation value higher or lower than a certain threshold is marked, and it is corresponded to the time node of the painting task. After matching the deviation value with the task completion ratio, the deviation state related to the task in the trajectory interval is compared with the target deviation value through the ratio value. Combined with the classification standard of task execution status in teaching, the deviation influencing parameters are extracted and evaluated. For example, the deviation value adds a negative weight to the interval with a completion ratio lower than a certain percentage to clarify the degree of influence of the deviation on task execution, and a comprehensive task state parameter set is generated to further optimize the teaching strategies and feedback mechanisms in interactive art education.

[0029] See also Figure 4 , the specific steps for obtaining the teaching question type results are: Screening the task status records in the task status parameter set, comparing the task status deviation values ​​with the reference values ​​of the target operation records item by item, screening the tasks whose deviation values ​​are higher than the reference values, and generating a data set of task deviation degrees; First, the task status deviation value is called, and the average of multiple monitoring records is used as the basic deviation value. At the same time, the reference value of the target operation record is obtained, and the average is calculated through multiple task execution records to establish a deviation threshold. When screening the task status, the absolute value of the deviation value is dynamically calculated. The ratio of the deviation value to the reference value is calculated for each record of the current task. The deviation is judged whether it exceeds the threshold range based on the upper and lower fluctuation range of the ratio of the deviation value to the dynamic threshold. The records that exceed the range are further screened through the quantitative ratio interval, and the records that do not meet the requirements are eliminated one by one based on this standard. Finally, tasks with relatively large deviation values ​​are extracted from the remaining records to generate a data set of the degree of task deviation.

[0030] Based on the data set of task deviation degree, the problem types corresponding to the deviation values ​​are classified, and the key parameters of the problems in the classification are analyzed, using the formula: ; Calculate the key parameter values ​​of the problem type; in, Represents the key parameter value of the problem type, represents the current parameter value of the deviation record, represents the target reference value, Represents the total number of deviation records, represents the weight adjustment coefficient, Represents the impact factor value of the problem type record, Represents the total number of factors affecting the problem type; The benefit of the formula is that it can improve the accuracy and relevance of problem classification by comprehensively calculating the influencing factors of the deviation value and the problem type at the same time and using the quantitative combination of multiple parameters to accurately extract key parameters; The current parameter value representing the deviation record is extracted by monitoring the continuous record of task state changes, Represents the target reference value, which is calculated by the historical average of the target operation records. Represents the total number of deviation records, set to the number of data points within the time series range of the record, The impact factor value representing the problem type is extracted by the classification label of the task record and weighted. Represents the number of influencing factors of the problem type, and counts the number of quantitative factors corresponding to each problem label in the task record. Represents the weight adjustment coefficient, which is dynamically set by fitting and analyzing the correlation between the deviation value and the influencing factor; Example of parameter substitution: set up , , , , , ; First calculate the sum of the absolute values ​​of the deviations: ; Calculate the mean of the deviations: ; Calculate the mean impact factor: ; Substituting into the formula: ; The result shows that the key parameter value of the question type is 1.31. By comprehensively calculating the factor influence of the deviation and the question type, the key parameter set of the question type is extracted, which can be used for subsequent classification operations.

[0031] Based on the key parameter values ​​of the question type, the parameter set is integrated according to the question type, and the logical correlation and influence pattern are analyzed, and used as the logical judgment standard to generate the teaching question type results; The parameter sets are integrated according to the problem type. During the integration process, the logical correlation of the parameters of each problem type is analyzed one by one. First, the key parameter sets contained in each type of problem are extracted, and the correlation analysis is performed on them. The correlation coefficients between the key parameters of each type of problem are calculated. According to the correlation, it is determined whether they belong to the same logical correlation mode. The parameter sets with high correlation are classified into one parameter category. Secondly, the influence pattern of the parameters is analyzed. By calculating the influence ratio of each type of parameter on the problem classification, an influence model is established. The classification standards are gradually adjusted to ensure the logical consistency between the parameters in the model. Finally, the problem classification is completed according to the logical correlation and classification influence ratio of all parameter sets to generate the teaching problem type results.

[0032] See also Figure 5 ,The specific steps for obtaining teaching objective setting data are as follows: Based on the results of teaching problem types, data parameters of task deviation status are extracted and grouped, the characteristics of target parameters of the painting stage are identified, the corresponding relationship between task deviation and stage target parameters is calculated, the deviation status matching priority is adjusted, and the correlation information between task deviation and stage target is obtained; By analyzing the performance characteristics of task deviations in different types of teaching problems, task deviation data parameters are extracted, including the time range, amplitude and frequency distribution of task deviations. According to the numerical range and characteristics of the deviations, the data parameters are divided into multiple groups, each of which corresponds to different task types and stage goal requirements. For example, groups with smaller deviation amplitudes but higher frequencies are classified as detail adjustment tasks, and groups with larger amplitudes but lower frequencies are classified as key path optimization tasks. The characteristics of painting stage target parameters are identified. Through the shape, structural complexity and required trajectory characteristics of the painting targets involved in the stage goal requirements, the parameter characteristics that match the target are extracted. For example, the complexity of the painting targets is identified by detecting the density of key points in the stage target. When calculating the correspondence between task deviations and stage target parameters, the matching degree of task deviations and target parameters is calculated, including the overlap of deviation data with the target time node on the time axis, and the ratio of deviation amplitude to target task completion ratio. According to the calculation results, the matching priority of the deviation state is adjusted, and the deviation state that has a greater impact on task completion is matched first, and finally the information associated with task deviations and stage goals is obtained.

[0033] Based on the task deviation and stage target correlation information, the task operation path is extracted and the target parameter distribution is calculated. The operation parameters in the task path are matched, the path parameters are dynamically adjusted, the weights in the operation path are assigned, and the execution order of the task path is adjusted to obtain the optimized path and target distribution parameters. The trajectory corresponding to the high-frequency area of ​​deviation is extracted as the critical path, and the target parameter distribution is calculated for each path, including the task density on the path, the matching degree of trajectory length and deviation distribution, etc. When matching the operation parameters in the task path, the deviation points in each path are matched with the target parameter points. The matching degree is calculated and the unmatched deviation points are marked through comparative analysis of the path length and trajectory point distribution. When the path parameters are dynamically adjusted, the operation order on the path is adjusted according to the path matching degree, such as giving priority to the path with higher matching degree. At the same time, the weight allocation rule is set according to the deviation amplitude, and the weight in the operation path is allocated. The execution priority of the operation path is controlled by the weight value. When adjusting the execution order of the task path, the path execution list is reordered based on the stage target priority. For example, the execution order of the target with strict time requirements is given priority. Finally, the optimized path and target distribution parameters are obtained for subsequent task adjustment.

[0034] Based on the optimization path and target distribution parameters, the task execution order in the distribution parameters is extracted, the target path of the painting stage is adjusted and redistributed, the execution parameter order of the task path is optimized, and the teaching target setting data is obtained by combining the operation weight of the target distribution; The optimized paths are sorted according to the weight values, and the starting and ending points of the task execution of each path are extracted. The continuity and logic of the path execution are ensured by rearranging the task order. When adjusting and redistributing the target path of the painting stage, the operations with low execution efficiency in the path are allocated to the paths with lower weights to improve the execution efficiency of the high-priority paths. The deviation accumulation of the painting tasks is reduced by optimizing the operation order in the task path, and the complex structure drawing is completed before the time period with frequent deviations to reduce the interference of complex tasks on subsequent operations. At the same time, combined with the operation weights of the target distribution, the parameter values ​​of the tasks at each stage in the path are weighted to ensure that complex tasks and simple tasks can achieve a balance in time distribution and execution efficiency. Finally, the teaching goal setting data is obtained to improve the task arrangement and goal setting strategies of interactive art teaching.

[0035] See also Figure 6 , the specific steps for obtaining the target adjustment relationship diagram are: Extract key features from the teaching goal setting data, analyze the distribution relationship between goals, use distribution parameters to count the spacing and distribution patterns of teaching goals, calculate the standard deviation of goal distribution and analyze the correlation between goals, and obtain the distribution relationship parameters between goals; Through monitoring the teaching objectives, a key indicator parameter set is constructed, which includes the difficulty coefficient, priority indicator, completion rate, time requirement, etc. of the objectives. By analyzing the differences between the objectives in the parameter set, a specific weight formula is used to calculate the weight ratio between the objectives. The weight ratio is used to generate the preliminary distribution characteristics between the objectives, and the distribution relationship between the objectives is analyzed. The distance between the objectives is further calculated in combination with the distribution relationship. The mean, variance and standard deviation of the distribution are obtained by calculating the distance. The standard deviation is used as a quantitative basis for measuring the distribution status of the objectives. Subsequently, the correlation between the objectives is analyzed according to the size of the standard deviation. The objectives with larger distribution distances are grouped and analyzed separately. When the distribution gap is small, they are merged to gradually form a clearer distribution pattern. By further refining the distribution pattern and combining statistical methods to analyze the difference coefficients between the objectives, the degree of correlation between the objectives is obtained, and finally the distribution relationship parameters between the objectives are obtained.

[0036] According to the distribution relationship parameters between targets, combined with the similarity parameters and adjustment weights between targets, the task allocation path is optimized through the formula: ; Get the total optimization value of task adjustment; in, represents the total optimization value of task adjustment, represents the similarity between targets, represents the distribution distance between targets, Represents the weight coefficient of task adjustment, represents the target quantity; The benefit of the formula is that by introducing the combination of the homogeneity parameter and the distribution distance parameter and adjusting the weight coefficient at the same time, it can effectively reflect the balance between the key objectives and secondary objectives in task allocation at different stages, and improve the scientificity and applicability of task allocation; Homogeneity parameter It is a correlation measure between targets, which can be obtained by calculating the Pearson correlation coefficient of the target key features. Assume ; Distribution distance is the absolute difference of the target feature, which can be calculated based on the weighted average of the target priority and the associated weight difference. Assume ; Weight coefficient Indicates the dynamic adjustment value of the goal priority, based on the historical data of goal completion, assuming ; Substituting the parameters into the formula: ; ; ; This result shows that the total optimization value of task adjustment It is 0.417, which indicates that the distribution relationship between teaching objectives has reached a relatively balanced state. It also reflects the priority distribution characteristics of each objective in the task adjustment path optimization, which is ultimately used to further optimize the allocation and adjustment of teaching tasks.

[0037] According to the total optimization value of task adjustment, the teaching task is divided into stages, the stage goals are grouped using the distribution relationship parameters and adjustment paths, the distribution ratio of the number of goals in each group is analyzed, the stages of the goals are gradually adjusted and matched, and a goal adjustment relationship diagram is generated; The distribution relationship parameters are used to group and analyze each teaching objective. The objective characteristics are extracted and the weight coefficients are calculated. The objective characteristics in each group are extracted and the ratio of the objective distribution in the group is calculated. The distribution ratio is composed of the relevance and completion of the objectives in the group and the difficulty distribution in the group. The ratio value is quantified by normalization. The objectives are grouped and sorted according to the distribution ratio. A phased allocation strategy is selected based on the objective sorting results. By comparing the objective characteristics in the phased grouping with the priority matching in the task adjustment path, the objectives in the group that meet the priority are allocated to the current stage, and the remaining objectives are allocated to the subsequent stages in turn. If the objective characteristics in the stage are unbalanced, the objectives are adjusted to the stage to ensure that the number and priority of the objectives in the stage meet the distribution ratio requirements. By continuously adjusting the stage distribution ratio, a goal adjustment relationship diagram is finally generated.

[0038] See also Figure 7 , the specific steps for obtaining the teaching effect design adjustment plan are: Based on the target adjustment relationship diagram, extract the task completion ratio and behavior change trend data, compare the behavior status with the task target process, analyze the change of the task completion ratio in sections, identify the correlation between the change of the task completion ratio and the key features of the behavior trend, and obtain the matching relationship between the task completion ratio and the behavior trend; First, it is necessary to clean the data in the stage task execution records. By screening outliers in the task status records (such as task completion time that exceeds the expected range and behavior record data that exceeds the upper and lower limits), interference data is eliminated and normal data is classified into the task status record table. Then, the task completion rate data is extracted. The task completion rate is obtained by calculating the ratio of the actual completion time of each task to the target time. The behavior change trend data is obtained by extracting and analyzing the key features of the user behavior records. The standard deviation and distribution range of the behavior change trend are calculated by using the quantitative statistics of the behavior frequency and behavior type within the time period. A comparative analysis is conducted based on the mean change of the ratio and the fluctuation characteristics of the trend. The change in the completion rate is correlated and matched with the change in the behavior trend data, and the key correlation features between the two are gradually extracted to finally form a matching relationship between the task completion rate and the behavior trend.

[0039] Based on the matching relationship between task completion ratio and behavior trend, combined with the key nodes of task process, the correlation analysis of stage process goals is carried out to extract the key nodes of trend change and task correlation status, using the formula: ; Calculate and obtain the matching status value of the trend change and the task; in, Represents the matching status value of trend change and task, Represents the cumulative value of the change in task completion rate, The standard deviation value representing the trend of behavior change, Represents the weight of the stage task progress, is the dynamic adjustment coefficient; The benefit of the formula is that by introducing the cumulative value of the completion rate change and the standard deviation of the behavior change trend, combined with the weight coefficient of the task goal, it can accurately extract the key nodes in the matching state of the task and the behavior change trend, and improve the accuracy of the adjustment of the teaching goal; (Completion ratio cumulative value): calculated by calculating the completion ratio difference of each task and accumulating it. For example, if the completion ratio of task 1 is 80%, the completion ratio of task 2 is 90%, and the completion ratio of task 3 is 70%, then ; (Standard deviation of behavior change trend): Calculate the standard deviation by analyzing the fluctuation of behavior records within a time period. For example, if the change in behavior data is [3, 5, 4, 6, 4], then the deviation value is ; (Weight coefficient of task process target): Dynamic weight value is set according to the importance and priority of task target. For example, if the weight of task 1 is 1.5, the weight of task 2 is 1.3, and the weight of task 3 is 1.2, then the average value is taken. ; (Weight adjustment coefficient): Combined with the dynamic characteristics of task distribution, for example, the adjustment coefficient is 1.2; Substituting the parameters into the formula: ; ; Result analysis: Since negative values ​​appear, it does not conform to the actual task status adjustment logic. It is necessary to re-verify the data extraction and the positive and negative value of the deviation, adjust the trend node extraction conditions or correct the weight coefficient.

[0040] According to the matching status value of trend changes and tasks, and based on the completion of task goals, matching status data is extracted, and the task status of the differentiated stages is compared and analyzed, the correlation weights of staged teaching tasks and behavioral changes are adjusted, and a teaching effect design adjustment plan is established; Firstly, the ratio data of task completion status and the matching status of trend change nodes are grouped and analyzed. Through the task execution process records, the key nodes of behavioral trend of each task are extracted. The actual deviation value of its completion ratio and the theoretical deviation value of the target ratio are compared. The node deviation value is converted into a weight adjustment factor, and the weight factor is dynamically adjusted with the target completion time. The difference value between each node is obtained through multi-stage comparative analysis. Then, the node status of each stage task is classified, and the completion ratio deviation and weight change results are used as the basis for stage division. The stage task status matching is dynamically optimized. Finally, the nodes of each stage are summarized, and the teaching effect design adjustment plan is output.

[0041] The interactive teaching method for art education is implemented based on the interactive teaching system for art education, and includes the following steps: S1: Based on the students’ painting behavior, we extract the brush stroke trajectory, the boundary of the coloring area, the starting point and end point of the line, analyze the length and direction changes of the path, classify the trajectory features by segments, extract the boundary contour of the closed area, classify the features based on the pixel coverage ratio, and generate the distribution results of the painting trajectory features; S2: Based on the distribution results of the painting trajectory features, extract the associated trajectory path, compare the direction change value and the target offset, analyze the coverage characteristics of the unfinished area, analyze the path density and direction distribution, extract the associated data of the target insufficient coverage area and the path offset, classify the path offset area, and obtain the characteristics of the painting target deviation area; S3: Based on the characteristics of the deviation area of ​​the drawing target, adjust the direction offset value and trajectory length of the path node, correct the distribution relationship between the nodes, compare the coverage range with the target operation parameters, optimize the matching of the task trajectory with the adjusted target distribution, and generate the stage target adjustment path map; S4: Adjust the path diagram based on the stage goal, compare the distance and distribution changes between nodes, calculate the path association value within the coverage range of the target node, extract the offset parameters and trajectory adjustment results of the node distribution change, screen the coverage data of the key change nodes, and establish an adjustment plan for the teaching effect design.

[0042] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An interactive teaching system for art education, characterized in that: The system comprises: The painting behavior trajectory module is based on students' painting behavior. It extracts brushstroke trajectories, coloring area boundaries, line starting points and end points, analyzes trajectory continuity and coloring coverage ratio, analyzes trajectory changes and the number of undoes, and performs filtering and segmentation classification to obtain painting behavior trajectory classification data. The teaching task deviation diagnosis module analyzes the association between the painting stage goal and the task status based on the painting behavior trajectory classification data, compares the progress deviation value and the task ratio, generates a task status parameter set, combines the target operation record, evaluates the task deviation status and problem type, extracts the key items of the problem type, and establishes the teaching problem type result; The teaching goal adjustment module adjusts the task operation path and the target distribution parameters based on the teaching problem type results, matches the task deviation state with the painting stage target, obtains the teaching goal setting data, combines the distribution relationship between the targets and the task adjustment path, optimizes the teaching task allocation and stage division, and establishes a target adjustment relationship diagram; The teaching effect trend analysis module extracts the stage task execution records based on the target adjustment relationship diagram, analyzes the task completion rate and behavior change trend data, compares the painting behavior status with the task target progress, extracts the key nodes of the trend change and the task association status, and establishes a teaching effect design adjustment plan.

2. The interactive teaching system for art education according to claim 1 is characterized in that: The steps for obtaining the painting behavior trajectory classification data are specifically as follows: Based on the students' painting behavior, the starting point coordinates, end point coordinates and continuous trajectory point data of the painting stroke trajectory are extracted, the length and direction changes of the trajectory are analyzed, and a set of trajectory point change parameters is generated; Based on the trajectory point change parameter set, the smoothness and breakpoints between trajectory points are analyzed using the formula: ； The continuity score of the pen trajectory is calculated; in, represents the pen trajectory continuity score, Representative The angle between the trajectory points, Represents the length change between trajectory points, represents the smoothness weight, represents the length change weight, represents the total number of trajectory points; The brushstroke trajectory continuity score is called, combined with the density parameters of the starting point and the end point, the low-scoring trajectory segments are filtered and classified into segments, the trajectory segments are segmented and classified by reading the scoring threshold, and the attribution of the classified trajectory segments is adjusted to obtain the painting behavior trajectory classification data.

3. The interactive teaching system for art education according to claim 2 is characterized in that: The steps for obtaining the task status parameter set are specifically as follows: Based on the painting behavior trajectory classification data, extract the time attribute and spatial position information of each trajectory point, identify the time difference and distance between adjacent points, divide the time interval and displacement range interval, analyze the trajectory length and the number of trajectory points, and obtain trajectory interval data; Based on the trajectory interval data, the number of task operations and the target number of operations in each interval are counted, the difference between the number of operations corresponding to the trajectory point and the target number is identified, the task completion ratio is analyzed, the task completion status is marked, and the task progress deviation data is obtained; Based on the task progress deviation data, the deviation change trend in the trajectory interval is analyzed, the deviation interval and the corresponding task are extracted, the deviation value and the task completion ratio are matched, the deviation impact parameters and the task execution state parameters are evaluated, and the task state parameter set is obtained.

4. The interactive teaching system for art education according to claim 3 is characterized in that: The steps for obtaining the teaching question type results are specifically as follows: Screening the task status records in the task status parameter set, comparing the task status deviation values ​​with the reference values ​​of the target operation records item by item, screening the tasks whose deviation values ​​are higher than the reference values, and generating a data set of task deviation degrees; Based on the data set of the task deviation degree, the problem types corresponding to the deviation values ​​are classified, and the key parameters of the problems in the classification are analyzed, using the formula: ； Calculate the key parameter values ​​of the problem type; in, Represents the key parameter value of the problem type, represents the current parameter value of the deviation record, represents the target reference value, Represents the total number of deviation records, represents the weight adjustment coefficient, Represents the impact factor value of the problem type record, Represents the total number of factors affecting the problem type; Based on the key parameter values ​​of the question type, the parameter set is integrated according to the question type, and the logical correlation and impact pattern are analyzed, and used as a logical judgment standard to generate teaching question type results.

5. The interactive teaching system for art education according to claim 4 is characterized in that: The steps for obtaining the teaching objective setting data are specifically as follows: Based on the teaching problem type results, data parameters of task deviation status are extracted and grouped, the characteristics of target parameters of the painting stage are identified, the corresponding relationship between task deviation and stage target parameters is calculated, the deviation status matching priority is adjusted, and the association information between task deviation and stage target is obtained; Based on the task deviation and stage target association information, extract the task operation path and calculate the target parameter distribution, match the operation parameters in the task path, dynamically adjust the path parameters, assign weights in the operation path, adjust the execution order of the task path, and obtain the optimized path and target distribution parameters; Based on the optimization path and target distribution parameters, the task execution order in the distribution parameters is extracted, the target path of the painting stage is adjusted and redistributed, the execution parameter order of the task path is optimized, and the teaching target setting data is obtained in combination with the operation weight of the target distribution.

6. The interactive teaching system for art education according to claim 5, characterized in that: The steps for obtaining the target adjustment relationship diagram are specifically as follows: Extracting key features from the teaching target setting data, analyzing the distribution relationship between targets, using distribution parameters to count the spacing and distribution pattern of teaching targets, calculating the standard deviation of target distribution and analyzing the correlation between targets, and obtaining distribution relationship parameters between targets; According to the distribution relationship parameters between the targets, combined with the similarity parameters and adjustment weights between the targets, the task allocation path is optimized through the formula: ； Get the total optimization value of task adjustment; in, represents the total optimization value of task adjustment, represents the similarity between targets, represents the distribution distance between targets, Represents the weight coefficient of task adjustment, represents the target quantity; According to the total optimization value of the task adjustment, the teaching task is carried out in stages, the stage goals are grouped using distribution relationship parameters and adjustment paths, the distribution ratio of the number of goals in each group is analyzed, the stages of the goals are gradually adjusted and matched, and a goal adjustment relationship diagram is generated.

7. The interactive teaching system for art education according to claim 6, characterized in that: The steps for obtaining the teaching effect design adjustment plan are specifically as follows: Based on the target adjustment relationship diagram, extract the task completion ratio and behavior change trend data, compare the behavior status with the task target process, analyze the change of the task completion ratio in sections, identify the correlation between the change of the task completion ratio and the key features of the behavior trend, and obtain the matching relationship between the task completion ratio and the behavior trend; Based on the matching relationship between the task completion ratio and the behavior trend, combined with the key nodes of the task process, the correlation analysis of the stage process goals is carried out to extract the key nodes of the trend change and the task correlation status, using the formula: ； Calculate and obtain the matching status value of the trend change and the task; in, Represents the matching status value of trend change and task, Represents the cumulative value of the change in task completion rate, The standard deviation value representing the trend of behavior change, Represents the weight of the stage task progress, is the dynamic adjustment coefficient; According to the matching status value of the trend change and the task, and based on the completion of the task objectives, the matching status data is extracted, the task status of the differentiated stages is compared and analyzed, the correlation weights between the staged teaching tasks and the behavioral changes are adjusted, and a teaching effect design adjustment plan is established.

8. An interactive teaching method for art education, characterized in that: The interactive teaching system for art education according to any one of claims 1 to 7 is implemented, comprising the following steps: S1: Based on the students’ painting behavior, we extract the brush stroke trajectory, the boundary of the coloring area, the starting point and end point of the line, analyze the length and direction changes of the path, classify the trajectory features by segments, extract the boundary contour of the closed area, classify the features based on the pixel coverage ratio, and generate the distribution results of the painting trajectory features; S2: Based on the distribution result of the painting trajectory feature, extract the associated trajectory path, compare the direction change value and the target offset, analyze the coverage characteristics of the unfinished area, analyze the path density and direction distribution, extract the associated data of the target insufficient coverage area and the path offset, classify the path offset area, and obtain the characteristics of the painting target deviation area; S3: Based on the deviation area characteristics of the drawing target, the direction offset value and trajectory length of the path node are adjusted, the distribution relationship between the nodes is corrected, the coverage range is compared with the operation parameters of the target, the task trajectory is matched and optimized with the adjusted target distribution, and a stage target adjustment path diagram is generated; S4: Based on the stage target adjustment path diagram, compare the distance and distribution changes between nodes, calculate the path association value within the coverage range of the target node, extract the offset parameters and trajectory adjustment results of the node distribution changes, screen the coverage data of the key change nodes, and establish a teaching effect design adjustment plan.

Images