Multi-dimensional teaching competency assessment intervention adjustment analysis method and system
By using a multi-dimensional teaching competence assessment method, combining teaching foundation and efficacy perception data, teaching characteristic data is generated, and cluster analysis and trajectory time series characteristic assessment are performed. This solves the problem that dynamic efficacy is difficult to reflect in traditional assessments, and achieves more accurate teaching ability assessment and optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHONGQING NORMAL UNIVERSITY
- Filing Date
- 2026-01-14
- Publication Date
- 2026-04-24
AI Technical Summary
Traditional teaching competence assessments rely on static data, which makes it difficult to reflect the dynamic effectiveness of the teaching process. The assessment dimensions have a low degree of matching with actual teaching abilities and cannot accurately capture the strengths and weaknesses of different teachers.
By acquiring basic teaching data and efficacy perception data, teaching characteristic data is generated, cluster analysis is performed to determine the dimensions of teaching ability, and combined with trajectory time series characteristics and constraint data, teaching competence assessment intervention and adjustment plans are generated. The optimal plan is then selected using the adaptation loss coefficient.
This approach enables more realistic teaching assessments, enhances the relevance and feasibility of assessments, ensures that intervention plans conform to assessment logic and objective constraints, while also taking into account the subjective preferences of the assessment subjects, and optimizes teaching abilities.
Smart Images
Figure CN121920899A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of teaching technology, and more specifically, to a multi-dimensional teaching competence assessment intervention and regulation analysis method and system. Background Technology
[0002] Traditional teaching competence assessments rely heavily on static teaching data such as teaching outcomes and lesson plan quality, while rarely incorporating dynamic performance data such as behavioral patterns and teacher-student perception preferences during the teaching process. This makes it difficult for assessment results to truly reflect the actual performance in the teaching setting. For example, assessing teacher competence solely based on student exam scores fails to reflect differences in teachers' process-related abilities such as classroom interaction and pacing, easily leading to a one-sided assessment.
[0003] Traditional assessments often employ a uniform, fixed framework for competency dimensions, failing to dynamically categorize them based on the individualized teaching behaviors of the assessed individuals. This results in a low degree of alignment between assessment dimensions and actual teaching abilities. For instance, teachers of different subjects and with different teaching styles should inherently possess different core teaching competency dimensions. However, traditional approaches often cover all subjects with fixed dimensions such as instructional design and classroom organization, making it difficult to accurately capture the strengths and weaknesses of different teachers. Summary of the Invention
[0004] In view of the shortcomings of existing technologies, the purpose of this invention is to provide a multi-dimensional teaching competence assessment, intervention, regulation, and analysis method and system.
[0005] To achieve the above objectives, the present invention provides the following technical solution: A multidimensional method for assessing and moderating teaching competence, comprising the following steps: Acquire the teaching basic data and efficacy perception data of the evaluation subjects; wherein, the teaching basic data includes teaching ability parameters and teaching implementation constraint data, and the efficacy perception data includes teaching behavior trajectory data and perception preference text information; Teaching characteristic data of the assessment object is generated based on teaching ability parameters, and behavioral trajectory feature points are obtained based on teaching behavior trajectory data; cluster analysis is performed on the teaching behavior trajectory data to obtain the teaching ability dimension of the assessment object. The trajectory characteristics of teaching ability dimension are obtained by analyzing the trajectory data of teaching behavior; the dimension weight value of teaching ability dimension is obtained by analyzing the trajectory time characteristics; and the adjustment constraints of assessment intervention are obtained by analyzing the teaching implementation constraint data and the dimension weight value of teaching ability dimension. The intervention and adjustment plan for teaching competency assessment will be generated by adjusting constraints, dimensional weight values, and perceptual preference text information. The adjustment constraint parameters for the assessment intervention are obtained based on the adjustment constraints; the implementation parameters of the teaching competence assessment intervention adjustment scheme are obtained; the adaptation loss coefficient of the assessment intervention adjustment scheme is obtained based on the implementation parameters and adjustment constraint parameters; and the set of teaching competence assessment intervention adjustment schemes for the assessment object is output based on the adaptation loss coefficient.
[0006] Preferably, generating teaching characteristic data of the assessment subject based on teaching ability parameters specifically includes the following steps: The teaching ability parameters include the teaching ability structure of the assessment subject; Teaching feature data is generated based on the teaching ability structure; wherein, the teaching feature data includes feature point density.
[0007] Preferably, obtaining behavioral trajectory feature points based on teaching behavior trajectory data specifically includes the following steps: Set the feature extraction frequency, and obtain the ability status of teaching behavior trajectory in teaching feature data based on the feature extraction frequency; Based on the assessment of the subject's abilities, behavioral trajectory feature points in the teaching characteristic data are obtained.
[0008] Preferably, cluster analysis is performed on the teaching behavior trajectory data to obtain the teaching ability dimensions of the evaluation subjects, specifically including the following steps: The feature discrimination boundary of the initial group is obtained by processing the teaching behavior trajectory data; Trajectory groups are obtained by integrating the initial groups based on the feature-distinguishing boundaries; After obtaining the teaching implementation scenario information corresponding to the trajectory group, establish the correspondence between each trajectory group and the teaching implementation scenario; Based on the common trajectory characteristics of each trajectory group and the corresponding teaching implementation scenario information, the teaching ability representation attributes corresponding to each trajectory group are extracted; Based on the differences in the representation attributes of teaching ability, the teaching ability dimensions of the assessment objects are obtained by dividing the groups of each trajectory into dimensions.
[0009] Preferably, the initial group's feature discrimination boundary is obtained by processing the teaching behavior trajectory data, specifically including the following steps: Based on the teaching implementation process, the teaching behavior trajectory data is broken down into trajectory segments, and the trajectory length, trajectory direction and trajectory dwell characteristics of each trajectory segment are extracted to form a trajectory feature set; The trajectory feature set is processed by feature association to obtain the association strength between features of different trajectory segments, and the trajectory features that meet the preset requirements are selected to form the target feature group; Based on the target feature group, each trajectory segment is grouped to obtain an initial group. The feature distinction boundary of the initial group is determined by comparing the differences in common trajectory features of each initial group.
[0010] Preferably, the analysis of teaching behavior trajectory data to obtain the trajectory temporal characteristics of the teaching ability dimension specifically includes the following steps: The behavioral sequence of teaching behavior trajectory data is used to form a temporal behavior chain; the succession relationship between each behavior is extracted through the temporal behavior chain, and the triggering association of the preceding behavior to the subsequent behavior is clarified based on the succession relationship to obtain the behavior succession association information; The teaching process is divided into temporal stages based on the temporal behavior chain, with each temporal stage corresponding to different aspects of the teaching implementation; the frequency of occurrence of various behaviors in each temporal stage is counted, and the behavioral density of each temporal stage is obtained based on the frequency of occurrence and the continuous progress of behaviors in the temporal behavior chain. Determine the tightness of behavioral connections within different time periods based on behavioral connection information; determine the dominant behavioral type within each time period by combining the behavioral density of each time period. By tracing the evolution of dominant behavior types at various time stages, capturing the replacement nodes of dominant behavior types, and clarifying the transitional characteristics of dominant behaviors before and after the replacement nodes, the evolution of dominant behavior types can be judged based on the transitional characteristics to obtain the temporal pattern of behavior evolution. By combining the intensity of behavior, the closeness of the connection between behaviors, and the temporal pattern of behavior evolution in each time stage, temporal correlation features corresponding to each teaching ability dimension are extracted. Integrate the temporal correlation features of each time series to form the trajectory temporal features of each teaching ability dimension.
[0011] Preferably, the dimensional weight values of the teaching ability dimension are obtained based on trajectory time-series feature analysis, specifically including the following steps: The dimensional application information of the evaluation object in each teaching ability dimension is obtained based on the trajectory time sequence characteristics; wherein, the dimensional application information includes the dimensional application duration of the evaluation object in each teaching ability dimension; Obtain the total application time of the assessment subjects across all teaching ability dimensions, and obtain the dimension application time percentage based on the dimension application time and the total dimension application time; The dimension weight value of the teaching ability dimension is obtained based on the proportion of application time of each dimension.
[0012] Preferably, the moderating constraints for the assessment intervention are obtained based on the teaching implementation constraint data and the dimensional weights of the teaching ability dimension, specifically including the following steps: Based on the teaching implementation constraint data, we obtain the constraint type elements and the constraint range of the elements; based on the constraint type elements and the constraint range of the elements, we obtain the implementation safety constraints for the evaluation intervention. Set intervention intensity level ranges and intervention frequency ranges; each intervention intensity level range corresponds to an intervention intensity level; each intervention frequency range corresponds to an intervention implementation frequency; The intervention intensity level is obtained by comparing the dimensional weight value of the teaching ability dimension with the intervention intensity level range; the intervention implementation frequency is obtained by comparing the dimensional weight value of the teaching ability dimension with the intervention frequency range; and the intervention resource ratio is obtained based on the dimensional weight value of the teaching ability dimension and the total assessment weight ratio of the teaching ability dimension. The dimensional constraints of each teaching ability dimension are obtained based on the intervention intensity level, intervention implementation frequency, and intervention resource ratio corresponding to each teaching ability dimension. The regulatory constraints for evaluating interventions are obtained based on the implementation of safety constraints and dimensional constraints.
[0013] Preferably, the adaptation loss coefficient for evaluating the intervention and adjustment scheme is obtained based on the implementation parameters and adjustment constraint parameters, specifically as follows: The implementation parameters and constraint parameters are compared to obtain the adaptation loss coefficient corresponding to the evaluation intervention and adjustment scheme.
[0014] A multi-dimensional teaching competence assessment, intervention, and adjustment analysis system, comprising: Acquisition Module: Acquires the teaching basic data and efficacy perception data of the evaluation object; wherein, the teaching basic data includes teaching ability parameters and teaching implementation constraint data, and the efficacy perception data includes teaching behavior trajectory data and perception preference text information; Analysis module: Generates teaching characteristic data of the assessment object based on teaching ability parameters, obtains behavioral trajectory feature points based on teaching behavior trajectory data; performs cluster analysis on teaching behavior trajectory data to obtain the teaching ability dimension of the assessment object; Processing module: Analyzes teaching behavior trajectory data to obtain trajectory temporal characteristics of the teaching ability dimension; analyzes the trajectory temporal characteristics to obtain the dimension weight value of the teaching ability dimension; and obtains the adjustment constraints of the assessment intervention based on the teaching implementation constraint data and the dimension weight value of the teaching ability dimension. Generation module: Generates an intervention and adjustment plan for teaching competency assessment by adjusting constraints, dimensional weight values, and perceptual preference text information; Output module: Obtains the adjustment constraint parameters of the assessment intervention based on the adjustment constraint conditions; obtains the implementation parameters of the teaching competence assessment intervention adjustment scheme; obtains the adaptation loss coefficient of the assessment intervention adjustment scheme based on the implementation parameters and adjustment constraint parameters; and outputs the set of teaching competence assessment intervention adjustment schemes for the assessment object based on the adaptation loss coefficient.
[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention covers both basic teaching data and perceived effectiveness data, including objective parameters such as teaching ability and implementation constraints, as well as subjective process information such as behavioral trajectories and perceived preferences. This avoids the one-sidedness of a single data dimension and more realistically reflects the actual teaching situation of the assessed individuals. By generating teaching characteristic data from teaching ability parameters and performing cluster analysis on behavioral trajectory data to obtain teaching ability dimensions, the assessment dimensions of teaching competence are made more aligned with the individualized performance of the assessed individuals. Dimension weight values are determined based on trajectory temporal characteristics, and the design of adjustment constraints is obtained by combining constraint data. This ensures that the generation of intervention plans has both data-supported weighting and objective boundary limitations. For example, if a teacher has a higher weight value in the knowledge delivery dimension, the intervention plan will allocate more resources accordingly, while also adhering to constraints such as teaching time and equipment conditions, preventing the intervention plan from deviating from the actual executable scope of teaching and improving its feasibility. The process of combining adjustment constraints, dimension weights, and perceived preferences to generate intervention plans, and then filtering the plan set through an adaptation loss coefficient, ensures that the plans conform to the assessment logic and objective constraints, while also taking into account the subjective preferences of the assessed individuals. Furthermore, the adaptation loss coefficient selects the plan with the highest degree of fit to the constraints. Effectively enhance the practical value of teaching assessment and intervention, and help the assessed individuals optimize their teaching abilities in a targeted manner. Attached Figure Description
[0016] Figure 1 A schematic diagram illustrating the steps of a multi-dimensional teaching competence assessment intervention and regulation analysis method provided in this embodiment of the invention; Figure 2 This is a schematic diagram of a multi-dimensional teaching competence assessment, intervention, and adjustment analysis system provided in this embodiment of the invention. Detailed Implementation
[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.
[0019] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.
[0020] Reference Figures 1-2 As shown.
[0021] The embodiments further illustrate the multi-dimensional teaching competence assessment intervention and regulation analysis method and system proposed in this invention.
[0022] A multidimensional method for assessing and moderating teaching competence, comprising the following steps: Acquire basic teaching data and perceived efficacy data of the assessment subjects; among which, basic teaching data includes teaching ability parameters and teaching implementation constraint data, and perceived efficacy data includes teaching behavior trajectory data and perceived preference text information; Teaching characteristic data of the assessment object is generated based on teaching ability parameters, and behavioral trajectory feature points are obtained based on teaching behavior trajectory data; cluster analysis is performed on the teaching behavior trajectory data to obtain the teaching ability dimension of the assessment object. The trajectory characteristics of teaching ability dimension are obtained by analyzing the trajectory data of teaching behavior; the dimension weight value of teaching ability dimension is obtained by analyzing the trajectory time characteristics; and the adjustment constraints of assessment intervention are obtained by analyzing the teaching implementation constraint data and the dimension weight value of teaching ability dimension. The intervention and adjustment plan for teaching competency assessment will be generated by adjusting constraints, dimensional weight values, and perceptual preference text information. Based on the adjustment constraints, the adjustment constraint parameters for the assessment intervention are obtained; the implementation parameters of the teaching competence assessment intervention adjustment scheme are obtained, and the fit loss coefficient of the assessment intervention adjustment scheme is obtained based on the implementation parameters and the adjustment constraint parameters, specifically: The implementation parameters and constraint parameters are compared to obtain the adaptation loss coefficient corresponding to the evaluation intervention and adjustment scheme.
[0023] The set of intervention and adjustment schemes for assessing the teaching competence of the assessment subjects is output based on the adaptation loss coefficient.
[0024] The adjustment of constraints, dimensional weights, and perceived preferences is used to generate a moderating plan for teaching competence assessment intervention. The constraints are the boundary rules that the assessment intervention must follow; the dimensional weights reflect the importance of different teaching ability dimensions in the assessment; and the perceived preferences reflect the subjective tendencies of the assessed individuals in teaching, such as teachers' preference for interactive teaching methods. These constraints, dimensional weights, and perceived preferences construct a preliminary moderating plan for teaching competence assessment intervention, ensuring that the plan conforms to both objective constraints and matches the actual characteristics and preferences of the assessed individuals.
[0025] Quantifiable adjustment constraint parameters are extracted from existing adjustment constraints. These parameters are the specific numerical representations of the constraints, such as the upper limit of intervention intensity and the interval range of intervention frequency. Implementation parameters for the actual execution of the preliminary teaching competency assessment intervention adjustment plan are extracted, such as the specific numerical values of intervention intensity and the specific frequency of intervention implementation. The implementation parameters are compared with the adjustment constraint parameters. The adaptation loss coefficient is calculated as Σ(|implementation parameter i - adjustment constraint parameter i| / adjustment constraint parameter i) / n, where i represents different types of parameters and n represents the number of parameters involved in the comparison. If the range of intervention intensity in the adjustment constraint parameters is 3-5, while the intervention intensity in the implementation parameters is set to 6, then the deviation value corresponding to this parameter is |6-5| / 5 = 0.2. If there are deviation values for other parameters, averaging these deviation values yields the adaptation loss coefficient for the plan.
[0026] The fit loss coefficient reflects the degree to which the initial plan fits the constraints; the smaller the fit loss coefficient, the better the plan meets the constraints. In practice, multiple different initial intervention and adjustment plans are generated, and the fit loss coefficient of each plan is calculated. The plans are then screened and ranked based on the size of the fit loss coefficient. Plans with fit loss coefficients within a reasonable range are integrated into a set of intervention and adjustment plans for assessing the teaching competence of the evaluation subjects, so that the optimal plan can be selected and implemented according to actual needs.
[0027] The process of generating teaching characteristic data for assessment subjects based on teaching ability parameters includes the following steps: Teaching ability parameters include the teaching ability structure of the assessment subject; Teaching feature data is generated based on the teaching ability structure; the teaching feature data includes feature point density.
[0028] The composition of teaching ability parameters is the teaching ability structure of the assessment object. The teaching ability structure is a combination framework of the assessment object's various abilities in the teaching field. For example, a teacher's teaching ability structure includes different ability modules such as instructional design ability, classroom interaction ability, and homework feedback ability. Each module corresponds to its ability performance in different stages of the teaching process.
[0029] Teaching feature data is generated based on the teaching ability structure, and this data includes feature point density. Feature point density is a parameter used to quantify the distribution and concentration of each ability module in the teaching ability structure. Feature point density = number of feature points corresponding to a certain ability module in the teaching ability structure ÷ teaching session duration corresponding to that ability module.
[0030] If the teaching ability structure of the assessed subject includes a classroom interaction ability module, and the corresponding teaching segment for this module lasts 20 minutes, and the number of feature points corresponding to the assessed subject's classroom questioning and group discussion guidance interactive behaviors within this segment is 15, then the feature point density for this module is 15 ÷ 20 = 0.75. Feature point density can clearly reflect the intensity of the assessed subject's behavior in a certain teaching ability module, thus allowing the teaching feature data to more accurately correspond to the actual performance of their teaching ability structure.
[0031] The process of obtaining behavioral trajectory feature points based on teaching behavior trajectory data includes the following steps: Set the feature extraction frequency, and obtain the ability status of teaching behavior trajectory in teaching feature data based on the feature extraction frequency; Based on the assessment of the subject's abilities, behavioral trajectory feature points in the teaching characteristic data are obtained.
[0032] Feature extraction frequency refers to the time interval at which features are collected from teaching behavior trajectory data during the teaching process. For example, feature data corresponding to teaching behaviors may be extracted every 5 minutes. Based on the set feature extraction frequency, the performance of teaching behavior trajectories in teaching feature data is sampled and judged to obtain the corresponding ability status. Ability status refers to the performance level of teaching behavior trajectories under the corresponding teaching feature dimension. Taking the feature point density in teaching feature data as an example, if the feature extraction frequency is once every 5 minutes, and the number of feature points corresponding to the teaching behavior trajectory is 4 within a 5-minute sampling interval, and the teaching segment duration corresponding to this interval is 5 minutes, then the feature point density in this interval is 4 ÷ 5 = 0.8. Combining this with the standard threshold for this teaching feature dimension, such as a standard feature point density of 0.6, it can be judged that the ability status in this interval is better than the standard level.
[0033] Based on this ability status, behavioral trajectory feature points of the assessment subject in the teaching characteristic data are determined. For example, if the ability status corresponding to a feature point density of 0.8 in the above sampling interval is better than the standard level, then the teaching behavior trajectory position corresponding to this sampling time will be marked as a behavioral trajectory feature point. This feature point contains both the teaching behavior trajectory information at this time and is associated with the corresponding ability status.
[0034] Cluster analysis of teaching behavior trajectory data yields the teaching ability dimensions of the assessed subjects, specifically including the following steps: The feature discrimination boundary of the initial group is obtained by processing the teaching behavior trajectory data; Trajectory groups are obtained by integrating the initial groups based on the feature-distinguishing boundaries; After obtaining the teaching implementation scenario information corresponding to the trajectory group, establish the correspondence between each trajectory group and the teaching implementation scenario; Based on the common trajectory characteristics of each trajectory group and the corresponding teaching implementation scenario information, the teaching ability representation attributes corresponding to each trajectory group are extracted; Based on the differences in the representation attributes of teaching ability, the teaching ability dimensions of the assessment objects are obtained by dividing the groups of each trajectory into dimensions.
[0035] The initial group feature distinction boundary is obtained by processing the teaching behavior trajectory data. First, the teaching behavior trajectory data is broken down into different trajectory segments. The trajectory length, direction, and dwell time features of each segment are extracted. By judging the correlation strength of these features, closely related trajectory features are grouped into target feature groups, thus grouping the trajectory segments into initial groups. The differences in common trajectory features among different initial groups are compared to determine the feature distinction boundary between each group. For example, the trajectory features of one initial group are mainly short-duration, high-frequency interactions, while another group is mainly long-duration knowledge explanations; the difference between the two constitutes the feature distinction boundary.
[0036] Based on these features, the initial groups are integrated to obtain trajectory groups. All initial groups containing short-duration, high-frequency interaction features are integrated into one trajectory group, and initial groups containing long-duration knowledge explanation features are integrated into another trajectory group, ensuring that the trajectory features within each trajectory group have a high degree of consistency.
[0037] Obtain the teaching implementation scenario information corresponding to each trajectory group and establish the correspondence between the two. For example, the teaching implementation scenario corresponding to the short-duration, high-frequency interaction trajectory group is the classroom group discussion session; the teaching implementation scenario corresponding to the long-duration knowledge explanation trajectory group is the new lesson knowledge point instruction session.
[0038] Based on the common trajectory characteristics of each trajectory group and the corresponding teaching implementation scenario information, the teaching ability representation attributes of each group are extracted. Taking the trajectory group with short duration and high frequency of interaction as an example, its common trajectory characteristics are high frequency of initiating interaction and rapid response to student feedback. The corresponding teaching implementation scenario is group discussion, from which the teaching ability representation attribute of classroom interaction guidance can be extracted. On the other hand, the trajectory group with long duration of knowledge explanation has the common characteristics of logical knowledge output and stable content presentation. The corresponding scenario is knowledge point instruction, from which the attribute of knowledge system construction and instruction ability can be extracted.
[0039] Based on the differences in these teaching ability representation attributes, the teaching ability dimensions of the assessment subjects are obtained by dividing the group of each trajectory into dimensions. For example, classroom interaction guidance ability and knowledge system construction and delivery ability are different ability attributes. Treating them as independent dimensions can form a teaching ability dimension system for the assessment subjects.
[0040] The initial group's feature discrimination boundary is obtained by processing the teaching behavior trajectory data, specifically including the following steps: Based on the teaching implementation process, the teaching behavior trajectory data is broken down into trajectory segments, and the trajectory length, trajectory direction and trajectory dwell characteristics of each trajectory segment are extracted to form a trajectory feature set; The trajectory feature set is processed by feature association to obtain the association strength between features of different trajectory segments, and the trajectory features that meet the preset requirements are selected to form the target feature group; Based on the target feature group, each trajectory segment is grouped to obtain an initial group. The feature distinction boundary of the initial group is determined by comparing the differences in common trajectory features of each initial group.
[0041] The teaching behavior trajectory data is broken down into trajectory segments based on the teaching implementation process. The teaching implementation process usually includes new lesson introduction, knowledge point instruction, classroom exercises, and summary and review. Each segment corresponds to a continuous teaching behavior. Based on this, the trajectory data is broken down so that each trajectory segment corresponds to a specific teaching segment. For example, a 40-minute lesson can be broken down into new lesson introduction (5 minutes), knowledge point instruction (20 minutes), classroom exercises (10 minutes), and summary and review (5 minutes).
[0042] The trajectory length, trajectory direction, and trajectory dwell characteristics of each trajectory segment are extracted to form a trajectory feature set. Trajectory length refers to the teaching duration corresponding to that trajectory segment; for example, the trajectory length of a knowledge point instruction segment is 20 minutes. Trajectory direction refers to the development trend of teaching behavior within that segment; for example, the direction of progress from basic concepts to extended cases in knowledge point instruction. Trajectory dwell characteristics refer to the proportion of duration of a certain type of teaching behavior within the segment; for example, the proportion of time the teacher spends guiding students in solving problems in a classroom exercise segment. These features collectively constitute the trajectory feature set for each trajectory segment.
[0043] Feature association processing is performed on the trajectory feature set to obtain the association strength between features of different trajectory segments. Trajectory features whose association strength meets preset requirements are then selected to form a target feature group. Association strength measures the similarity of the same feature in different trajectory segments. Association strength = (absolute value of feature X in trajectory segment A - value of feature X in trajectory segment B) ÷ value of feature X in trajectory segment A. If the preset requirement is that the association strength does not exceed 0.2, and if the trajectory length of trajectory segment A is 20 minutes and the trajectory length of trajectory segment B is 18 minutes, then the association strength of the trajectory length feature between the two is |20-18|÷20=0.1, which meets the preset requirement, and this feature can be included in the target feature group. Similarly, if the association strength of the trajectory direction and trajectory dwell features of multiple trajectory segments also meets the requirements, these features will collectively form the target feature group.
[0044] Initial groups are obtained by grouping each trajectory segment based on the target feature group. For example, trajectory segments that meet the requirements for the correlation strength of trajectory length, trajectory direction, and trajectory dwell features are grouped into the same initial group. For example, trajectory segments in the knowledge point teaching sessions of multiple courses can be grouped into one initial group if their trajectory length, direction, and dwell feature correlation strength all meet the requirements.
[0045] The feature differentiation boundaries of the initial groups are determined by comparing the differences in common trajectory characteristics among the initial groups. The trajectory segments within each initial group have common trajectory characteristics. For example, the common trajectory characteristics of one initial group are a trajectory length of 15-20 minutes, a trajectory direction from concept to case, and a trajectory dwelling characteristic of explanation accounting for more than 80%. The common trajectory characteristics of another initial group are a trajectory length of 5-10 minutes, a trajectory direction from practice to error correction, and a trajectory dwelling characteristic of guidance accounting for more than 70%. The differences between these common characteristics constitute the feature differentiation boundaries of different initial groups, which are used to clarify the feature boundaries between each group.
[0046] Analyzing teaching behavior trajectory data yields the trajectory temporal characteristics of the teaching ability dimension, specifically including the following steps: The behavioral sequence of teaching behavior trajectory data is used to form a temporal behavior chain; the succession relationship between each behavior is extracted through the temporal behavior chain, and the triggering association of the preceding behavior to the subsequent behavior is clarified based on the succession relationship to obtain the behavior succession association information; The teaching process is divided into temporal stages based on the temporal behavior chain, with each temporal stage corresponding to different aspects of the teaching implementation; the frequency of occurrence of various behaviors in each temporal stage is counted, and the behavioral density of each temporal stage is obtained based on the frequency of occurrence and the continuous progress of behaviors in the temporal behavior chain. Determine the tightness of behavioral connections within different time periods based on behavioral connection information; determine the dominant behavioral type within each time period by combining the behavioral density of each time period. By tracing the evolution of dominant behavior types at various time stages, capturing the replacement nodes of dominant behavior types, and clarifying the transitional characteristics of dominant behaviors before and after the replacement nodes, the evolution of dominant behavior types can be judged based on the transitional characteristics to obtain the temporal pattern of behavior evolution. By combining the intensity of behavior, the closeness of the connection between behaviors, and the temporal pattern of behavior evolution in each time stage, temporal correlation features corresponding to each teaching ability dimension are extracted. Integrate the temporal correlation features of each time series to form the trajectory temporal features of each teaching ability dimension.
[0047] First, the behavioral sequence of the teaching behavior trajectory data is determined to form a temporal behavior chain. Teaching behavior trajectory data is a collection of teaching behaviors occurring chronologically. These behaviors are linked together in order of occurrence to form a temporal behavior chain. For example, the behavioral sequence of a lesson might be: introductory question, concept explanation, case demonstration, student practice, and error correction guidance. Arranging these in this order constitutes the corresponding temporal behavior chain. The sequential relationships between behaviors are extracted through the temporal behavior chain, clarifying the triggering association between preceding and subsequent behaviors to obtain behavioral succession information. For instance, if the subsequent behavior after the introductory question in the temporal behavior chain is concept explanation, it means that the introductory question triggered the concept explanation.
[0048] The teaching process is divided into temporal stages based on a sequential behavior chain, with each stage corresponding to a different aspect of the teaching implementation. For example, the temporal behavior chain can be divided into stages such as the introduction stage (corresponding to introductory questions), the lecture stage (corresponding to concept explanation and case demonstration), and the practice stage (corresponding to student practice and error correction guidance). Then, the frequency of each type of behavior within each temporal stage is counted, and combined with the duration of the behaviors in the temporal behavior chain, the behavior density of each stage is obtained. Behavior density = total frequency of behaviors within a certain temporal stage ÷ duration of that temporal stage. Taking the lecture stage as an example, if this stage lasts 20 minutes and the total frequency of concept explanation and case demonstration is 12 times, then the behavior density of this stage is 12 ÷ 20 = 0.6.
[0049] The tightness of behavioral connections within different time-series stages is determined based on behavioral continuity information. The tightness of these connections can be measured by the interval between the preceding and subsequent behaviors; shorter intervals indicate higher tightness. For example, if a case demonstration is triggered within one minute of the end of a concept explanation in the lecture stage, it indicates a high degree of behavioral continuity within that stage. Combining the behavioral intensity of each time-series stage, the dominant behavioral type is determined: the behavior with the highest frequency and intensity is the dominant behavioral type for that stage. For instance, if error correction guidance accounts for 70% of the total behavior frequency in the practice stage and has a frequency intensity of 0.5, then error correction guidance is the dominant behavioral type in the practice stage.
[0050] By tracing the evolution of dominant behavior types across different time stages, we can identify the transition points between them and clarify the transitional characteristics of the dominant behaviors before and after these points. For example, the transition from introductory questions in the introduction stage to concept explanations in the lecture stage is the transition point, and the transitional characteristic might be the closing remarks of the introductory questions connecting to the opening statements of the concept explanations. Based on these transitional characteristics, we can determine the evolution of dominant behavior types and obtain the temporal patterns of behavioral evolution. For instance, the dominant behavior type in this course might gradually transition from interactive behaviors to explanatory behaviors, and then to guiding behaviors.
[0051] By combining the intensity of behavior, the tightness of the connection between behaviors, and the temporal pattern of behavior evolution at each time stage, temporal correlation features corresponding to each teaching ability dimension are extracted. For example, for the teaching ability dimension of classroom organization, the corresponding temporal correlation features may be: 0.4 intensity of behavior in the introduction stage, high tightness of the connection between behaviors, and the transition of the dominant behavior from interaction to explanation.
[0052] The dimensional weight values of the teaching ability dimension are obtained based on the trajectory time series feature analysis, specifically including the following steps: Based on the trajectory time sequence characteristics, the dimensional application information of the assessment object in each teaching ability dimension is obtained; among which, the dimensional application information includes the dimensional application duration of the assessment object in each teaching ability dimension; Obtain the total application time of the assessment subjects across all teaching ability dimensions, and obtain the dimension application time percentage based on the dimension application time and the total dimension application time; The dimension weight value of the teaching ability dimension is obtained based on the proportion of application time of each dimension.
[0053] Based on the trajectory temporal characteristics, the application information of the assessed subject in each teaching ability dimension is obtained, with the core information being the duration of dimension application. The trajectory temporal characteristics record the behavioral patterns at each stage of the teaching process. Combining these patterns, the actual application time corresponding to each teaching ability dimension can be determined. For example, the teaching ability dimensions include classroom interaction ability and knowledge delivery ability. Through the trajectory temporal characteristics, it can be seen that the assessment subject's application time in the classroom interaction ability dimension is 15 minutes, and the application time in the knowledge delivery ability dimension is 25 minutes.
[0054] Obtain the total application time of the assessed subject across all teaching ability dimensions, and then calculate the percentage of application time for each dimension based on the application time of each dimension. The total application time for each dimension is the sum of the application times for all teaching ability dimensions; total application time = Σ (application time of each teaching ability dimension). Total application time for each dimension = 15 + 25 = 40 minutes. Percentage of application time for each dimension = application time of a specific teaching ability dimension ÷ total application time for that dimension. Correspondingly, for the classroom interaction ability dimension, its application time percentage = 15 ÷ 40 = 0.375; for the knowledge delivery ability dimension, its application time percentage = 25 ÷ 40 = 0.625.
[0055] The weight values for each teaching ability dimension are derived from the percentage of time each dimension is used. The percentage of time a dimension is used directly corresponds to its weight value; a higher percentage indicates that the teaching ability dimension is used more frequently and is more important in the teaching process of the assessed individual. For example, the weight value for classroom interaction ability is 0.375, and the weight value for knowledge delivery ability is 0.625. These weight values serve as core references for subsequent assessment, intervention, and adjustment, reflecting the proportion of different teaching ability dimensions in the overall assessment.
[0056] Based on the teaching implementation constraint data and the dimensional weights of the teaching ability dimension, the moderating constraints for the assessment intervention are obtained, specifically including the following steps: Based on the teaching implementation constraint data, we obtain the constraint type elements and the constraint range of the elements; based on the constraint type elements and the constraint range of the elements, we obtain the implementation safety constraints for the evaluation intervention. Set intervention intensity level ranges and intervention frequency ranges; each intervention intensity level range corresponds to an intervention intensity level; each intervention frequency range corresponds to an intervention implementation frequency; The intervention intensity level is obtained by comparing the dimensional weight value of the teaching ability dimension with the intervention intensity level range; the intervention implementation frequency is obtained by comparing the dimensional weight value of the teaching ability dimension with the intervention frequency range; and the intervention resource ratio is obtained based on the dimensional weight value of the teaching ability dimension and the total assessment weight ratio of the teaching ability dimension. The dimensional constraints of each teaching ability dimension are obtained based on the intervention intensity level, intervention implementation frequency, and intervention resource ratio corresponding to each teaching ability dimension. The regulatory constraints for evaluating interventions are obtained based on the implementation of safety constraints and dimensional constraints.
[0057] Based on the teaching implementation constraint data, constraint type elements and element constraint ranges are obtained, thereby determining the safe implementation constraints for assessment interventions. The teaching implementation constraint data covers objective limitations in the teaching process, such as teaching duration, class size, and teaching equipment configuration. These correspond to different constraint type elements; for example, constraint type elements could be teaching duration limits or equipment usage time limits. The element constraint range refers to the specific numerical boundaries of each type of element. For instance, the constraint range for teaching duration limits is no more than 40 minutes per class, and the constraint range for equipment usage time limits is no more than 20 minutes per class. Combining the constraint type elements and element constraint ranges clarifies the boundaries that assessment interventions cannot breach, forming safe implementation constraints. For example, the duration of intervention activities must not exceed the 40-minute upper limit of teaching time.
[0058] Set up intervention intensity level ranges and intervention frequency ranges, with each range corresponding to specific intervention parameters. The intervention intensity level range is a grading range for the level of intervention, for example, 0-0.4 corresponds to a low intervention intensity level, 0.4-0.7 corresponds to a medium level, and 0.7-1 corresponds to a high level. The intervention frequency range is a grading range for the number of interventions, for example, 0-2 times / week corresponds to a low intervention frequency, 2-5 times / week corresponds to a medium frequency, and 5-8 times / week corresponds to a high frequency.
[0059] The corresponding intervention intensity level and intervention frequency are obtained by comparing the dimensional weight values of the teaching ability dimension with the above-mentioned intervals, and the intervention resource allocation is calculated. Taking knowledge delivery ability in the teaching ability dimension as an example, if its dimensional weight value is 0.625, and after comparing with the intervention intensity level intervals, 0.625 falls within the 0.4-0.7 interval, the corresponding intervention intensity level is medium; if 0.625 corresponds to the interval of 2-5 times / week, the corresponding intervention frequency is medium. Intervention resource allocation = dimensional weight value of a certain teaching ability dimension ÷ total evaluation weight allocation of all teaching ability dimensions. Assuming that the total evaluation weight allocation of all teaching ability dimensions is 1 (the sum of the weight values of each dimension), and the dimensional weight value of knowledge delivery ability is 0.625, then its intervention resource allocation = 0.625 ÷ 1 = 0.625, meaning that the intervention resources allocated to this dimension account for 62.5% of the total resources.
[0060] The dimensional constraints for each teaching ability dimension are derived by combining the intervention intensity level, intervention frequency, and intervention resource ratio. For example, the dimension constraints for knowledge delivery ability are: medium intervention intensity level, medium intervention frequency, and intervention resource ratio of 0.625. These conditions clearly define the boundaries of the intervention parameters for this dimension.
[0061] The integrated implementation of safety constraints and dimensional constraints of various teaching ability dimensions yields the moderating constraints for the assessment intervention.
[0062] A multi-dimensional teaching competence assessment, intervention, and adjustment analysis system, comprising: Acquisition Module: Acquires basic teaching data and perceived efficacy data of the assessment subjects; among which, basic teaching data includes teaching ability parameters and teaching implementation constraint data, and perceived efficacy data includes teaching behavior trajectory data and perceived preference text information; Analysis module: Generates teaching characteristic data of the assessment object based on teaching ability parameters, obtains behavioral trajectory feature points based on teaching behavior trajectory data; performs cluster analysis on teaching behavior trajectory data to obtain the teaching ability dimension of the assessment object; Processing module: Analyzes teaching behavior trajectory data to obtain trajectory temporal characteristics of the teaching ability dimension; analyzes the trajectory temporal characteristics to obtain the dimension weight value of the teaching ability dimension; and obtains the adjustment constraints of the assessment intervention based on the teaching implementation constraint data and the dimension weight value of the teaching ability dimension. Generation module: Generates an intervention and adjustment plan for teaching competency assessment by adjusting constraints, dimensional weight values, and perceptual preference text information; Output module: Obtains the adjustment constraint parameters of the assessment intervention based on the adjustment constraint conditions; obtains the implementation parameters of the teaching competence assessment intervention adjustment scheme; obtains the adaptation loss coefficient of the assessment intervention adjustment scheme based on the implementation parameters and adjustment constraint parameters; and outputs the set of teaching competence assessment intervention adjustment schemes for the assessment object based on the adaptation loss coefficient.
[0063] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0064] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A multi-dimensional method for assessing and analyzing teaching competence through intervention and regulation, characterized in that, The method includes the following steps: Acquire the teaching basic data and efficacy perception data of the evaluation subjects; wherein, the teaching basic data includes teaching ability parameters and teaching implementation constraint data, and the efficacy perception data includes teaching behavior trajectory data and perception preference text information; Teaching characteristic data of the assessment object is generated based on teaching ability parameters, and behavioral trajectory feature points are obtained based on teaching behavior trajectory data; cluster analysis is performed on the teaching behavior trajectory data to obtain the teaching ability dimension of the assessment object. The trajectory characteristics of teaching ability dimension are obtained by analyzing the trajectory data of teaching behavior; the dimension weight value of teaching ability dimension is obtained by analyzing the trajectory time characteristics; and the adjustment constraints of assessment intervention are obtained by analyzing the teaching implementation constraint data and the dimension weight value of teaching ability dimension. The intervention and adjustment plan for teaching competency assessment will be generated by adjusting constraints, dimensional weight values, and perceptual preference text information. The adjustment constraint parameters for the assessment intervention are obtained based on the adjustment constraints; the implementation parameters of the teaching competence assessment intervention adjustment scheme are obtained; the adaptation loss coefficient of the assessment intervention adjustment scheme is obtained based on the implementation parameters and adjustment constraint parameters; and the set of teaching competence assessment intervention adjustment schemes for the assessment object is output based on the adaptation loss coefficient.
2. The multi-dimensional teaching competence assessment intervention and regulation analysis method according to claim 1, characterized in that, The process of generating teaching characteristic data for assessment subjects based on teaching ability parameters includes the following steps: The teaching ability parameters include the teaching ability structure of the assessment subject; Teaching feature data is generated based on the teaching ability structure; wherein, the teaching feature data includes feature point density.
3. The multi-dimensional teaching competence assessment intervention and regulation analysis method according to claim 1, characterized in that, The process of obtaining behavioral trajectory feature points based on teaching behavior trajectory data includes the following steps: Set the feature extraction frequency, and obtain the ability status of teaching behavior trajectory in teaching feature data based on the feature extraction frequency; Based on the assessment of the subject's abilities, behavioral trajectory feature points in the teaching characteristic data are obtained.
4. The multi-dimensional teaching competence assessment intervention and regulation analysis method according to claim 1, characterized in that, Cluster analysis of teaching behavior trajectory data yields the teaching ability dimensions of the assessed subjects, specifically including the following steps: The feature discrimination boundary of the initial group is obtained by processing the teaching behavior trajectory data; Trajectory groups are obtained by integrating the initial groups based on the feature-distinguishing boundaries; After obtaining the teaching implementation scenario information corresponding to the trajectory group, establish the correspondence between each trajectory group and the teaching implementation scenario; Based on the common trajectory characteristics of each trajectory group and the corresponding teaching implementation scenario information, the teaching ability representation attributes corresponding to each trajectory group are extracted; Based on the differences in the representation attributes of teaching ability, the teaching ability dimensions of the assessment objects are obtained by dividing the groups of each trajectory into dimensions.
5. The multi-dimensional teaching competence assessment intervention and regulation analysis method according to claim 4, characterized in that, The initial group's feature discrimination boundary is obtained by processing the teaching behavior trajectory data, specifically including the following steps: Based on the teaching implementation process, the teaching behavior trajectory data is broken down into trajectory segments, and the trajectory length, trajectory direction and trajectory dwell characteristics of each trajectory segment are extracted to form a trajectory feature set; The trajectory feature set is processed by feature association to obtain the association strength between features of different trajectory segments, and the trajectory features that meet the preset requirements are selected to form the target feature group; Based on the target feature group, each trajectory segment is grouped to obtain an initial group. The feature distinction boundary of the initial group is determined by comparing the differences in common trajectory features of each initial group.
6. The multi-dimensional teaching competence assessment intervention and regulation analysis method according to claim 5, characterized in that, Analyzing teaching behavior trajectory data yields the trajectory temporal characteristics of the teaching ability dimension, specifically including the following steps: The behavioral sequence of teaching behavior trajectory data is used to form a temporal behavior chain; the succession relationship between each behavior is extracted through the temporal behavior chain, and the triggering association of the preceding behavior to the subsequent behavior is clarified based on the succession relationship to obtain the behavior succession association information; The teaching process is divided into temporal stages based on the temporal behavior chain, with each temporal stage corresponding to different aspects of the teaching implementation; the frequency of occurrence of various behaviors in each temporal stage is counted, and the behavioral density of each temporal stage is obtained based on the frequency of occurrence and the continuous progress of behaviors in the temporal behavior chain. Determine the tightness of behavioral connections within different time periods based on behavioral connection information; determine the dominant behavioral type within each time period by combining the behavioral density of each time period. By tracing the evolution of dominant behavior types at various time stages, capturing the replacement nodes of dominant behavior types, and clarifying the transitional characteristics of dominant behaviors before and after the replacement nodes, the evolution of dominant behavior types can be judged based on the transitional characteristics to obtain the temporal pattern of behavior evolution. By combining the intensity of behavior, the closeness of the connection between behaviors, and the temporal pattern of behavior evolution in each time stage, temporal correlation features corresponding to each teaching ability dimension are extracted. Integrate the temporal correlation features of each time series to form the trajectory temporal features of each teaching ability dimension.
7. The multi-dimensional teaching competence assessment intervention and regulation analysis method according to claim 6, characterized in that, The dimensional weight values of the teaching ability dimension are obtained based on the trajectory time series feature analysis, specifically including the following steps: The dimensional application information of the evaluation object in each teaching ability dimension is obtained based on the trajectory time sequence characteristics; wherein, the dimensional application information includes the dimensional application duration of the evaluation object in each teaching ability dimension; Obtain the total application time of the assessment subjects across all teaching ability dimensions, and obtain the dimension application time percentage based on the dimension application time and the total dimension application time; The dimension weight value of the teaching ability dimension is obtained based on the proportion of application time of each dimension.
8. The multi-dimensional teaching competence assessment intervention and regulation analysis method according to claim 7, characterized in that, Based on the teaching implementation constraint data and the dimensional weights of the teaching ability dimension, the moderating constraints for the assessment intervention are obtained, specifically including the following steps: Based on the teaching implementation constraint data, we obtain the constraint type elements and the constraint range of the elements; based on the constraint type elements and the constraint range of the elements, we obtain the implementation safety constraints for the evaluation intervention. Set intervention intensity level ranges and intervention frequency ranges; each intervention intensity level range corresponds to an intervention intensity level; each intervention frequency range corresponds to an intervention implementation frequency; The intervention intensity level is obtained by comparing the dimensional weight value of the teaching ability dimension with the intervention intensity level range; the intervention implementation frequency is obtained by comparing the dimensional weight value of the teaching ability dimension with the intervention frequency range; and the intervention resource ratio is obtained based on the dimensional weight value of the teaching ability dimension and the total assessment weight ratio of the teaching ability dimension. The dimensional constraints of each teaching ability dimension are obtained based on the intervention intensity level, intervention implementation frequency, and intervention resource ratio corresponding to each teaching ability dimension. The regulatory constraints for evaluating interventions are obtained based on the implementation of safety constraints and dimensional constraints.
9. The multi-dimensional teaching competence assessment intervention and regulation analysis method according to claim 8, characterized in that, The adaptation loss coefficient for evaluating the intervention and adjustment scheme is obtained based on the implementation parameters and adjustment constraint parameters, specifically: The implementation parameters and constraint parameters are compared to obtain the adaptation loss coefficient corresponding to the evaluation intervention and adjustment scheme.
10. A multi-dimensional teaching competence assessment intervention and regulation analysis system, applied to the multi-dimensional teaching competence assessment intervention and regulation analysis method according to any one of claims 1 to 9, characterized in that, include: Acquisition Module: Acquires the teaching basic data and efficacy perception data of the evaluation object; wherein, the teaching basic data includes teaching ability parameters and teaching implementation constraint data, and the efficacy perception data includes teaching behavior trajectory data and perception preference text information; Analysis module: Generates teaching characteristic data of the assessment object based on teaching ability parameters, obtains behavioral trajectory feature points based on teaching behavior trajectory data; performs cluster analysis on teaching behavior trajectory data to obtain the teaching ability dimension of the assessment object; Processing module: Analyzes teaching behavior trajectory data to obtain trajectory temporal characteristics of the teaching ability dimension; analyzes the trajectory temporal characteristics to obtain the dimension weight value of the teaching ability dimension; and obtains the adjustment constraints of the assessment intervention based on the teaching implementation constraint data and the dimension weight value of the teaching ability dimension. Generation module: Generates an intervention and adjustment plan for teaching competency assessment by adjusting constraints, dimensional weight values, and perceptual preference text information; Output module: Obtains the adjustment constraint parameters of the assessment intervention based on the adjustment constraint conditions; obtains the implementation parameters of the teaching competence assessment intervention adjustment scheme; obtains the adaptation loss coefficient of the assessment intervention adjustment scheme based on the implementation parameters and adjustment constraint parameters; and outputs the set of teaching competence assessment intervention adjustment schemes for the assessment object based on the adaptation loss coefficient.