Intelligent campus teacher performance evaluation and intelligent assessment system

Abstract

The invention discloses an intelligent campus teacher performance evaluation and intelligent assessment system, relates to the technical field, and is used for solving the problem that the deviation of performance evaluation is increased due to insufficient support for personalized differences and innovation behaviors of teaching behaviors. Association analysis is performed in combination with multi-dimensional management data in a smart campus, a teacher performance portrait is generated, teacher development demands are classified by using a hierarchical progressive algorithm based on portrait data, and a personalized development path is generated; and the comprehensive feedback module tracks and records the teaching improvement effect of the teacher through a visual display interface and a real-time monitoring mechanism to finally form closed-loop feedback, so that multi-dimensional dynamic evaluation, personalized development support and visual display of an assessment result of the teacher performance are realized, and comprehensiveness and accuracy of teacher performance evaluation are improved.

Description

Technical Field

[0001] The present invention relates to the field of education management technology, and more specifically, to a smart campus teacher performance evaluation and intelligent assessment system. Background Art

[0002] With the rapid development of educational informatization and the gradual deepening of smart campus construction, the research and development of teacher performance evaluation and intelligent assessment systems have become an important direction for improving educational management efficiency. However, the existing teacher performance evaluation and assessment systems have certain limitations in data collection, analysis dimensions, personalized evaluation, and intelligent support, and cannot fully meet the needs of smart campuses for comprehensive, accurate, and dynamic evaluation of teachers.

[0003] The existing technology has the following deficiencies:

[0004] At present, the existing teacher performance evaluation and assessment system mainly relies on static data and a single evaluation indicator. The data collection granularity is coarse and the real-time performance is poor. The evaluation model lacks the ability to deeply integrate multidimensional data and conduct dynamic correlation analysis. At the same time, it lacks support for the personalized differences and innovative behaviors of teaching behaviors. This increases the bias of performance evaluation to a certain extent and reduces the objectivity of the assessment results. Therefore, a smart campus teacher performance evaluation and intelligent assessment system is proposed.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a smart campus teacher performance evaluation and intelligent assessment system, which solves the problems raised in the above-mentioned background technology by analyzing the linkage relationship between teacher teaching behavior data and the smart campus ecology and dynamically adjusting the evaluation dimensions.

[0007] To achieve the above objectives, the present invention provides the following technical solutions: a smart campus teacher performance evaluation and intelligent assessment system, comprising a data acquisition module, a performance analysis module, a personalized support module, and a comprehensive feedback module;

[0008] The data collection module is used to obtain teachers' teaching behavior data and send the data to the performance analysis module;

[0009] The performance analysis module receives teaching behavior data, performs correlation analysis based on the multi-dimensional management data in the smart campus, generates teacher performance profiles, and transmits the profile data to the personalized support module;

[0010] The personalized support module receives performance profile data, classifies teacher development needs based on the profile data using a hierarchical progressive algorithm, and generates personalized development paths, which are then passed to the comprehensive feedback module.

[0011] The comprehensive feedback module receives personalized development path data, generates a visual display interface based on the path data, and combines the real-time monitoring mechanism to track and record the teacher's teaching improvement effects, ultimately forming a closed-loop feedback loop.

[0012] In a preferred embodiment, the data acquisition module obtains the teacher's teaching behavior data through Internet of Things sensors, campus management system interfaces or classroom behavior capture devices, specifically including classroom teaching behavior, student evaluation feedback, frequency of teaching resource use and classroom interaction data;

[0013] A data preprocessing unit is set up inside the data acquisition module, which processes the original data using data cleaning and normalization methods, stores it as a structured data table, and transmits it to the performance analysis module through signal connection.

[0014] In a preferred embodiment, the performance analysis module receives the structured data table from the data collection module, combines the educational management data, student academic data, and logistics management data in the smart campus, and constructs a multidimensional correlation analysis model;

[0015] The model extracts key characteristic variables through principal component analysis, uses a weighted scoring mechanism to calculate the comprehensive scores of teachers in the dimensions of teaching effectiveness, classroom management, and teaching innovation, and generates a teacher performance profile;

[0016] A dynamic weight adjustment unit is set up inside the performance analysis module to update the weight parameters in real time according to changes in the smart campus data ecosystem.

[0017] In a preferred embodiment, the personalized support module receives the teacher performance portrait generated by the performance analysis module and classifies the teacher's development needs using a hierarchical progressive algorithm. The specific steps are as follows:

[0018] Set up initial classification rules and divide teachers into three categories: foundation improvement type, capacity expansion type, and innovation leading type according to the comprehensive scores in the performance portrait;

[0019] Demand mining: extract key issues from teaching behavior data for each type of teacher, and determine improvement directions based on the resource distribution in the smart campus data ecosystem;

[0020] Path generation uses a path planning algorithm to generate a personalized development path based on the improvement direction. The path includes specific improvement goals, a recommended resource list, and a time schedule.

[0021] In a preferred embodiment, the hierarchical progressive algorithm in the personalization support module is specifically implemented as follows:

[0022] Data grouping: grouping the comprehensive scores in the teacher performance profile according to the set interval range;

[0023] Feature extraction: extracting key characteristic variables that affect teacher development from each set of data;

[0024] Progressive optimization gradually refines the classification rules according to the importance of feature variables until the classification accuracy requirements are met.

[0025] In a preferred embodiment, the comprehensive feedback module receives the path data generated by the personalized support module and constructs a visual display interface through a graphical interface generation tool;

[0026] The interface adopts a multi-level display mode. The first level displays the teacher's comprehensive performance score, the second level displays the specific content of the personalized development path, and the third level displays the tracking record of real-time improvement effects.

[0027] A real-time monitoring unit is set up inside the comprehensive feedback module, which obtains teachers' teaching improvement data in real time through the Internet of Things sensors and the campus management system interface, compares and analyzes it with the path data, and generates an improvement effect report.

[0028] In a preferred embodiment, the real-time monitoring unit in the comprehensive feedback module implements the following specific steps:

[0029] Data collection, obtaining teachers' teaching improvement data through IoT sensors and campus management system interfaces;

[0030] Data comparison: compare the improved data with the target data in the personalized development path item by item;

[0031] Effect evaluation: Generate improvement effect scores based on comparison results, and adjust target parameters in the path based on the score results;

[0032] Closed-loop feedback: The adjusted path data is re-transmitted to the personalized support module to form a closed-loop feedback mechanism.

[0033] In a preferred embodiment, the visual display interface in the comprehensive feedback module adopts dynamic charts, including bar charts, line charts and radar charts, which are used to respectively display the teacher's comprehensive performance score, the key nodes of the personalized development path and the changing trend of the real-time improvement effect;

[0034] Interactive function units are set up inside the interface. Users can view detailed data by clicking on nodes in the chart and adjust target parameters in the path by dragging and dropping.

[0035] In a preferred embodiment, when generating the improvement effect report, the comprehensive feedback module uses a fuzzy comprehensive evaluation method to quantitatively evaluate the teacher's teaching improvement effect. The specific steps are as follows:

[0036] Indicator selection: multiple evaluation indicators are selected from teaching behavior data, including classroom interaction frequency, student satisfaction change rate, and teaching resource utilization rate;

[0037] Weight allocation, assigning weight values ​​according to the importance of indicators;

[0038] Fuzzy scoring, using membership function to perform fuzzy scoring on each indicator;

[0039] Comprehensive evaluation combines the fuzzy scoring results with the weight values ​​to calculate the comprehensive improvement effect score.

[0040] In a preferred embodiment, the data acquisition module obtains the teacher's classroom lecture voice, body movements, and teacher-student interaction through the camera and microphone array installed in the classroom, and extracts the teaching resource usage records uploaded by the teacher and the students' online evaluation feedback through the campus management system interface.

[0041] Technical effects and advantages of the present invention:

[0042] The present invention generates teacher performance portraits by prioritizing the collection of teachers' teaching behavior data, combining it with the multi-dimensional management data in the smart campus for correlation analysis, and then classifies teacher development needs based on the portrait data using a hierarchical progressive algorithm to generate personalized development paths. The comprehensive feedback module tracks and records the teaching improvement effects of teachers through a visual display interface and a real-time monitoring mechanism, ultimately forming a closed-loop feedback loop. The system integrates the data ecology of the smart campus, realizes multi-dimensional dynamic evaluation of teacher performance, personalized development support, and intuitive display of assessment results, solves the shortcomings of existing technologies in data analysis depth, personalized support, and visual display, and improves the comprehensiveness and accuracy of teacher performance evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a schematic diagram of the module structure of a smart campus teacher performance evaluation and intelligent assessment system of the present invention.

[0044] Figure 2 This is a schematic diagram of the visual display interface of the comprehensive feedback module in the smart campus teacher performance evaluation and intelligent assessment system of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] Example 1

[0047] The present invention provides a smart campus teacher performance evaluation and intelligent assessment system. Figure 1 and attached Figure 2 Provide detailed explanation.

[0048] like Figure 1 As shown, the system includes a data acquisition module, a performance analysis module, a personalized support module and a comprehensive feedback module, and data interaction is achieved between the modules through signal connections.

[0049] The data collection module is used to obtain teachers' teaching behavior data and send the data to the performance analysis module;

[0050] The performance analysis module receives teaching behavior data, performs correlation analysis based on the multi-dimensional management data in the smart campus, generates teacher performance profiles, and transmits the profile data to the personalized support module;

[0051] The personalized support module receives performance profile data, classifies teacher development needs based on the profile data using a hierarchical progressive algorithm, and generates personalized development paths, which are then passed to the comprehensive feedback module.

[0052] The comprehensive feedback module receives personalized development path data, generates a visual display interface based on the path data, and combines the real-time monitoring mechanism to track and record the teacher's teaching improvement effects, ultimately forming a closed-loop feedback loop.

[0053] During the specific implementation process:

[0054] The data acquisition module obtains teachers' teaching behavior data through IoT sensors, campus management system interfaces or classroom behavior capture devices. These data include classroom teaching behavior, student evaluation feedback, frequency of teaching resource use and classroom interaction data.

[0055] A data preprocessing unit is set up inside the data acquisition module, which processes the original data using data cleaning and normalization methods and stores them as a structured data table.

[0056] Among them, teaching behavior data includes classroom teaching behavior, student evaluation feedback, and frequency of teaching resource use;

[0057] Classroom teaching behavior refers to the content, duration, frequency of blackboard writing, amplitude of body movements, and changes in voice and intonation of teachers during classroom teaching. The acquisition logic is to collect teachers' images, audio, and motion data in real time through cameras, microphone arrays, and classroom behavior capture devices installed in the classroom, and extract behavioral features by combining image recognition algorithms and speech analysis algorithms, and convert them into quantifiable data.

[0058] Student evaluation feedback refers to students' subjective evaluation data on teachers' teaching effectiveness and instant classroom feedback information. Its acquisition logic is to call students' evaluation records in the course evaluation system through the campus management system interface, and combine them with the instant classroom feedback results collected on classroom feedback terminals or mobile devices to automatically summarize and generate a student evaluation feedback dataset.

[0059] The frequency of teaching resource usage refers to the statistical data on the frequency of teachers uploading, downloading, and calling various teaching resources using the smart campus teaching resource platform inside and outside the classroom. The acquisition logic is to extract teachers' teaching resource operation records in real time through the smart campus teaching resource management system interface and calculate the usage frequency.

[0060] It should be noted that various teaching resources include courseware, videos, exercises, etc. The specific teaching resources are set by the experimenters and will not be described here;

[0061] Classroom interaction data refers to the frequency, duration and content categories of interactions between teachers and students in the classroom. The acquisition logic is based on the real-time collection of teacher-student interaction data through classroom interactive terminals, audio and video acquisition equipment in the classroom and interaction recording systems, and generates structured data through keyword extraction, semantic analysis and interaction frequency statistics methods.

[0062] It should be noted that data cleaning is performed by our experimenters based on data integrity rules and outlier removal rules. Normalization methods include but are not limited to maximum and minimum value normalization, Z-score normalization, and decimal scaling normalization. The specific selection of normalization methods is not described here.

[0063] For example, in an actual application scenario, the data acquisition module obtains the teacher's classroom voice, body movements, and teacher-student interactions through cameras and microphone arrays installed in the classroom, and at the same time extracts the teaching resource usage records uploaded by the teacher and the students' online evaluation feedback through the campus management system interface.

[0064] These raw data are cleaned by the data preprocessing unit to remove noise data, and then the data of different dimensions are unified into the same standard range through normalization method, stored as a structured data table, and transmitted to the performance analysis module through signal connection.

[0065] The performance analysis module receives the structured data table from the data acquisition module, combines it with the educational management data, student academic data, and logistics management data in the smart campus, and builds a multidimensional correlation analysis model.

[0066] Among them, educational management data includes teacher class schedule information, course arrangements, teaching progress, and attendance records; student academic data includes student test scores at each stage, homework completion status, classroom test results, and credit points; and logistics management data includes classroom usage records, campus equipment operating status, energy consumption statistics, and environmental monitoring data;

[0067] Specifically, the above data are collected and stored in the campus comprehensive data center database and distributed storage server locations through database interface calls and file batch imports, and are available for calls by the performance analysis module and visualization display interface.

[0068] The model extracts key characteristic variables through principal component analysis, uses a weighted scoring mechanism to calculate the comprehensive scores of teachers in dimensions such as teaching effectiveness, classroom management, and teaching innovation, and generates a teacher performance portrait.

[0069] Specifically, the comprehensive score evaluation rule is dimension setting: the comprehensive performance score is composed of the following three core dimensions:

[0070] The teaching effectiveness dimension is used to reflect the quality of teachers’ classroom teaching, which is reflected by the improvement rate of students’ academic performance;

[0071] The classroom management dimension is used to reflect teachers' behaviors in maintaining classroom discipline, controlling teaching progress, and managing classroom resource allocation, and is reflected by the proportion of time spent maintaining classroom discipline.

[0072] The teaching innovation dimension is used to reflect teachers' performance in teaching methods, teaching tools, and course content innovation, and is reflected by the semantic similarity of the same course content with other teachers in the same subject;

[0073] Furthermore, the logic for obtaining the student academic performance improvement rate is to connect the system to the smart campus examination database to obtain the previous periodic examination scores of students in the courses taught by the teacher. Based on the students' initial and final grades, the improvement rate is calculated according to the following formula:

[0074]

[0075] Where N is the number of students, ∈ is a small constant to prevent the denominator from being zero, and S initial,i is the initial score of the i-th student, S final,i is the final score of the i-th student, R score Improve the academic performance of students;

[0076] The logic for obtaining the proportion of classroom discipline maintenance time is that the system uses the cameras and voice acquisition devices in the smart classroom to count the time teachers spend maintaining discipline in the classroom and compare it with the total class time to obtain the proportion of classroom discipline maintenance time. Furthermore, the performance analysis module uses the following quadratic function model to convert the score:

[0077] S manage =-a(R manage -R opt ) 2 +S max ;

[0078] Where a is the adjustment coefficient, which is used to control the opening size of the function, R opt is the optimal threshold of management time ratio, S max is the full score of the classroom management dimension, R manage The proportion of time spent maintaining classroom discipline, S manage This is the score conversion value of the proportion of time spent maintaining classroom discipline. Specifically, the score conversion value of the proportion of time spent maintaining classroom discipline will be used as the basis for the model calculation.

[0079] It is understandable that there is a nonlinear relationship between the proportion of time spent maintaining classroom discipline and teachers' classroom management capabilities.

[0080] When the proportion of time spent maintaining classroom discipline approaches the optimal threshold preset by the system, the teacher's comprehensive score reaches its peak, reflecting that the teacher has efficient classroom management capabilities. If the proportion of time spent maintaining classroom discipline is significantly lower or higher than the threshold, the teacher's comprehensive score decreases, where:

[0081] The proportion of time spent maintaining classroom discipline is relatively low, indicating that teachers lack the necessary management intervention for classroom discipline and reflect insufficient management capabilities;

[0082] If the proportion of time spent on maintaining classroom discipline is too high, it means that teachers spend too much time on classroom discipline management, which indirectly reflects that classroom management is difficult or that teachers have limited ability to manage classroom discipline.

[0083] Therefore, the present invention sets an optimal threshold for the proportion of classroom discipline maintenance time, so that the proportion and the teacher's comprehensive score show a quadratic function change relationship of "first increase and then decrease": within the optimal threshold range, the proportion of classroom discipline maintenance time is positively correlated with the teacher's comprehensive score; when it exceeds or falls below this range, the proportion of classroom discipline maintenance time is negatively correlated with the teacher's comprehensive score, so as to comprehensively and objectively reflect the teacher's classroom management ability.

[0084] The logic for obtaining the semantic similarity of the same course content taught by other teachers in the same subject is that the system calls the data from the teaching resource platform, extracts feature vectors from the teacher's classroom PPT, handouts, recordings, etc. through the natural language processing engine, and calculates the semantic similarity with the same course content taught by other teachers in the same subject through cosine similarity.

[0085] Specifically, cosine similarity is common knowledge to those skilled in the art and will not be described in detail here;

[0086] Optionally, the above three parameters are only examples. In practice, other parameters may be used as evaluation criteria.

[0087] In a specific embodiment, the performance analysis module extracts a teacher's student performance distribution data, course schedule information, and teaching resource call records from the smart campus database, combines it with the classroom interaction data provided by the data collection module, and extracts the key characteristic variables that affect teacher performance through principal component analysis;

[0088] For example, the frequency of classroom questions, the accuracy of students' answers, and the utilization rate of teaching resources; these characteristic variables are assigned different weight values, and the comprehensive scores of teachers in the three dimensions of teaching effectiveness, classroom management, and teaching innovation are calculated through a weighted scoring mechanism.

[0089] In addition, a dynamic weight adjustment unit is set up inside the performance analysis module to update the weight parameters in real time according to changes in the smart campus data ecosystem.

[0090] For example, when a school introduces new teaching tools or adjusts course objectives, the dynamic weight adjustment unit reallocates the weight values ​​of each feature variable to ensure the timeliness of the analysis results.

[0091] The personalized support module receives the teacher performance portrait generated by the performance analysis module and uses a hierarchical progressive algorithm to classify the teacher's development needs.

[0092] The specific implementation steps are as follows:

[0093] First, set the initial classification rules and divide teachers into three categories according to the comprehensive scores in the performance portraits: basic improvement type, capacity expansion type and innovation leading type.

[0094] For example, in a specific scenario, a teacher’s overall score is 75, which belongs to the capacity expansion category.

[0095] Next, we will conduct demand exploration. For each type of teacher, we will extract key problem points from the teaching behavior data and determine the direction of improvement based on the resource distribution in the smart campus data ecosystem.

[0096] For the above-mentioned capacity-expanding teachers, the personalized support module extracts problem points with low classroom interaction frequency from their performance portraits, and combines the distribution of teaching resources in the smart campus database to recommend increasing the frequency of using interactive teaching tools.

[0097] Finally, path generation is performed. Based on the improvement direction, a path planning algorithm is used to generate a personalized development path. The path includes specific improvement goals, a recommended resource list, and a time schedule.

[0098] For example, the personalized development paths generated for the above-mentioned teachers include "increasing the number of classroom interactions to more than 15 times per month", "watching excellent interactive teaching case videos twice a week", and "completing a special training on interactive teaching within three months".

[0099] The specific implementation steps of the hierarchical progressive algorithm in the personalized support module are as follows: first, group the data and group the comprehensive scores in the teacher performance portrait according to the set interval range.

[0100] For example, teachers with an overall score below 60 are classified as basic improvement type, teachers with a score between 60 and 85 are classified as capacity expansion type, and teachers with a score above 85 are classified as innovation leading type.

[0101] Feature extraction is then performed to extract key characteristic variables that affect teacher development from each set of data.

[0102] For example, characteristic variables such as classroom interaction frequency, teaching resource utilization rate, and student satisfaction change rate are extracted from the data of capacity-development teachers.

[0103] Finally, progressive optimization is performed, ranking the feature variables according to their importance, and gradually refining the classification rules until the classification accuracy requirements are met.

[0104] For example, for teachers with the capacity development type, further analysis of the specific distribution of their classroom interaction frequency found that some teachers' interactions were concentrated in the pre-class introduction session and ignored the in-class discussion session. Therefore, a sub-category of "the proportion of in-class interaction frequency" was added to the classification rules.

[0105] The comprehensive feedback module receives the path data generated by the personalized support module and builds a visual display interface through a graphical interface generation tool.

[0106] The interface adopts a multi-level display mode. The first level displays the teacher's comprehensive performance score, the second level displays the specific content of the personalized development path, and the third level displays the tracking records of real-time improvement effects.

[0107] In a specific embodiment, the visual display interface generated by the comprehensive feedback module for a teacher includes a bar chart showing his or her comprehensive performance score, a line chart showing the completion status of key nodes in the personalized development path, and a radar chart showing the changing trend of real-time improvement effects.

[0108] A real-time monitoring unit is set up inside the comprehensive feedback module, which obtains teachers' teaching improvement data in real time through the Internet of Things sensors and the campus management system interface, compares and analyzes it with the path data, and generates an improvement effect report.

[0109] For example, the real-time monitoring unit captured the teacher's classroom interaction through cameras installed in the classroom and found that the teacher asked 18 questions in class this month, exceeding the path target of 15 times, so it was marked as "met the target" in the improvement effect report.

[0110] If an indicator fails to meet the standard, the real-time monitoring unit will adjust the target parameters in the path based on the comparison results, such as increasing the target number of classroom questions to 20 times next month.

[0111] The specific implementation steps of the real-time monitoring unit in the comprehensive feedback module are as follows: First, data collection is carried out to obtain teachers' teaching improvement data through the Internet of Things sensors and the campus management system interface.

[0112] For example, the teacher's classroom lecture voice data is obtained through the microphone array installed in the classroom, and the uploaded teaching resource usage records are extracted through the campus management system interface.

[0113] Then conduct a data comparison, comparing the improved data with the target data in the personalized development path item by item.

[0114] For example, compare the actual number of classroom interactions this month with the path target of 15. Next, conduct an effectiveness evaluation, generate an improvement score based on the comparison results, and adjust the target parameters in the path based on the score results.

[0115] For example, if the number of classroom interactions reaches 18 times this month, the improvement effect score will be "excellent" and the number of interactions will be adjusted to 20 times in the path goal for next month.

[0116] Finally, closed-loop feedback is performed, and the adjusted path data is re-transmitted to the personalized support module to form a closed-loop feedback mechanism.

[0117] The visual display interface in the comprehensive feedback module adopts dynamic charts, including bar charts, line charts and radar charts, which are used to display the teacher's comprehensive performance score, the key nodes of the personalized development path and the changing trends of the real-time improvement effect.

[0118] Interactive function units are set up inside the interface. Users can view detailed data by clicking on nodes in the chart and adjust target parameters in the path by dragging and dropping.

[0119] For example, in a specific embodiment, a teacher clicks on the "Classroom Interaction Frequency" node in the line chart to view the specific distribution of the number of interactions this month, and adjusts the target number for next month from 20 to 22 times by dragging.

[0120] When generating the improvement effect report, the comprehensive feedback module uses the fuzzy comprehensive evaluation method to quantitatively evaluate the teaching improvement effect of teachers.

[0121] The specific implementation steps are as follows:

[0122] First, we select indicators and select multiple evaluation indicators from the teaching behavior data, including classroom interaction frequency, student satisfaction change rate, and teaching resource utilization rate.

[0123] Then, weight distribution is performed, and weight values ​​are assigned according to the importance of the indicators. For example, the weight value of classroom interaction frequency is 0.4, the student satisfaction change rate is 0.3, and the teaching resource utilization rate is 0.3.

[0124] Next, we perform fuzzy scoring, using a membership function to assign a fuzzy score to each indicator. For example, for the frequency of classroom interaction, if the actual number of times this month is 18 and the target number is 15, then its membership score is 0.9.

[0125] Finally, a comprehensive evaluation is conducted, combining the fuzzy scoring results with the weight values ​​to calculate the comprehensive improvement effect score.

[0126] For example, if the fuzzy score of classroom interaction frequency is 0.9, the student satisfaction change rate is 0.8, and the teaching resource utilization rate is 0.7, then the comprehensive improvement effect score is 0.9×0.4+0.8×0.3+0.7×0.3=0.81.

[0127] The present invention generates teacher performance portraits by prioritizing the collection of teachers' teaching behavior data, combining it with multi-dimensional management data in the smart campus for correlation analysis, and then adopts a hierarchical progressive algorithm based on the portrait data to classify teachers' development needs and generate personalized development paths.

[0128] The comprehensive feedback module tracks and records the teachers' teaching improvement effects through a visual display interface and real-time monitoring mechanism, ultimately forming a closed-loop feedback loop.

[0129] The system integrates the data ecology of the smart campus, realizes multi-dimensional dynamic evaluation of teacher performance, personalized development support and intuitive display of assessment results, solves the shortcomings of existing technologies in data analysis depth, personalized support and visual display, and improves the comprehensiveness and accuracy of teacher performance evaluation.

[0130] In order to better enable relevant personnel in this technical field to fully understand and implement the present invention, the specific implementation principle of the present invention is further supplemented below with reference to a specific application scenario.

[0131] In a smart campus, a teacher's teaching behavior data is collected in real time through cameras, microphone arrays, and campus management system interfaces installed in the classroom.

[0132] The camera captures classroom lectures and teacher-student interactions, the microphone array records the frequency of teachers' questions and the accuracy of students' answers, and the campus management system interface extracts teaching resource usage records and students' online evaluation feedback.

[0133] These raw data are cleaned by the data preprocessing unit inside the data acquisition module to remove noise data, and the data of different dimensions are unified into the same standard range through normalization method and then stored as a structured data table.

[0134] Subsequently, the data acquisition module transmits the structured data table to the performance analysis module through a signal connection.

[0135] After receiving the structured data table, the performance analysis module combines the educational management data, student academic data, and logistics management data in the smart campus to build a multidimensional correlation analysis model.

[0136] For example, the teacher's student score distribution data, course schedule information, and teaching resource call records are extracted from the smart campus database and combined with the classroom interaction data provided by the data acquisition module.

[0137] The principal component analysis method was used to extract key characteristic variables that affect teacher performance, such as the frequency of classroom questions, the accuracy of students' answers, and the utilization rate of teaching resources.

[0138] These characteristic variables are assigned different weight values, and the teacher's comprehensive score in the three dimensions of teaching effectiveness, classroom management, and teaching innovation is calculated through a weighted scoring mechanism.

[0139] If the school introduces new teaching tools or adjusts course objectives, the dynamic weight adjustment unit will reallocate the weight values ​​of each characteristic variable to ensure the timeliness of the analysis results.

[0140] Finally, the performance analysis module generates a performance profile of the teacher and passes the profile data to the personalized support module.

[0141] After receiving the performance portrait data, the personalized support module first divides teachers into three categories based on the comprehensive score: basic improvement type, capacity expansion type or innovation leading type.

[0142] For example, a teacher’s comprehensive score is 75 points, which belongs to the ability development category.

[0143] Next, the personalized support module extracts key problem points from the teaching behavior data, such as the low frequency of classroom interaction, and determines the direction of improvement based on the resource distribution in the smart campus data ecosystem.

[0144] On this basis, a path planning algorithm is used to generate a personalized development path, which includes specific improvement goals, a recommended resource list, and a time schedule.

[0145] For example, the personalized development path generated for the teacher includes "increasing the number of classroom interactions to more than 15 times per month", "watching excellent interactive teaching case videos twice a week", and "completing a special training on interactive teaching within three months".

[0146] In order to further optimize the classification rules, the personalized support module also conducted a detailed analysis of the distribution of teachers' classroom interaction frequency through a hierarchical progressive algorithm. It was found that some teachers' interactions were concentrated in the pre-class introduction phase and ignored the in-class discussion phase. Therefore, a sub-category of "the proportion of in-class interaction frequency" was added.

[0147] After receiving the path data generated by the personalized support module, the comprehensive feedback module constructs a visual display interface through a graphical interface generation tool.

[0148] The interface adopts a multi-level display mode. The first level shows the teacher's comprehensive performance score through a bar chart, the second level shows the completion status of key nodes in the personalized development path through a line chart, and the third level shows the changing trend of real-time improvement effects through a radar chart.

[0149] The real-time monitoring unit within the comprehensive feedback module obtains teachers' teaching improvement data in real time through the Internet of Things sensors and the campus management system interface.

[0150] For example, by installing cameras in the classroom to capture the teacher's classroom interactions, it was found that the teacher asked 18 questions in class this month, exceeding the path target of 15 times, so it was marked as "met the target" in the improvement effect report.

[0151] If an indicator fails to meet the standard, the real-time monitoring unit will adjust the target parameters in the path based on the comparison results, such as increasing the target number of classroom questions to 20 times next month.

[0152] Finally, the adjusted path data is re-transmitted to the personalized support module, forming a closed-loop feedback mechanism.

[0153] When generating the improvement effect report, the comprehensive feedback module uses the fuzzy comprehensive evaluation method to quantitatively evaluate the teacher's teaching improvement effect.

[0154] The specific steps are as follows:

[0155] First, multiple evaluation indicators were selected, including the frequency of classroom interaction, the change rate of student satisfaction, and the utilization rate of teaching resources;

[0156] Then, weight values ​​are assigned according to the importance of the indicators. For example, the weight value of classroom interaction frequency is 0.4, the student satisfaction change rate is 0.3, and the teaching resource utilization rate is 0.3;

[0157] Next, the membership function is used to perform a fuzzy score on each indicator. For example, for the frequency of classroom interaction, if the actual number of times this month is 18 times and the target number is 15 times, then its membership score is 0.9;

[0158] Finally, the fuzzy scoring results are combined with the weight values ​​to calculate the comprehensive improvement effect score. For example, if the fuzzy score of classroom interaction frequency is 0.9, the student satisfaction change rate is 0.8, and the teaching resource utilization rate is 0.7, then the comprehensive improvement effect score is 0.9×0.4+0.8×0.3+0.7×0.3=0.81.

[0159] The above operation process shows that this system achieves comprehensive evaluation and dynamic optimization of teacher performance through multi-module collaboration.

[0160] The data collection module prioritizes collecting teachers' teaching behavior data, combines it with multi-dimensional management data in the smart campus for correlation analysis, and generates teacher performance portraits;

[0161] The personalized support module uses a hierarchical and progressive algorithm based on the portrait data to classify teachers' development needs and generate personalized development paths;

[0162] The comprehensive feedback module tracks and records the teachers' teaching improvement effects through a visual display interface and real-time monitoring mechanism, ultimately forming a closed-loop feedback loop.

[0163] The system integrates the data ecology of the smart campus, solves the shortcomings of existing technologies in data analysis depth, personalized support and visual display, and significantly improves the comprehensiveness and accuracy of teacher performance evaluation.

[0164] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0165] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0166] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0167] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0168] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0169] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0170] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0171] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0172] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0173] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A smart campus teacher performance evaluation and intelligent assessment system, characterized by: It includes data collection module, performance analysis module, personalized support module and comprehensive feedback module; The data collection module is used to obtain teachers' teaching behavior data and send the data to the performance analysis module; The performance analysis module receives teaching behavior data, performs correlation analysis based on the multi-dimensional management data in the smart campus, generates teacher performance profiles, and transmits the profile data to the personalized support module; The personalized support module receives performance profile data, classifies teacher development needs based on the profile data using a hierarchical progressive algorithm, and generates personalized development paths, which are then passed to the comprehensive feedback module. The comprehensive feedback module receives personalized development path data, generates a visual display interface based on the path data, and combines the real-time monitoring mechanism to track and record the teacher's teaching improvement effects, ultimately forming a closed-loop feedback loop.

2. The smart campus teacher performance evaluation and intelligent assessment system according to claim 1 is characterized by: The data collection module obtains teachers' teaching behavior data through IoT sensors, campus management system interfaces, or classroom behavior capture devices, including classroom teaching behavior, student evaluation feedback, frequency of teaching resource use, and classroom interaction data; A data preprocessing unit is set up inside the data acquisition module, which processes the original data using data cleaning and normalization methods, stores it as a structured data table, and transmits it to the performance analysis module through signal connection.

3. The smart campus teacher performance evaluation and intelligent assessment system according to claim 1 is characterized by: The performance analysis module receives the structured data table from the data collection module and combines it with the educational management data, student academic data, and logistics management data in the smart campus to build a multi-dimensional correlation analysis model; The model extracts key characteristic variables through principal component analysis, uses a weighted scoring mechanism to calculate the comprehensive scores of teachers in the dimensions of teaching effectiveness, classroom management, and teaching innovation, and generates a teacher performance profile; A dynamic weight adjustment unit is set up inside the performance analysis module to update the weight parameters in real time according to changes in the smart campus data ecosystem.

4. The smart campus teacher performance evaluation and intelligent assessment system according to claim 3 is characterized by: The personalized support module receives the teacher performance profile generated by the performance analysis module and classifies the teacher's development needs using a hierarchical progressive algorithm. The specific steps are as follows: Set up initial classification rules and divide teachers into three categories: foundation improvement type, capacity expansion type, and innovation leading type according to the comprehensive scores in the performance portrait; Demand mining: extract key issues from teaching behavior data for each type of teacher, and determine improvement directions based on the resource distribution in the smart campus data ecosystem; Path generation: Based on the improvement direction, a path planning algorithm is used to generate a personalized development path. The path includes specific improvement goals, a recommended resource list, and a time schedule.

5. The smart campus teacher performance evaluation and intelligent assessment system according to claim 4 is characterized by: The specific implementation steps of the hierarchical progressive algorithm in the personalization support module are as follows: Data grouping: grouping the comprehensive scores in the teacher performance profile according to the set interval range; Feature extraction: extracting key characteristic variables that affect teacher development from each set of data; Progressive optimization gradually refines the classification rules according to the importance of feature variables until the classification accuracy requirements are met.

6. The smart campus teacher performance evaluation and intelligent assessment system according to claim 1 is characterized by: The comprehensive feedback module receives the path data generated by the personalized support module and builds a visual display interface through a graphical interface generation tool; The interface adopts a multi-level display mode. The first level displays the teacher's comprehensive performance score, the second level displays the specific content of the personalized development path, and the third level displays the tracking record of real-time improvement effects. A real-time monitoring unit is set up inside the comprehensive feedback module, which obtains teachers' teaching improvement data in real time through the Internet of Things sensors and the campus management system interface, compares and analyzes it with the path data, and generates an improvement effect report.

7. The smart campus teacher performance evaluation and intelligent assessment system according to claim 6 is characterized by: The specific implementation steps of the real-time monitoring unit in the comprehensive feedback module are as follows: Data collection, obtaining teachers' teaching improvement data through IoT sensors and campus management system interfaces; Data comparison: compare the improved data with the target data in the personalized development path item by item; Effect evaluation: Generate improvement effect scores based on comparison results, and adjust target parameters in the path based on the score results; Closed-loop feedback: The adjusted path data is re-transmitted to the personalized support module to form a closed-loop feedback mechanism.

8. The smart campus teacher performance evaluation and intelligent assessment system according to claim 6 is characterized by: The visual display interface in the comprehensive feedback module adopts dynamic charts, including bar charts, line charts and radar charts, which are used to display teachers' comprehensive performance scores, key nodes of personalized development paths, and real-time improvement effect trends. Interactive function units are set up inside the interface. Users can view detailed data by clicking on nodes in the chart and adjust target parameters in the path by dragging and dropping.

9. The smart campus teacher performance evaluation and intelligent assessment system according to claim 6, characterized in that: When generating the improvement effect report, the comprehensive feedback module uses the fuzzy comprehensive evaluation method to quantitatively evaluate the teacher's teaching improvement effect. The specific steps are as follows: Indicator selection: multiple evaluation indicators are selected from teaching behavior data, including classroom interaction frequency, student satisfaction change rate, and teaching resource utilization rate; Weight allocation, assigning weight values ​​according to the importance of indicators; Fuzzy scoring, using membership function to perform fuzzy scoring on each indicator; Comprehensive evaluation combines the fuzzy scoring results with the weight values ​​to calculate the comprehensive improvement effect score.

10. The smart campus teacher performance evaluation and intelligent assessment system according to claim 1 is characterized by: The data acquisition module obtains the teacher's classroom voice, body movements, and teacher-student interactions through cameras and microphone arrays installed in the classroom. At the same time, it extracts the teaching resource usage records uploaded by teachers and students' online evaluation feedback through the campus management system interface.

Images