A teaching intelligent evaluation method and system

Abstract

The present application relates to a kind of teaching intelligent evaluation method, system, electronic equipment and storage medium, solve the technical problem that existing teaching quality evaluation is too simple, evaluation result cannot adapt to the demand of teaching link improvement.Method includes: from the learning state data of the multiple-path teaching process of reaching learner, form learning quantitative data set;Through the ability evaluation model analysis learning quantitative data forms the comprehensive evaluation of learning ability, according to the comprehensive evaluation result forms the personalized ability data of feedback to teaching two sides;According to the personalized ability data, form the process of feedback and incentive strategy, according to the weight calibration of the prior data of teacher;According to personalized ability data, match feedback and incentive strategy adjust the configuration and distribution of learning resource.Form the personalized evaluation of the comprehensive ability of learner.Evaluation result guarantees the adaptation of customized learning path and incentive content.Resource configuration and distribution for individual differences of learner are realized.

Description

Technical Field

[0001] This invention relates to the field of teaching technology, specifically to an intelligent teaching assessment method and system. Background Technology

[0002] With the development of educational informatization and intelligentization, resources such as learning projects, project-stage curriculum design, and course sub-content are becoming increasingly abundant. To improve learning efficiency and teaching quality, various educational platforms are increasingly demanding assessments of learners' abilities. Traditional educational assessment methods rely heavily on periodic data, lacking a multi-dimensional and dynamic assessment of learners' comprehensive abilities. This is mainly reflected in: The assessment is too simplistic and lacks accuracy, relying mainly on exam scores and assignment grades, and lacks a comprehensive evaluation of multiple dimensions such as the learning process, thinking ability, and collaboration ability. The lack of personalized incentives, the delayed feedback of assessment results, and the absence of follow-up personalized and real-time learning suggestions and incentive measures make it impossible to provide customized learning paths and feedback incentives based on the individual differences of learners.

[0003] Unable to adapt to change, most assessment systems fail to collect sufficient behavioral data during the learning process, resulting in incomplete and undynamic assessment results.

[0004] Existing technologies are insufficient to fully reflect learners' true abilities and cannot effectively motivate them to learn. In the context of personalized education and competency-based educational reforms, it is particularly important to develop a comprehensive, accurate, and inspiring assessment system for learners' development. Summary of the Invention

[0005] To address the aforementioned problems, embodiments of the present invention provide a teaching intelligent assessment method and system, which solves the technical problems that existing teaching quality assessments are too simplistic and the assessment results cannot meet the needs of improving teaching processes.

[0006] The intelligent teaching assessment method of this invention includes: Learning status data is obtained from the multi-channel teaching process that reaches learners, forming a quantitative learning dataset; By analyzing quantitative learning data through a competency assessment model, a comprehensive assessment of learning ability is formed, and personalized competency data is generated based on the comprehensive assessment results to provide feedback to both teachers and students. In the process of developing feedback and incentive strategies based on personalized ability data, weight adjustments are made based on the teacher's prior data. The allocation and distribution of learning resources are adjusted based on personalized ability data, feedback, and incentive strategies.

[0007] In one embodiment of the present invention, the formation of the learning quantization dataset includes: Identify the learning environment that learners are exposed to, and extract learning content, status, behavior, and related statistical data from the learning environment according to the time sequence to form multi-source process data; Multi-source process data are cleaned, fused, and feature extracted to form a learning quantization dataset.

[0008] In one embodiment of the present invention, the formation of the personalized capability data includes: A weighted scoring model is used to comprehensively assess learning ability across multiple dimensions. Multi-dimensional comprehensive prediction of learning ability is made through machine learning evaluation algorithms; The assessment of learning ability in each dimension is formed by combining scores and predicted values ​​with weighted averages. The assessment results are formatted according to the feedback direction to form personalized capability data.

[0009] In one embodiment of the present invention, the formation of the weight adjustment includes: It provides a human-computer interaction interface to parse personalized ability data, forming an interactive control interface for educators to adjust personalized ability data and / or model weight parameters.

[0010] In one embodiment of the present invention, the configuration and distribution include: Based on personalized ability data, comprehensive ability suggestions in graphic and textual form are generated and advanced path planning options are provided to learners and distributed to them. Incentive mechanisms are adapted based on personalized ability data, and incentive resources are allocated and distributed to learners. Based on learner options, corresponding learning resources are configured to form a teaching schedule and distributed to learners.

[0011] The intelligent teaching assessment system of this invention includes: A multidimensional data acquisition device is used to acquire learning status data from multiple teaching processes that reach learners, forming a quantitative learning dataset. The comprehensive ability assessment device is used to analyze quantitative learning data through an ability assessment model to form a comprehensive assessment of learning ability, and to generate personalized ability data for feedback to both teachers and students based on the comprehensive assessment results. In the process of optimizing the control device to form feedback and incentive strategies based on personalized ability data, the weights are adjusted based on the teacher's prior data. The feedback and incentive interaction device is used to adjust the configuration and distribution of learning resources based on personalized ability data and matching feedback and incentive strategies.

[0012] In one embodiment of the present invention, the multidimensional data acquisition device includes: The data acquisition module is used to determine the learning environment that learners are exposed to, and to obtain the learning content, status, behavior and related statistical data from the learning environment according to the time sequence to form multi-source process data; The data processing module is used to clean, fuse, and extract features from multi-source process data to form a learning quantization dataset.

[0013] In one embodiment of the present invention, the comprehensive capability assessment device includes: The scoring and evaluation module is used to comprehensively score learning ability from multiple dimensions using a weighted scoring model. The prediction and evaluation module is used to make multi-dimensional comprehensive predictions of learning ability through machine learning evaluation algorithms. The dimensional assessment module is used to combine scores and predicted values ​​to weightedly assess learning ability in each dimension. The assessment output module is used to format the assessment results according to the feedback direction, forming personalized ability data.

[0014] In one embodiment of the present invention, the human being in the optimization control device includes: The two-way calibration module is used to provide a human-computer interaction interface for parsing personalized ability data, forming an interactive control interface for educators to adjust personalized ability data and / or model weight parameters.

[0015] In one embodiment of the present invention, the feedback-stimulation interaction device includes: The suggestion display module is used to generate comprehensive ability suggestions in text and graphics based on personalized ability data and provide advanced path planning options to be distributed to learners. The incentive adaptation module is used to adapt incentive mechanisms based on personalized ability data and configure incentive resources for distribution to learners. The resource adaptation module is used to configure corresponding learning resources according to learner options, form a teaching schedule, and distribute it to learners.

[0016] The intelligent teaching assessment method and system of this invention comprehensively extracts learning behavior data within the learning cycle and uses a dynamic assessment model to categorize and quantify multi-dimensional abilities from the data, forming a personalized assessment of learners' overall abilities. The learner profile generated from the assessment results, combined with the instructor's monitoring and dynamic adjustments, ensures the adaptation of customized learning paths and incentive content. This enables resource allocation and distribution tailored to individual learner differences, effectively improving the resource utilization rate and teaching quality of the education platform. Attached Figure Description

[0017] Figure 1 The diagram shown is a flowchart of an embodiment of the intelligent teaching assessment method of the present invention.

[0018] Figure 2The diagram shown illustrates the application process of an intelligent teaching assessment method according to an embodiment of the present invention.

[0019] Figure 3 The diagram shown is a schematic representation of the architecture of an intelligent teaching assessment system according to an embodiment of the present invention.

[0020] Figure 4 The diagram shown is a schematic representation of the architecture of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0021] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0022] An embodiment of the present invention provides an intelligent teaching assessment method, as follows: Figure 1 As shown. In Figure 1 In this embodiment, the following are included: Step 100: Obtain learning status data from the multi-channel teaching process that reaches learners to form a quantitative learning dataset.

[0023] Those skilled in the art will understand that learners encounter various teaching modules, specialized courses, classroom tools, and teaching management systems on an educational platform during their learning process. This results in a dynamic distribution of learning status information throughout the entire learning cycle, including learners' interactive behaviors, learning content and knowledge systems, and statistical data—all reflecting the depth and breadth of their learning. By utilizing data acquisition technology, anchored at the individual learner, and obtaining all learning status mapping data from each contact pathway, it is possible to reflect the learner's actual learning process and ability evolution. For example, based on learning duration and course content, quantifying the types of interactive behaviors, feedback duration, ROI data of emotions or behaviors during the learning process, and standard quantitative values ​​of feedback in the management system, can generate structured and unstructured quantitative data for learners throughout the entire learning cycle. Structured quantitative data is formed based on quantitative benchmarks, such as duration and completed course scales, while unstructured quantitative data is formed based on type benchmarks, such as the breadth and depth of knowledge of non-standard answers in course branches. By fusing and normalizing the mapping data from different contact pathways, a continuously updated learning quantitative dataset can be formed.

[0024] Step 200: Analyze the quantitative learning data through the ability assessment model to form a comprehensive assessment of learning ability, and generate personalized ability data for feedback to both the teacher and student based on the comprehensive assessment results.

[0025] Those skilled in the art will understand that data parsing models can enable multi-dimensional, in-depth analysis of massive datasets, revealing implicit correlations between data points and quantifying long-term or short-term learning states and the focus of learning behaviors. For example, using weighted scoring models or machine learning algorithms for ability assessment models allows for interpretable or adaptive data analysis of quantitative learning data. This categorizes and quantifies the long-term and short-term impacts of learning states on the learning process and the factors contributing to the development of different learning abilities, ultimately forming multi-dimensional quantitative data on acquired abilities for assessing individual learner differences. Based on the teaching platform's curriculum system and the quantitative factors such as the type, weight, and difficulty of course branches within the system, the multi-dimensional quantitative data forms a dimensional connection with the quantitative data of the teaching platform's courses. Assessment results are primarily reflected in single and composite dimensions such as knowledge mastery, thinking ability, collaboration ability, and innovation ability. Personalized ability data from the assessment results are organized in multimedia format and fed back to both instructors and students.

[0026] Step 300: In the process of forming feedback and incentive strategies based on personalized ability data, weight adjustments are made based on the teacher's prior data.

[0027] Those skilled in the art will understand that the evaluation results may contain small probabilities of overfitting or underfitting due to model flaws, leading to errors in the quantification of personalized abilities. Therefore, it is necessary to use prior data and professional experience from instructors for weighted adjustments to avoid significant systematic errors that could result in resource mismatches or discrepancies between learners' abilities and actual learning outcomes. Instructors' adjustments target both the data itself and the model parameters. Personalized ability data serves as the basis for adjusting parameters in feedback and incentive strategies within the teaching system, such as adjusting learning paths, allocating resources, and distributing incentive content.

[0028] Step 400: Adjust the configuration and distribution of learning resources based on personalized ability data, matching feedback and incentive strategies.

[0029] Based on the dimensional classification of multi-dimensional quantitative data and the dimensional connection of the teaching platform's quantitative classification, corresponding learning resources are configured according to the quantitative data of learners' various abilities. By default, the process of generating feedback and incentive strategies based on personalized ability data is automated through parameter passing, resulting in parallel assessment and optimization for a batch of learners. The configured learning resources are distributed to learners according to the time-series schedule generated by the teaching platform. Subsequent teaching processes involve updating assessment data and iterating assessments.

[0030] The intelligent teaching assessment method of this invention comprehensively extracts learning behavior data within the learning cycle and uses a dynamic assessment model to categorize and quantify multi-dimensional abilities from the data, forming a personalized assessment of learners' overall abilities. The learner profile generated from the assessment results, combined with the instructor's monitoring and dynamic adjustments, ensures the adaptation of customized learning paths and incentive content. This enables resource allocation and distribution tailored to individual learner differences, effectively improving the resource utilization rate and teaching quality of the education platform.

[0031] like Figure 1 As shown, in one embodiment of the present invention, step 100 includes: Step 110: Determine the learning environment that the learner is exposed to, and obtain the learning content, status, behavior and related statistical data from the learning environment according to the time sequence to form multi-source process data.

[0032] Data collected includes, but is not limited to, learner-centric data such as assignment scores, classroom interactions, project participation, and learning behavior logs. It also includes data from the learning environment, such as learning management systems, classroom interaction tools, project platform curriculum structures, and behavior analysis platforms.

[0033] Step 120: Clean, fuse, and extract features from the multi-source process data to form a learning quantization dataset.

[0034] Data cleaning handles missing and outlier values ​​based on data source, data type, and data dimension. In one embodiment of this invention, data sources can be reflected in knowledge dimensions such as answer records, exam scores, and assignment submissions; thinking dimensions such as open-ended questions, project reports, and thinking assessments; and writing dimensions such as group task logs, peer evaluations, and interaction records. In one embodiment of this invention, missing value imputation uses the mean for objective data (knowledge) and the median for subjective data (thinking / collaboration) to avoid extreme values ​​from subjective scoring skewing the results. Outlier handling uses IQR (Independent Quality Reduction) to replace rather than delete, preserving the integrity of the behavioral samples.

[0035] The core of data fusion is to associate data by student identity while addressing inconsistencies in dimensions. In one embodiment of this invention, outer join is preferred for fusion to avoid losing dimensions that only contain partial data. All dimension scores are standardized to a fixed interval to eliminate the influence of units in subsequent weighted scoring / machine learning.

[0036] Feature extraction extracts features from the fused data that can be directly used to evaluate the model. These features are divided into basic numerical features and higher-order derived features, outputting a 0-1 normalized feature set that can be directly used in the capability assessment model. In one embodiment of this invention, the features include, but are not limited to, total knowledge score / total thinking score / total collaboration score, knowledge stability, thinking improvement rate, and collaboration participation.

[0037] The intelligent teaching assessment method of this invention collects a wide range of data on the learning process to form mapping data on learning behavior and learning effect, thus ensuring the abundance of data for quantifying the dimensions of learning ability measurement.

[0038] like Figure 1 As shown, in one embodiment of the present invention, step 200 includes: Step 210: Conduct a multi-dimensional comprehensive assessment of learning ability using a weighted scoring model.

[0039] In one embodiment of the present invention, the model is in the form of: S t =w1S1+w2S2+…+w n S n ,in, S t Comprehensive capability score of a single temporal node S i : Score of the i-th dimension (knowledge, thinking, collaboration, etc.) w i : Corresponding weight, ∑w i =1 Where S represents the overall ability trend and T represents different learning durations.

[0040] In one embodiment of the present invention, a targeted improvement is made through the following method: Analytic Hierarchy Process (AHP): Weights are determined by experts / questionnaires; Entropy weighting method: Data-driven automatic weighting reduces subjective bias; Dynamic weighting: The weights are automatically adjusted as the learning stage progresses.

[0041] Step 220: Make a multi-dimensional comprehensive prediction of learning ability using machine learning evaluation algorithms.

[0042] In one embodiment of the present invention, a multivariate linear regression or random forest model is used for comprehensive evaluation.

[0043] The model form of multiple linear regression is as follows: y = θ0 + θ1x1 + θ2x2 + … + θ m x m， in: y: Predicted value of comprehensive ability score θ0: Intercept term (constant term), representing the value when all input features x i When both are 0, the model gives the basic predicted value. θ1,θ2,...,θ mRegression coefficients (weights) represent the degree and direction of influence of each feature on the overall ability score. x1,x2,...,x m Input features correspond to multi-dimensional evaluation indicators such as knowledge, thinking, and collaboration. m: The number of input features, i.e., the number of evaluation dimensions. In one embodiment of the present invention, a random forest model is used to automatically capture nonlinear relationships and output feature importance to explain the weights. By constructing multiple independent decision trees and averaging (regression) or voting (classification) their prediction results, a more robust and accurate final prediction is obtained.

[0044] The model form of the random forest model is as follows: Given T decision trees {h1(x),h2(x),...,h... T It consists of (x)}.

[0045] The training data for each tree is obtained by bootstrap sampling of the learning quantization dataset. When a node splits, a subset of features is randomly selected for evaluation to increase the independence between trees.

[0046] The mathematical form of the random forest model (regression scenario) is: The predictions of a random forest are the average of the predictions of all decision trees. ,in, : The prediction value of the t-th decision tree for input x.

[0047] T: The number of decision trees in the forest.

[0048] x: Multidimensional characteristics of comprehensive ability y: The final predicted value of the comprehensive ability score is the average of the predictions from multiple trees, which is more stable and has stronger resistance to overfitting than a single decision tree.

[0049] Step 230: Combine scores and predicted values ​​to form a weighted assessment of learning ability in each dimension.

[0050] Based on the specific classification, scoring, and prediction of comprehensive learning ability, numerical quantification of each dimension of comprehensive learning ability is formed. For example, single quantification of dimensions such as knowledge mastery, thinking ability, collaboration ability, and innovation ability are formed, as well as composite quantification combining two dimensions of ability, which more comprehensively reflects the changing trends of learners' abilities and their strengths and weaknesses in each learning cycle.

[0051] Step 240: Format the assessment results according to the feedback direction to form personalized competency data.

[0052] Feedback can be directed towards instructors, administrators, and learners. The presentation of individualized competency data varies depending on the direction of feedback. In one embodiment of this invention, the instructor feedback primarily uses charts and adjustment objects, the administrator feedback primarily uses charts and dataset objects, and the learner feedback feedback is presented in the form of text, audio, or video, based on assessment results and learner historical data.

[0053] The intelligent teaching assessment method of this invention obtains multi-dimensional evaluations and predictions of learning abilities from data on learning status through an ability assessment model. This fully quantifies the formation process, strengths, and weaknesses of learning abilities, providing a foundation for improvement for both teachers and students and meeting the needs of automatic optimization.

[0054] like Figure 1 As shown, in one embodiment of the present invention, step 300 includes: Step 310: Provide a human-computer interaction interface to parse personalized ability data and form an interactive control interface for educators to adjust personalized ability data and / or model weight parameters.

[0055] Given the quantitative errors in the collected data and the output errors in the ability assessment model, human intervention is crucial in the personalized ability data distribution process. The professional experience of instructors is used to verify the reasonableness of learners' comprehensive abilities. Comparison and modification tools provided through a human-computer interaction interface ensure the reliability of the comprehensive assessment results.

[0056] The intelligent teaching assessment method of this invention performs manual verification of data consistency during the transmission of personalized ability data, thus avoiding obvious errors in the automatic optimization process of learning resources.

[0057] like Figure 1 As shown, in one embodiment of the present invention, step 400 includes: Step 410: Based on personalized ability data, generate comprehensive ability suggestions in text and graphics and provide advanced path planning options to the learners.

[0058] By connecting the assessment data output by the competency assessment model with the management data of the teaching platform, configuration parameters for the learning resources of the teaching platform are formed. Based on personalized competency data, learning outcome displays and learning suggestions are generated for learners. At the same time, the learning path planning function of the teaching platform is used to generate advanced path planning options by providing personalized competency data.

[0059] Step 420: Adapt incentive mechanisms based on personalized ability data and configure incentive resources for distribution to learners.

[0060] Based on learners' phased learning achievements and incentive mechanisms, corresponding incentive resources are provided, including but not limited to badges, gifts, or points, to create immediate and long-term motivation for learners to continue learning.

[0061] Step 430: Configure the corresponding learning resources according to the learner's options, form a teaching schedule, and distribute it to the learner.

[0062] Based on learners' acceptance of the advanced learning path planning options, learning resources are configured according to personalized ability data, learning progress is set, and course resources are delivered in an orderly manner.

[0063] The intelligent teaching assessment method of this invention automates the allocation of teaching resources based on personalized ability data and the teaching incentive mechanism. This effectively ensures the resource utilization rate and teaching quality of the education platform.

[0064] In practical applications, the application process of the intelligent teaching assessment method of this invention is as follows: Figure 2 As shown. In Figure 2 In this process, learning status data of different levels and types is acquired through multi-source data acquisition, and a real-time streaming data acquisition and asynchronous batch log capture approach is adopted based on the characteristics of data formation. After cleaning, normalization, and feature extraction, the quantitative learning data is reconstructed to form a structured assessment dataset. Furthermore, a comprehensive assessment report is generated after quantitatively evaluating knowledge mastery, thinking ability, writing ability, and innovation ability using an ability assessment model. Based on the comprehensive assessment report, personalized data content in different directions is generated, providing instructors with adjustment parameters and interactive interfaces for optimizing resource allocation or model weights, and providing learners with graphical and textual displays of learning outcomes. Furthermore, personalized data is used as scheduling parameters for the teaching platform, enabling platform functions such as new learning path suggestions, course resource scheduling, and learning incentive feedback. Finally, data and assessments are iteratively updated according to learning progress.

[0065] An embodiment of the present invention is a teaching intelligent assessment system, such as... Figure 3 As shown, in Figure 3 In this embodiment, the following are included: Multidimensional data acquisition device 10 is used to acquire learning status data from the multi-channel teaching process that reaches learners, and form a quantitative learning dataset; The comprehensive ability assessment device 20 is used to analyze quantitative learning data through an ability assessment model to form a comprehensive assessment of learning ability, and to generate personalized ability data for feedback to both teachers and students based on the comprehensive assessment results. In the process of optimizing the control device 30, which is used to form feedback and incentive strategies based on personalized ability data, the weights are adjusted based on the teacher's prior data. The feedback and incentive interaction device 40 is used to adjust the configuration and distribution of learning resources based on personalized ability data and matching feedback and incentive strategies.

[0066] like Figure 3 As shown, in one embodiment of the present invention, the multidimensional data acquisition device 10 includes: Data acquisition module 11 is used to determine the learning environment that learners are exposed to, and to obtain the learning content, status, behavior and related statistical data from the learning environment according to the time sequence to form multi-source process data; The data processing module 12 is used to clean, fuse, and extract features from multi-source process data to form a learning quantization dataset.

[0067] like Figure 3 As shown, in one embodiment of the present invention, the comprehensive capability assessment device 20 includes: The scoring and assessment module 21 is used to conduct a multi-dimensional comprehensive assessment of learning ability through a weighted scoring model; Prediction and evaluation module 22 is used to make a multi-dimensional comprehensive prediction of learning ability through machine learning evaluation algorithms; Dimensional assessment module 23 is used to combine scores and predicted values ​​to weightedly assess the learning ability of each dimension; The assessment output module 24 is used to format the assessment results according to the feedback direction to form personalized ability data.

[0068] like Figure 3 As shown, in one embodiment of the present invention, the human body optimization control device 30 includes: The two-way calibration module 31 is used to provide a human-computer interaction interface to parse personalized ability data and form an interactive control interface for educators to adjust personalized ability data and / or model weight parameters.

[0069] like Figure 3 As shown, in one embodiment of the present invention, the feedback-stimulation interaction device 40 includes: The suggestion module 41 is used to generate comprehensive ability suggestions in text and graphics based on personalized ability data and provide advanced path planning options to be distributed to learners; The incentive adaptation module 42 is used to adapt the incentive mechanism according to personalized ability data and configure incentive resources to be distributed to learners. Resource adaptation module 43 is used to configure corresponding learning resources according to learner options, form a teaching schedule, and distribute it to learners.

[0070] This application also provides an electronic device, the structure of which is as follows: Figure 4As shown, the electronic device 4000 includes at least one processor 4001, a memory 4002, and a bus 4003. At least one processor 4001 is electrically connected to the memory 4002. The memory 4002 is configured to store at least one computer-executable instruction, and the processor 4001 is configured to execute the at least one computer-executable instruction, thereby performing the steps of any teaching intelligent assessment method provided in any embodiment or any optional embodiment of this application.

[0071] Furthermore, the processor 4001 can be an FPGA (Field-Programmable Gate Array) or other devices with logic processing capabilities, such as an MCU (Microcontroller Unit) or a CPU (Central Processing Unit).

[0072] This application also provides another computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the intelligent teaching assessment method provided in any embodiment or optional implementation of this application.

[0073] The computer-readable storage media provided in this application include, but are not limited to, any type of disk (including floppy disk, hard disk, optical disk, CD-ROM, and magneto-optical disk), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards. In other words, readable storage media include any medium by which a device (e.g., a computer) stores or transmits information in a readable form.

[0074] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method of teaching intelligent assessment, characterized by, include: Learning status data is obtained from the multi-channel teaching process that reaches learners, forming a quantitative learning dataset; By analyzing quantitative learning data through a competency assessment model, a comprehensive assessment of learning ability is formed, and personalized competency data is generated based on the comprehensive assessment results to provide feedback to both teachers and students. In the process of developing feedback and incentive strategies based on personalized ability data, weight adjustments are made based on the teacher's prior data. The allocation and distribution of learning resources are adjusted based on personalized ability data, feedback, and incentive strategies.

2. The method of claim 1, wherein, The formation of the learning quantization dataset includes: Identify the learning environment that learners are exposed to, and extract learning content, status, behavior, and related statistical data from the learning environment according to the time sequence to form multi-source process data; Multi-source process data are cleaned, fused, and feature extracted to form a learning quantization dataset.

3. The method of claim 1, wherein the teaching intelligence assessment is based on a plurality of teaching intelligence assessment criteria. The formation of the personalized capability data includes: A weighted scoring model is used to comprehensively assess learning ability across multiple dimensions. Multi-dimensional comprehensive prediction of learning ability is made through machine learning evaluation algorithms; The assessment of learning ability in each dimension is formed by combining scores and predicted values ​​with weighted averages. The assessment results are formatted according to the feedback direction to form personalized capability data.

4. The method of claim 1, wherein the teaching intelligent assessment method is characterized by, The formation of the weight adjustment includes: It provides a human-computer interaction interface to parse personalized ability data, forming an interactive control interface for educators to adjust personalized ability data and / or model weight parameters.

5. The intelligent teaching assessment method as described in claim 1, characterized in that, The configuration and distribution include: Based on personalized ability data, comprehensive ability suggestions in graphic and textual form are generated and advanced path planning options are provided to learners and distributed to them. Incentive mechanisms are adapted based on personalized ability data, and incentive resources are allocated and distributed to learners. Based on learner options, corresponding learning resources are configured to form a teaching schedule and distributed to learners.

6. A teaching intelligent assessment system, characterized in that, include: A multidimensional data acquisition device is used to acquire learning status data from multiple teaching processes that reach learners, forming a quantitative learning dataset. The comprehensive ability assessment device is used to analyze quantitative learning data through an ability assessment model to form a comprehensive assessment of learning ability, and to generate personalized ability data for feedback to both teachers and students based on the comprehensive assessment results. In the process of optimizing the control device to form feedback and incentive strategies based on personalized ability data, the weights are adjusted based on the teacher's prior data. The feedback and incentive interaction device is used to adjust the configuration and distribution of learning resources based on personalized ability data and matching feedback and incentive strategies.

7. The intelligent teaching assessment system as described in claim 6, characterized in that, The multidimensional data acquisition device includes: The data acquisition module is used to determine the learning environment that learners are exposed to, and to obtain the learning content, status, behavior and related statistical data from the learning environment according to the time sequence to form multi-source process data; The data processing module is used to clean, fuse, and extract features from multi-source process data to form a learning quantization dataset.

8. The intelligent teaching assessment system as described in claim 6, characterized in that, The comprehensive capability assessment device includes: The scoring and evaluation module is used to comprehensively score learning ability from multiple dimensions using a weighted scoring model. The prediction and evaluation module is used to make multi-dimensional comprehensive predictions of learning ability through machine learning evaluation algorithms. The dimensional assessment module is used to combine scores and predicted values ​​to weightedly assess learning ability in each dimension. The assessment output module is used to format the assessment results according to the feedback direction, forming personalized ability data.

9. The intelligent teaching assessment system as described in claim 6, characterized in that, The person in the optimized control device includes: The two-way calibration module is used to provide a human-computer interaction interface for parsing personalized ability data, forming an interactive control interface for educators to adjust personalized ability data and / or model weight parameters.

10. The intelligent teaching assessment system as described in claim 6, characterized in that, The feedback-incentive interaction device includes: The suggestion display module is used to generate comprehensive ability suggestions in text and graphics based on personalized ability data and provide advanced path planning options to be distributed to learners. The incentive adaptation module is used to adapt incentive mechanisms based on personalized ability data and configure incentive resources for distribution to learners. The resource adaptation module is used to configure corresponding learning resources according to learner options, form a teaching schedule, and distribute it to learners.

Images