Data processing method and device, electronic equipment and computer readable storage medium

Abstract

The invention discloses a data processing method, and relates to the technical field of education, and the specific implementation scheme is as follows: obtaining teaching behavior data of at least one education subject for teaching a learning subject and learning feedback data of the learning subject for each education subject; determining an evaluation dimension of the at least one education subject based on the teaching behavior data and the learning feedback data; performing evaluation of evaluation dimensions on the learning feedback data to obtain dimension values of the education subjects in the evaluation dimensions; and based on the dimension value of each education subject in each evaluation dimension, determining the teaching efficiency value of each education subject. Therefore, the performance of the educational subject can be comprehensively evaluated from different angles.

Description

Technical Field

[0001] The present disclosure belongs to the field of data processing, and in particular relates to a data processing method and device, an electronic device, and a computer-readable storage medium. Background Art

[0002] As a key component of modern distance education, online education provides people with convenient conditions for continuous learning. With the continuous progress of distance education, the research on the evaluation system and methods of online education effectiveness has received increasing attention. At present, the research on the effectiveness of online education mainly focuses on the in-depth longitudinal analysis of cost-effectiveness, and begins to try to compare the indicators of distance education effectiveness, resource utilization efficiency and graduate quality of different educational institutions (such as online education colleges) across institutions. However, most related studies rely on data and involve the perspective of teachers. These studies often focus on the subjective interpretation of teachers and are insufficient in quantitative analysis.

[0003] The advancement of educational informatization in recent years has not only brought about an explosive growth in the amount of information, but also put forward higher requirements for information extraction and analysis. How to mine potential rules and knowledge from massive data to assist decision-making has become an issue that we urgently need to solve. The rise and development of data mining technology has provided strong technical support for this demand. Compared with the traditional teaching model, the construction of the online teaching evaluation system is still insufficient. Many online teaching platforms lack effective teaching evaluation functions. Even if some platforms provide evaluation functions, the models used are often too simple and rigid to meet actual needs.

[0004] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the disclosure and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0005] The purpose of this disclosure is to evaluate the educational subject from multiple evaluation dimensions such as educational environment, educational management, educational effectiveness, and learning support service system, and obtain the teaching effectiveness value of the educational subject.

[0006] According to the first aspect, the present disclosure provides a data processing method, which includes: obtaining teaching behavior data of at least one educational subject teaching a learning subject and learning feedback data of the learning subject to each educational subject; determining the evaluation dimension of at least one educational subject based on the teaching behavior data and the learning feedback data; evaluating the learning feedback data in terms of the evaluation dimension to obtain the dimension value of each educational subject in each evaluation dimension; determining the teaching effectiveness value of each educational subject based on the dimension value of each educational subject in each evaluation dimension.

[0007] According to the second aspect, the present disclosure provides a data processing device, which includes: an acquisition unit, configured to acquire teaching behavior data of at least one educational subject teaching a learning subject and learning feedback data of the learning subject to each educational subject; a dimension determination unit, configured to determine the evaluation dimension of at least one educational subject based on the teaching behavior data and the learning feedback data; a obtaining unit, configured to evaluate the learning feedback data in terms of the evaluation dimension, and obtain the dimension value of each educational subject in each evaluation dimension; a value determination unit, configured to determine the teaching effectiveness value of each educational subject based on the dimension value of each educational subject in each evaluation dimension.

[0008] According to a third aspect, the present disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner of the first aspect.

[0009] According to a fourth aspect, the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect.

[0010] The data processing method and device provided by the embodiments of the present disclosure first obtain the teaching behavior data of at least one educational subject teaching a learning subject and the learning feedback data of the learning subject to each educational subject; secondly, based on the teaching behavior data and the learning feedback data, determine the evaluation dimension of at least one educational subject; thirdly, evaluate the evaluation dimension of the learning feedback data to obtain the dimension value of each educational subject in each evaluation dimension; finally, based on the dimension value of each educational subject in each evaluation dimension, determine the teaching effectiveness value of each educational subject. Thus, by evaluating the multi-dimensional aspects of the educational subject, the educational subject can be comprehensively evaluated from different angles, thereby improving the comprehensiveness of the educational evaluation; through the dimension value, the teaching effectiveness value of the educational subject is determined, and the educational ability of the educational subject is effectively quantified.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a flow chart of an embodiment of a data processing method according to the present disclosure;

[0013] Figure 2 is a schematic structural diagram of an embodiment of a data processing device according to the present disclosure;

[0014] Figure 3 It is a block diagram of an electronic device used to implement the data processing method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0015] Unless explicitly stated otherwise, throughout the specification and claims, the term “comprise” or variations such as “include” or “comprising”, etc., will be understood to include the stated elements or components but not to exclude other elements or components.

[0016] The technical solution of the present disclosure is described below by means of specific embodiments. It should be understood that one or more steps mentioned in the present disclosure do not exclude the existence of other methods and steps before and after the combination step, or other methods and steps may be inserted between these explicitly mentioned steps. It should also be understood that these examples are only used to illustrate the present disclosure and are not used to limit the scope of the present disclosure. Unless otherwise specified, the numbering of each method step is only for the purpose of identifying each method step, and does not limit the order of arrangement of each method or limit the scope of implementation of the present disclosure. Changes or adjustments in their relative relationships can also be regarded as the scope of implementation of the present disclosure without substantial changes in the technical content.

[0017] The sources of the raw materials and instruments used in the examples are not particularly limited and can be purchased from the market or prepared according to conventional methods known to those skilled in the art.

[0018] Comparative evaluation is a method of understanding oneself by comparing with others. It helps individuals to objectively understand themselves and others and make judgments based on actual conditions by comparing with classmates, peers and advanced figures.

[0019] Research on the effectiveness of online education has mainly focused on in-depth longitudinal analysis of cost-effectiveness, and has begun to attempt to compare indicators such as the effectiveness of distance education, resource utilization efficiency, and graduate quality of different educational institutions (such as online education colleges) across institutions. However, there are relatively few studies on comparative evaluation, and most related studies rely on data and involve the perspective of teachers. These studies often focus on the subjective interpretation of teachers and are insufficient in quantitative analysis.

[0020] Many online teaching platforms lack effective teaching evaluation functions. Even if some platforms provide evaluation functions, the models they adopt are often too simple and rigid to meet actual needs.

[0021] In view of the defects in the prior art, the present disclosure provides a data processing method, which determines the teaching effectiveness value of each educational subject based on teaching behavior data and learning feedback data, can effectively evaluate the educational subject, and provide a reference for assessing teaching participants. Figure 1A flow chart 100 of an embodiment of a data processing method is shown. The data processing method comprises the following steps:

[0022] Step 101, obtaining teaching behavior data of at least one educational subject teaching a learning subject and learning feedback data of the learning subject to each educational subject.

[0023] In this embodiment, the educational subject is the subject that provides educational knowledge in the learning activities, and the learning subject is the subject that receives educational knowledge in the learning activities. As for the environment of the educational subject and the learning subject, the educational subject and the learning subject can be the two parties conducting learning activities in the actual classroom, and the educational subject and the learning subject can also be the two parties conducting learning activities on the online education platform. Since the educational subject and the learning subject exchange information on the online education platform, the teaching behavior data of the educational subject and the learning feedback data of the learning subject can be obtained through the online education platform.

[0024] In this embodiment, the teaching behavior data refers to various behavior data of the education subject in the teaching process, such as teaching time, course participation, interaction frequency, etc. The teaching behavior data may also include teaching resource usage data, such as courseware usage information and teaching tool usage information; the learning feedback data refers to the feedback information made by the learning subject in response to the education of the education subject, such as students' text feedback and action feedback on the teacher's education situation. The text feedback includes student evaluation, interaction data, learning outcomes, etc.

[0025] In this embodiment, the environments where the education subject and the learning subject are located are different, and the methods of obtaining the teaching behavior data and the learning feedback data are different. For example, for the actual education environment, the teaching behavior data and the learning feedback data come from the classroom observation records collected by the camera device in the classroom; for the online education environment, the teaching behavior data and the learning feedback data come from the online teaching platform records. Optionally, for scenarios where it is difficult to obtain the learning feedback data, the learning feedback data can also be obtained through the evaluation of the education subject by the learning subject and the questionnaire survey of the learning subject.

[0026] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of the teaching behavior data of the educational subjects involved are carried out after authorization, comply with the provisions of relevant laws and regulations, and do not violate public order and good morals; the collection, storage, use, processing, transmission, provision and disclosure of the learning feedback data of the learning subjects involved are carried out after authorization, comply with the provisions of relevant laws and regulations, and do not violate public order and good morals; the information related to user information in the teaching behavior data and learning feedback data is information obtained after the user's permission, and the data processing related to the user in the teaching behavior data and learning feedback data is carried out under confidentiality conditions.

[0027] Step 102: Determine an evaluation dimension of at least one educational subject based on the teaching behavior data and the learning feedback data.

[0028] In this embodiment, the evaluation dimension is a hierarchical structure for evaluating the educational subject. Each educational subject has at least one evaluation dimension, each evaluation dimension represents an evaluation level, and all evaluation dimensions of each educational subject together constitute a comprehensive evaluation of the teaching ability of the educational subject. The construction of the evaluation dimension makes the evaluation of the educational subject more systematic and structured, and helps to comprehensively evaluate the performance of teachers from different angles.

[0029] In this embodiment, the evaluation dimension of the education subject can be given in combination with the existing evaluation system for evaluating teachers. Specifically, the above step 102 includes: determining at least one initial dimension of the education subject based on the teacher evaluation system; identifying the key factors affecting the teaching effect from at least one initial dimension based on the teaching behavior data and the learning feedback data, thereby determining the evaluation dimension. Among them, the initial dimension is the factor that has a major impact on the evaluation of the education subject, and the initial dimension includes: professional quality, teaching quality, student development, etc. Among them, the above-mentioned identification of the key factors affecting the teaching effect from at least one initial dimension based on the teaching behavior data and the learning feedback data includes: marking the teaching behavior data with behavior labels to determine the behavior labels that affect the teaching effect; analyzing the characteristics that affect the teaching effect of the learning feedback data to determine the educational characteristics; clustering the behavior labels and the educational characteristics to obtain multiple cluster types; dividing each cluster type in the multiple cluster types into different initial dimensions of at least one initial dimension, and determining the initial dimension with the most cluster types as the evaluation dimension.

[0030] In this embodiment, the evaluation dimensions may be teaching effectiveness, teaching methods, teaching attitude, etc.

[0031] Step 103, evaluate the learning feedback data in evaluation dimensions to obtain the dimension value of each educational subject in each evaluation dimension.

[0032] In this embodiment, the dimension value is the specific quantitative value of each evaluation dimension, and the dimension value can be quantified using a digital value to quantify the degree of the current evaluation dimension. To achieve the specific quantification of each evaluation dimension, a deep learning model or a machine learning model or a rule or a statistical technique can be used to calculate the specific dimension value of the learning feedback data to obtain the dimension value of the evaluation dimension of each educational subject. Specifically, the learning feedback data in the learning feedback data can be evaluated, for example, using natural language processing technology to extract key information in the learning feedback data, and combining expert scoring or peer evaluation, etc., to score each dimension and obtain the dimension value. The dimension value of each evaluation dimension has a corresponding range and meaning. For example: for the evaluation dimension of the teaching method, the dimension value range is 0-10 points, and the higher the score, the more accurate the teaching method.

[0033] In this embodiment, the administrator needs to understand the quality of the learning process through specific numerical values ​​rather than vague expressions. The dimensional values ​​of the evaluation dimensions are an important source of these data. By analyzing the learning feedback data, the learning feedback data of the learning subject is converted into the dimensional value of the teacher's teaching ability, thereby providing data support for the administrator's comprehensive evaluation of the education subject. To this end, through the specific scoring dimensions, the feedback of the learning subject is converted into an evaluation of the teacher's teaching ability to support the administrator's comprehensive evaluation of the learning process.

[0034] Step 104, based on the dimension values ​​of each educational subject in each evaluation dimension, determine the teaching effectiveness value of each educational subject.

[0035] In this embodiment, the teaching effectiveness value is an evaluation result of quantitatively evaluating the teaching ability of the education subject. The size of the teaching effectiveness value can reflect the size of the education subject's education ability to educate the learning subject.

[0036] In this embodiment, for each educational subject, the dimension values ​​of all evaluation dimensions of the educational subject may be added together to obtain the teaching effectiveness value of the educational subject.

[0037] The data processing method provided by the present disclosure first obtains the teaching behavior data of at least one educational subject teaching a learning subject and the learning feedback data of the learning subject to each educational subject; secondly, based on the teaching behavior data and the learning feedback data, determines the evaluation dimension of at least one educational subject; then, evaluates the evaluation dimension of the learning feedback data to obtain the dimension value of each educational subject in each evaluation dimension; finally, based on the dimension value of each educational subject in each evaluation dimension, determines the teaching effectiveness value of each educational subject. Thus, by evaluating the multi-dimensionality of the educational subject and determining the teaching effectiveness value of the educational subject, a scientific evaluation system is provided for the educational subject, and objective reference data is provided for management decision makers.

[0038] In some optional implementations of the present disclosure, the above-mentioned data processing method also includes: evaluating the learning status of the learning subject based on the learning feedback data, the teaching behavior data and the teaching effectiveness value to obtain a status evaluation value.

[0039] In this optional implementation, the learning status of the learning subject is the specific status displayed by the learning subject, and the learning status includes: the learning subject's knowledge level, skill mastery, learning motivation and other factors. Learning feedback data includes: text feedback and action feedback. Text feedback includes: text data such as student evaluation, interaction with the education subject, learning outcomes, etc.; action feedback includes: behavior data such as the learning subject's participation in educational activities, completion of homework, and participation in discussions. Teaching behavior data includes: teaching process data and teaching resource usage data, among which teaching process data includes: teaching time, course participation, interaction frequency, etc.; teaching resource usage data includes: courseware usage information, teaching tool usage information, etc. The teaching effectiveness value is the score of the education subject in each evaluation dimension (such as teaching methods, teaching attitudes, and teaching effectiveness, etc.).

[0040] In this optional implementation, the execution entity on which the data processing method runs will collect information from multiple data sub-modules of the online education platform, wherein the multiple data sub-modules of the online education platform include: a basic data sub-module, which includes: basic information of the learning subject, learning progress, etc.; a mutual evaluation data collection sub-module, which includes mutual evaluation information of the learning subject; a learning work collection sub-module, which includes learning achievements such as the learning subject's homework; and a reward and punishment record sub-module, which includes the reward and punishment records of the learning subject.

[0041] The above-mentioned evaluation of the learning status of the learning subject to obtain the status evaluation value includes: evaluating the influence of the learning subject's behavior data in the learning feedback data on the learning status to obtain the first status data, for example, analyzing the frequency of students' participation in classroom activities, the quality of completing homework, the enthusiasm for participating in discussions, etc., to judge their learning motivation, learning interest and learning attitude; evaluating the influence of teaching behavior data on the learning status of the learning subject under different teaching effectiveness values ​​to obtain the second status data, for example, analyzing the influence of different teaching styles and teaching methods on students' learning effects, learning interests and learning attitudes; based on the first status data and the second status data, obtaining the status evaluation value, the process of obtaining the status evaluation value is a comprehensive evaluation result, rather than just an evaluation of a certain aspect. Among them, the first status data and the second status data are both the actual status of the learning subject in teaching.

[0042] The data processing method provided by this optional implementation method evaluates the status of the learning subject and can conduct a comprehensive status analysis of the learning subject, thereby improving the versatility and inclusiveness of the status evaluation.

[0043] Optionally, the data processing method further includes: based on the state evaluation value, evaluating the influence of the behavior data of the learning subject in the learning feedback data on the learning state to obtain an evaluation result. For example, analyzing the frequency of students' participation in classroom activities, the quality of their homework, their enthusiasm for participating in discussions, etc., to judge their learning motivation, learning interest and learning attitude.

[0044] In some optional implementations of the present disclosure, the above method also includes: obtaining classroom behavior data of the learning subject; obtaining behavior pattern information of the learning subject based on the classroom behavior data and the perceptual behavior pattern model; and the teaching effectiveness value is also determined based on the behavior pattern information.

[0045] In this optional implementation, the classroom behavior data refers to the behavior data of the learning subject during the teaching process when the educational subject provides teaching.

[0046] In this optional implementation, the perceptual behavior pattern model is a model used to analyze learners' online learning behaviors and identify their behavior patterns and behavior characteristics. It takes the behavior data of the learning subject as input and outputs the learner's behavior patterns and characteristics. Specifically, the input of the perceptual behavior pattern model can be the learning behavior data of the learning subject (including classroom behavior data). The specific learning behavior data includes the learner's login frequency, learning time, course participation, interactive behavior, homework grades, etc. The output of the perceptual behavior pattern model: identify similar behavior patterns of learners, such as learners who actively participate in discussions, learners who learn passively, etc. Extract the behavioral characteristics of the learning subject, such as learning efficiency, learning interest, learning style, etc.

[0047] In this optional implementation, the perception behavior pattern model is obtained by using step a to step e training steps:

[0048] aData preprocessing: Clean, denoise, and standardize the collected learning behavior data.

[0049] bFeature engineering: extract features from learning behavior data, such as learning time, learning frequency, learning depth, etc.

[0050] c Cluster analysis: Use clustering algorithms, such as the K-means algorithm, to group learners according to their behavioral characteristics to form different behavioral patterns.

[0051] dPattern recognition: Analyze the characteristics of different behavioral patterns and identify the behavioral characteristics of learners.

[0052] eModel training: Use machine learning algorithms, such as support vector machines (SVM) or neural networks, to associate learning behavior data with behavior patterns and features to train a perception behavior pattern model.

[0053] The key points of the perceptual behavior pattern model training process are: Selecting features that can effectively distinguish different behavior patterns can train an accurate model. Selecting a suitable clustering algorithm can effectively identify different behavior patterns. Selecting a suitable machine learning algorithm can effectively associate learning behavior data with behavior patterns and features.

[0054] In this optional implementation, the teaching effectiveness value of each educational subject can be determined based on the behavior pattern information and the dimension values ​​of each evaluation dimension of each educational subject; specifically, the above-mentioned determination of the teaching effectiveness value of each educational subject based on the behavior pattern information and the dimension values ​​of each evaluation dimension of each educational subject includes: evaluating the teaching added value of the educational subject corresponding to the behavior pattern information according to the behavior pattern information, wherein the teaching added value is the value that can be increased by evaluating the teaching effectiveness of the educational subject, and the size of the teaching added value can be obtained by evaluating the specific performance of the behavior pattern information. For this purpose, a value can be set for the teaching added value based on the specific performance of the students, for example: the behavior pattern information shows that the students have high learning efficiency, which means that the teacher's teaching method is effective, the teaching ability is strong, and the teaching added value is large. The behavior pattern information shows that the students have a strong interest in learning, which means that the teacher's teaching content is interesting, the teaching ability is strong, and the teaching added value is large. The behavior pattern information shows that the teacher's teaching style matches the student's learning style, which means that the teacher's teaching ability is strong and the teaching added value is large.

[0055] In this optional implementation, the dimension values ​​of all evaluation dimensions of the educational subject are added to the teaching added value to obtain the teaching effectiveness value.

[0056] The data processing method provided by this optional implementation method obtains the classroom behavior data of the learning subject; based on the classroom behavior data and the perceptual behavior pattern model, the behavior pattern information of the learning subject is obtained; the teaching effectiveness value is also determined based on the behavior pattern information, thereby improving the reliability and accuracy of the teaching effectiveness value.

[0057] In some optional implementations of the present disclosure, the above method also includes: determining the interactive relationship information between the learning subject and each educational subject based on the perceptual behavior pattern model, classroom behavior data and teaching behavior data; the teaching effectiveness value is also determined based on the interactive relationship information.

[0058] In this optional implementation, the interactive relationship information is the interactive information between the education subject and the learning subject, such as the interaction frequency, interaction depth, and evaluation information of the interactive effect. Interaction frequency: By analyzing the frequency of interaction between the learning subject and the teacher, it can be judged whether the teacher actively communicates with the students and whether he pays attention to the students' learning and feedback. Interaction depth: Analyze the interactive content to judge whether the teacher can answer the students' questions in depth and whether he can guide the students to think and explore.

[0059] In this optional implementation, interactive relationship information can be obtained through the interactive relationship analysis model. Specifically, the process of obtaining the interactive relationship information is as follows: first, the collected perceptual behavior data, classroom behavior data, and teaching behavior data are cleaned and standardized, and irrelevant data, outliers, etc. are removed to ensure data quality and obtain processed data; behavioral features related to interactive relationships are extracted from the above processed data, and the behavioral features related to interactive relationships include: perceptual behavior features, classroom behavior features, and teaching behavior features; among them, perceptual behavior features are learners' learning style, learning efficiency, learning interest, etc. Classroom behavior features are learners' classroom participation, question frequency, answer quality, etc. Teaching behavior features are teachers' teaching style, classroom interaction frequency, difficulty of teaching content, etc. The above-mentioned behavioral features related to interactive relationships are integrated and input into the interactive relationship analysis model to obtain interactive relationship information output by the interactive relationship analysis model.

[0060] In this optional implementation, multiple machine learning models are used to implement the interactive relationship analysis model. Through this machine learning model, the interactive relationship information of the interactive relationship between the learning subject and the educational subject can be analyzed. For example, the following methods are used:

[0061] Cluster analysis groups learning subjects according to their perceptual behavior patterns, identifies groups of learning subjects with similar learning characteristics, and analyzes the interaction patterns between these groups and educational subjects.

[0062] Association rule mining: analyzing the association between learning behavior data and teaching behavior data, and identifying key factors that affect the interaction effect.

[0063] The classification model predicts the learning status and learning outcomes of the learning subject based on the interactive behavior data and evaluates the interactive effect.

[0064] Optionally, a deep learning model can be used to obtain an interactive relationship analysis model, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), to analyze text data, such as classroom discussion records or learners' study notes, to identify the interactive content and emotional tendencies between learners and educational subjects.

[0065] In this optional implementation, the teaching effectiveness value is also determined based on the interactive relationship information, that is, the teaching effectiveness value of each educational subject is determined based on the interactive relationship information and the dimensional values ​​of each evaluation dimension of each educational subject; specifically, for each educational subject, based on the interactive relationship information and the dimensional values ​​of each evaluation dimension of each educational subject, the teaching effectiveness value of the educational subject is determined, including: determining the interactive added value of the educational subject according to the interactive relationship information; adding the dimensional values ​​of all evaluation dimensions of the educational subject to the interactive added value to obtain the teaching effectiveness value.

[0066] In this optional implementation, the interaction added value is the additional teaching effectiveness value that can be added to the educational subject due to the interaction between the learning subject and the educational subject. Positive interaction can make the interaction added value positive, and negative interaction can make the interaction added value negative. Specifically, the interaction added value between the learning subject and the educational subject can be evaluated based on indicators such as interaction frequency, interaction content, and interaction quality in the interaction relationship information. The interaction added value can also be determined based on the interaction patterns identified between different learning subjects and educational subjects, such as active interaction, passive interaction, and cooperative interaction. The data processing method provided by this optional implementation determines the interaction relationship information between the learning subject and each educational subject based on the perceptual behavior pattern model, classroom behavior data, and teaching behavior data; the control teaching effectiveness value is also determined based on the interaction relationship information, which improves the reliability and accuracy of the teaching effectiveness value.

[0067] In some optional implementations of the present disclosure, the above-mentioned learning feedback data includes: feedback vocabulary; obtaining the learning feedback data of the learning subject to each educational subject includes: extracting text data in the learning feedback data; performing data cleaning on the text data to obtain cleaned data; frequency marking the vocabulary in the cleaned data to obtain the frequency value of each vocabulary in the cleaned data; determining high-frequency vocabulary based on the frequency value of each vocabulary; preprocessing and semantic analysis of high-frequency vocabulary to obtain semantic information of high-frequency vocabulary; based on the semantic information, selecting feedback vocabulary related to educational decisions from the high-frequency vocabulary.

[0068] In this optional implementation, the method for obtaining feedback vocabulary includes the following steps: Step_1 to Step_6:

[0069] Step_1 Data collection: Collect text data from the learning subject's learning feedback data, such as comment text, messages, and discussion forum speeches.

[0070] Step_2 Data cleaning: Clean the collected text data, remove irrelevant characters, punctuation marks, stop words, etc., and perform word segmentation.

[0071] Step_3 Word frequency statistics: Use word frequency statistics tools, such as Python's jieba library, to count the frequency of each word appearing in the text.

[0072] Step_4 High-frequency vocabulary screening: Set a threshold, for example, words that appear more than a certain number of times are considered high-frequency words.

[0073] Step_5 Lexical analysis: Further analysis is performed on the selected high-frequency words, such as part-of-speech tagging and word sense disambiguation, to understand their meaning and function.

[0074] Step_6 Knowledge extraction: Based on high-frequency words, extract feedback words such as the learning subject's feedback, learning needs, and learning difficulties, and provide reference for educational decision-making through feedback words.

[0075] The method for obtaining feedback vocabulary provided by this optional implementation method extracts text data from learning feedback data; performs data cleaning on the text data to obtain cleaned data; performs frequency annotation on the vocabulary in the cleaned data to obtain the frequency value of each vocabulary in the cleaned data; determines high-frequency vocabulary based on the frequency value of each vocabulary; performs preprocessing and semantic analysis on the high-frequency vocabulary to obtain the semantic information of the high-frequency vocabulary; based on the semantic information, selects feedback vocabulary related to educational decision-making from the high-frequency vocabulary, which provides a reliable implementation method for obtaining feedback vocabulary and improves the reliability of obtaining feedback vocabulary.

[0076] In some optional implementations of the present disclosure, the above-mentioned determination of the evaluation dimension of at least one educational subject based on the teaching behavior data and the learning feedback data includes: clustering the teaching behavior data to identify educational groups with similar teaching characteristics; identifying at least two educational characteristics of the educational groups based on the teaching behavior data of the educational groups; determining at least one key factor affecting the teaching effect based on the learning feedback data and the teaching behavior data; extracting the main factor affecting the key teaching event from at least one key factor; and determining the evaluation dimension of at least one educational subject based on the main factor and the educational characteristics.

[0077] In this optional implementation, the above-mentioned clustering of teaching behavior data is to cluster the teaching behavior data using the K-means algorithm. After the teaching behavior data is clustered, each type of educational subject can be regarded as an educational group, and the teaching characteristics of each educational group can be identified based on the teaching behavior data. Through the method disclosed in the present invention, at least three educational groups with similar teaching characteristics can be identified.

[0078] In this optional implementation, the educational feature is a feature that reflects the overall characteristics of the educational group, such as the educational features are: classroom interaction frequency and teaching style. Based on the teaching behavior data of the educational group, identifying at least two educational features of the educational group includes: inputting the teaching behavior data of the educational group into a feature extraction model to obtain educational features output by the feature extraction model. The feature extraction model is used to perform educational feature analysis on the behavior data to obtain educational features.

[0079] In this optional implementation, the key factors are the core elements that affect the teaching effect. By analyzing the key factors, problems in teaching can be identified, such as: Is the teaching content clear and easy to understand? Is the teaching method effective? Is the teaching rhythm appropriate? Does the educational subject pay attention to the individual differences of the learning subjects? The key factors can help determine the specific content of the evaluation dimensions. For example, if the key factor is "the depth of the teaching content", then "the depth of the teaching content" can be used as one of the evaluation dimensions. The above-mentioned determination of at least one key factor affecting the teaching effect based on the learning feedback data and the teaching behavior data includes: performing action and frequency analysis on the learning feedback data, determining feedback data with multiple feedbacks on the teaching actions, and extracting feedback data in the learning feedback data whose feedback times on the teaching behavior data reach a set number of times or a set frequency, and performing factor analysis on the feedback data to obtain the key factors.

[0080] In this optional implementation, the above-mentioned main factors are key factors that affect key teaching events among at least one key factor. For example, the key teaching event is academic performance or learning interest, and the key factors affecting the learning performance of the learning subject may include class participation and homework completion, that is, the main factors are: class participation and homework completion.

[0081] In this optional implementation, the above-mentioned determination of at least two evaluation dimensions of at least one educational subject based on main factors and educational characteristics includes: matching educational characteristics with main factors, and in response to the matching of educational characteristics with main factors, directly using key factors as evaluation dimensions, for example, using "depth of teaching content" as one of the evaluation dimensions.

[0082] Optionally, the above-mentioned determination of at least two evaluation dimensions of at least one educational subject based on main factors and educational characteristics includes: multi-level decomposition of key factors, and determination of evaluation dimensions under the multiple levels, that is, taking the key factors as the basis for constructing other evaluation dimensions. For example, based on the key factor "whether the educational subject pays attention to the individual differences of the learning subjects", the "personalized teaching" evaluation dimension can be constructed, including sub-dimensions such as "differentiated teaching strategies" and "learning subject participation".

[0083] Optionally, the above-mentioned determination of at least two evaluation dimensions of at least one educational subject based on main factors and educational characteristics includes: comprehensively analyzing key factors with other factors to construct a more comprehensive and multi-dimensional evaluation dimension, for example, comprehensively analyzing the key factors "diversity of teaching methods" and "learning interests of learning subjects" to construct an "effectiveness of teaching methods" evaluation dimension.

[0084] The method for determining evaluation dimensions provided by this optional implementation method clusters the teaching behavior data to identify educational groups with similar teaching characteristics; identifies at least two educational characteristics of the educational groups based on the teaching behavior data of the educational groups; determines at least one key factor affecting the teaching effect based on the learning feedback data and the teaching behavior data; extracts the main factors affecting key teaching events from at least one key factor; and determines the evaluation dimensions of at least one educational subject based on the main factors and the educational characteristics, which provides a reliable implementation basis for obtaining the evaluation dimensions and improves the reliability of obtaining the evaluation dimensions.

[0085] In some optional implementations of the present disclosure, the above-mentioned learning feedback data includes: feedback vocabulary, evaluating the evaluation dimensions of the learning feedback data, and obtaining the dimensional value of each educational subject in each evaluation dimension, including: using an education evaluation model to evaluate the evaluation dimensions of the feedback vocabulary, and obtaining the dimensional value of each educational subject in each evaluation dimension.

[0086] In this optional implementation, the education evaluation model includes: a sentiment classification sub-model and a dimensional evaluation sub-model. Among them, the sentiment classification sub-model is used to perform semantic analysis and sentiment classification on unstructured feedback vocabulary. The sentiment classification sub-model converts feedback vocabulary into structured data, for example, classifying feedback vocabulary into three types of positive, negative or neutral emotions. Through the sentiment classification sub-model, text content that is not related to the evaluation of teaching ability can be excluded, such as text in which the learning subject discusses the course content. Distinguishing whether the learning subject's evaluation of the education subject is positive or negative provides a basis for subsequent dimensional evaluation.

[0087] In this optional implementation, semantic analysis plays a vital role in the sentiment classification sub-model, which provides a basis for sentiment classification and dimension evaluation. Through the word vector model, the words in the text are converted into vector representations to capture the semantic relationship between words, providing more accurate information for subsequent sentiment classification and dimension evaluation. By calculating the similarity between word vectors, semantic information related to educational evaluation, such as "teaching methods", "teaching content", "teaching attitude", etc., is identified to provide a reference for the dimension evaluation sub-model.

[0088] In this optional implementation, the dimension evaluation sub-model is used to perform dimension evaluation on the structured data after sentiment classification. The model also generates the dimension values ​​of the education subject in each evaluation dimension based on the sentiment classification results and text content. The dimension evaluation sub-model converts the evaluation of the education subject by the learning subject into a specific score value, which facilitates the horizontal comparison of the teaching ability of different education subjects, evaluates the teaching ability of the education subject from different dimensions, and provides a more comprehensive evaluation result.

[0089] The method for obtaining the dimension value of the evaluation dimension provided by this optional implementation method evaluates the evaluation dimension of the feedback vocabulary in the learning feedback data through the education evaluation model, obtains the dimension value of each evaluation dimension, and improves the reliability of obtaining the dimension value of the evaluation dimension. The education evaluation model is a complex system, which is composed of the sentiment classification sub-model and the dimension evaluation sub-model working together to complete the evaluation of the teaching ability of the education subject. Semantic analysis provides a basis for the model, helps the model understand the text content, and performs accurate sentiment classification and dimension evaluation.

[0090] Optionally, the learning feedback data includes: feedback actions and feedback words, and the evaluation of the feedback words in the evaluation dimension to obtain the dimension value of each educational subject in each evaluation dimension includes: using the perceptual behavior pattern model to identify the behavior pattern information of the feedback action to obtain the behavior pattern information of the feedback action, and obtaining the dimension coefficient based on the behavior pattern information; using the education evaluation model to evaluate the evaluation dimension of the feedback words to obtain the sub-dimension value of each educational subject in each evaluation dimension; multiplying the dimension coefficient with the sub-dimension value to obtain the dimension value of each evaluation dimension. The feedback action is the feedback of the learning subject to the teaching behavior of the educational subject, such as raising hands, answering questions, sleeping, etc. The dimension coefficient is the weight value of the role of the feedback action of the learning subject in the evaluation dimension value. The larger the coefficient, the stronger the learning participation expressed by the feedback action; the smaller the coefficient, the lower the learning participation expressed by the feedback action.

[0091] In some optional implementations of the present disclosure, the above-mentioned education evaluation model is trained using training steps: obtaining a training sample set, the training sample set includes at least one training sample, each training sample includes a comment text, a text sentiment annotation corresponding to the comment text, and a dimension value; obtaining an initial education evaluation model, the education evaluation model includes: a sentiment classification sub-model and a dimension evaluation sub-model; the sentiment classification sub-model is used to perform sentiment classification on the text to obtain sentiment classification information; the dimension evaluation sub-model is used to evaluate the sentiment classification information and the text on each evaluation dimension to obtain the dimension value of each evaluation dimension; performing the following training steps: selecting training samples from the training sample set; inputting the selected training samples into the education evaluation model to obtain the dimension value of each evaluation dimension output by the education evaluation model; based on the dimension value, calculating the loss value of the education evaluation model; in response to the education evaluation model satisfying the training completion condition, obtaining a trained education evaluation model.

[0092] In this optional implementation, the above-mentioned input of the selected training samples into the education evaluation model to obtain the dimension values ​​of each evaluation dimension output by the education evaluation model includes: inputting the comment text in the selected training samples into the sentiment classification sub-model to obtain the sentiment classification information output by the sentiment classification sub-model; inputting the sentiment classification information and the comment text into the dimension evaluation sub-model to obtain the dimension values ​​of each evaluation dimension output by the dimension evaluation sub-model.

[0093] In this optional implementation, the above-mentioned calculation of the loss value of the education evaluation model based on the dimension value includes: calculating the classification loss of the sentiment classification sub-model based on the dimension value and the text sentiment annotation corresponding to the comment text; calculating the computational loss of the dimension evaluation sub-model based on the dimension value and the dimension value corresponding to the comment text; obtaining the loss value of the education evaluation model based on the classification loss and the computational loss.

[0094] In this optional implementation, the above-mentioned loss value of the education evaluation model based on the classification loss and the calculation loss includes: adding the classification loss and the calculation loss to obtain the loss value of the education evaluation model. Alternatively, the classification loss and the weight value of the sentiment classification sub-model are multiplied, and the calculation loss and the weight of the dimension evaluation sub-model are multiplied to obtain the loss value of the education evaluation model, wherein the weight value of the sentiment classification sub-model and the weight of the dimension evaluation sub-model can be set based on development needs.

[0095] The education evaluation model training method provided by this optional implementation method trains the sentiment classification sub-model and the dimension evaluation sub-model respectively through training samples to obtain a trained education evaluation model, thereby improving the accuracy of education evaluation model training.

[0096] In some optional implementations of the present disclosure, the above-mentioned determination of the teaching effectiveness value of each educational subject based on the dimensional value of each educational subject in each evaluation dimension includes: determining the weight value of each evaluation dimension based on each evaluation dimension of each educational subject; for each educational subject, weightedly summing the dimensional values ​​of each evaluation dimension of the educational subject according to the weight values ​​of each evaluation dimension, to obtain the teaching effectiveness value of the educational subject.

[0097] The method for determining the teaching effectiveness value of each educational subject provided by this optional implementation method determines the weight value of each evaluation dimension based on each evaluation dimension of each educational subject; for each educational subject, the dimension values ​​of each evaluation dimension of the educational subject are weighted and summed according to the weight values ​​of each evaluation dimension to obtain the teaching effectiveness value of the educational subject, which provides a reliable implementation method for obtaining the teaching effectiveness value and improves the reliability and accuracy of obtaining the teaching effectiveness value.

[0098] Further references Figure 2As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a data processing device, which is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0099] like Figure 2 As shown, the data processing device 200 provided in this embodiment includes: an acquisition unit 201, a dimension determination unit 202, a obtaining unit 203, and a value determination unit 204. Among them, the above-mentioned acquisition unit 201 can be configured to obtain the teaching behavior data of at least one educational subject teaching a learning subject and the learning feedback data of the learning subject to each educational subject. The above-mentioned dimension determination unit 202 can be configured to determine the evaluation dimension of at least one educational subject based on the teaching behavior data and the learning feedback data. The above-mentioned obtaining unit 203 can be configured to evaluate the evaluation dimension of the learning feedback data and obtain the dimension value of each educational subject in each evaluation dimension. The above-mentioned value determination unit 204 can be configured to determine the teaching effectiveness value of each educational subject based on the dimension value of each educational subject in each evaluation dimension.

[0100] In this embodiment, in the data processing device 200, the specific processing of the acquisition unit 201, the dimension determination unit 202, the obtaining unit 203, and the value determination unit 204 and the technical effects thereof can be referred to respectively. Figure 1 The relevant descriptions of step 101, step 102, step 103, and step 104 in the corresponding embodiment are not repeated here.

[0101] In one embodiment of the present disclosure, the above-mentioned device also includes an evaluation unit, which is configured to: evaluate the learning state of the learning subject based on the learning feedback data, the teaching behavior data and the teaching effectiveness value to obtain a state evaluation value.

[0102] In one embodiment of the present disclosure, the above-mentioned device also includes a teaching effectiveness value determination unit, which is configured to: obtain classroom behavior data of the learning subject; obtain behavior pattern information of the learning subject based on the classroom behavior data and the perceptual behavior pattern model; and the teaching effectiveness value is also determined based on the behavior pattern information.

[0103] In one embodiment of the present disclosure, the above-mentioned device also includes an interactive relationship determination unit, which is configured to: determine the interactive relationship information between the learning subject and each educational subject based on the perceived behavior pattern model, classroom behavior data, and teaching behavior data; the teaching effectiveness value is also determined based on the interactive relationship information.

[0104] In one embodiment of the present disclosure, the above-mentioned learning feedback data includes: feedback vocabulary, and the above-mentioned acquisition unit 201 is further configured to: extract text data in the learning feedback data; perform data cleaning on the text data to obtain cleaned data; use a word frequency statistics tool to frequency-label the vocabulary in the cleaned data to obtain the frequency value of each vocabulary in the cleaned data; determine high-frequency vocabulary based on the frequency value of each vocabulary; pre-process and semantically analyze the high-frequency vocabulary to obtain semantic information of the high-frequency vocabulary; based on the semantic information, select feedback vocabulary related to educational decisions from the high-frequency vocabulary.

[0105] In one embodiment of the present disclosure, the above-mentioned dimension determination unit 202 is further configured to: cluster the teaching behavior data to identify educational groups with similar teaching characteristics; identify at least two educational characteristics of the educational groups based on the teaching behavior data of the educational groups; determine at least one key factor affecting the teaching effect based on the learning feedback data and the teaching behavior data; extract the main factor affecting the key teaching event from at least one key factor; and determine the evaluation dimension of at least one educational subject based on the main factor and the educational characteristics.

[0106] In one embodiment of the present disclosure, the learning feedback data includes feedback vocabulary, and the obtaining unit 203 is further configured to evaluate the feedback vocabulary in evaluation dimensions using an education evaluation model to obtain the dimension value of each education subject in each evaluation dimension.

[0107] In one embodiment of the present disclosure, the above-mentioned education evaluation model is obtained by training with a training unit, and the above-mentioned training unit is configured to: obtain a training sample set, the training sample set includes at least one training sample, each training sample includes a comment text, a text sentiment annotation and a dimension value corresponding to the comment text; obtain an initial education evaluation model, the education evaluation model includes: a sentiment classification sub-model and a dimension evaluation sub-model; the sentiment classification sub-model is used to perform sentiment classification on the text to obtain sentiment classification information; the dimension evaluation sub-model is used to evaluate the sentiment classification information and the text on each evaluation dimension to obtain the dimension value of each evaluation dimension; perform the following training steps: select training samples from the training sample set; input the selected training samples into the education evaluation model to obtain the dimension value of each evaluation dimension output by the education evaluation model; based on the dimension value, calculate the loss value of the education evaluation model; in response to the education evaluation model meeting the training completion condition, obtain a trained education evaluation model.

[0108] In one embodiment of the present disclosure, the above-mentioned value determination unit 204 is further configured to: determine the weight value of each evaluation dimension based on each evaluation dimension of each educational subject; for each educational subject, weightedly sum the dimension values ​​of each evaluation dimension of the educational subject according to the weight value of each evaluation dimension, so as to obtain the teaching ability value and teaching effectiveness value of the educational subject.

[0109] In the data processing device provided in the embodiment of the present disclosure, first, the acquisition unit 201 acquires the teaching behavior data of at least one educational subject teaching the learning subject and the learning feedback data of the learning subject to each educational subject; secondly, the dimension determination unit 202 determines the evaluation dimension of at least one educational subject based on the teaching behavior data and the learning feedback data; then, the acquisition unit 203 evaluates the evaluation dimension of the feedback vocabulary to obtain the dimension value of each educational subject in each evaluation dimension; finally, the value determination unit 204 determines the teaching effectiveness value of each educational subject based on the dimension value of each educational subject in each evaluation dimension. Therefore, by evaluating the multi-dimensionality of the educational subject and determining the teaching effectiveness value of the educational subject, a more scientific evaluation system is provided for the educational subject, and objective reference data is provided for management decision makers.

[0110] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0111] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0112] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their modes are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0113] like Figure 3As shown, the device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0114] A number of components in the device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0115] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

[0116] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0117] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, causes the modes / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0118] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0119] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0120] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0121] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0122] The foregoing description of specific exemplary embodiments of the present disclosure is for the purpose of illustration and demonstration. These descriptions are not intended to limit the present disclosure to the precise form disclosed, and it is clear that many changes and variations can be made based on the above teachings. The purpose of selecting and describing the exemplary embodiments is to explain the specific principles of the present disclosure and its practical application, so that those skilled in the art can realize and utilize various different exemplary embodiments of the present disclosure and various different selections and changes. The scope of the present disclosure is intended to be defined by the claims and their equivalents.

Claims

1. A data processing method, the method comprising: Acquire teaching behavior data of at least one educational subject teaching a learning subject and learning feedback data of the learning subject to each educational subject; Determining an evaluation dimension of the at least one education subject based on the teaching behavior data and the learning feedback data; Evaluate the learning feedback data according to the evaluation dimensions to obtain the dimension values ​​of each educational subject in each evaluation dimension; Based on the dimension values ​​of each educational subject in each evaluation dimension, the teaching effectiveness value of each educational subject is determined.

2. The method according to claim 1, further comprising: Based on the learning feedback data, the teaching behavior data and the teaching effectiveness value, the learning state of the learning subject is evaluated to obtain a state evaluation value.

3. The method according to claim 1, further comprising: Acquiring classroom behavior data of the learning subject; Based on the classroom behavior data and the pre-trained perceptual behavior pattern model, the behavior pattern information of the learning subject is obtained, and the perceptual behavior pattern model is used to characterize the corresponding relationship between the subject behavior data and the behavior pattern information; The teaching effectiveness value is also determined based on the behavior pattern information.

4. The method according to claim 3, further comprising: Determining the interactive relationship information between the learning subject and each educational subject based on the perception behavior pattern model, the classroom behavior data and the teaching behavior data; The teaching effectiveness value is also determined based on the interactive relationship information.

5. The method according to any one of claims 1 to 4, wherein: The learning feedback data includes: feedback vocabulary; the acquisition of the learning feedback data of the learning subject to each educational subject includes: Extracting text data from the learning feedback data; Performing data cleaning on the text data to obtain cleaned data; Performing frequency marking on the words in the cleaned data to obtain the frequency value of each word in the cleaned data; Based on the frequency values ​​of each word, high frequency words are determined; Preprocessing and semantically analyzing the high-frequency words to obtain semantic information of the high-frequency words; Based on the semantic information, feedback words related to educational decision-making are selected from the high-frequency words.

6. The method according to any one of claims 1 to 4, wherein: The determining of the evaluation dimension of the at least one education subject based on the teaching behavior data and the learning feedback data comprises: Clustering the teaching behavior data to identify education groups with similar teaching characteristics; Based on the teaching behavior data of the education group, identifying at least two educational characteristics of the education group; Determine at least one key factor affecting the teaching effect based on the learning feedback data and the teaching behavior data; Extract at least one of the key factors that influence key teaching events; Based on the main factors and the educational characteristics, at least two evaluation dimensions of the at least one educational subject are determined.

7. The method according to any one of claims 1 to 4, wherein: The learning feedback data includes: feedback vocabulary, and the evaluating the evaluation dimensions of the learning feedback data to obtain the dimension values ​​of each educational subject in each evaluation dimension includes: using an education evaluation model to evaluate the feedback vocabulary in the evaluation dimensions to obtain the dimension values ​​of each educational subject in each evaluation dimension.

8. The method according to claim 7, wherein: The education evaluation model is trained using the training steps: Acquire a training sample set, wherein the training sample set includes at least one training sample, and each training sample includes a comment text, a text sentiment annotation corresponding to the comment text, and a dimension value; Obtain an initial education evaluation model, the education evaluation model comprising: a sentiment classification sub-model and a dimension evaluation sub-model; the sentiment classification sub-model is used to perform sentiment classification on the text to obtain sentiment classification information; the dimension evaluation sub-model is used to evaluate the sentiment classification information and the text in each evaluation dimension to obtain the dimension value of each evaluation dimension; perform the following training steps: Selecting training samples from the training sample set; Inputting the selected training samples into the education evaluation model to obtain the dimension values ​​of each evaluation dimension output by the education evaluation model; Based on the dimension value, calculating the loss value of the education evaluation model; In response to the educational evaluation model satisfying the training completion condition, a trained educational evaluation model is obtained.

9. The method according to any one of claims 1 to 4, wherein: Determining the teaching effectiveness value of each educational subject based on the dimension value of each educational subject in each evaluation dimension includes: Based on the various evaluation dimensions of each educational subject, determine the weight value of each evaluation dimension; For each educational subject, the dimension values ​​of each evaluation dimension of the educational subject are weighted and summed according to the weight values ​​of each evaluation dimension to obtain the teaching effectiveness value of the educational subject.

10. A data processing device, characterized in that: The device comprises: An acquisition unit configured to acquire teaching behavior data of at least one educational subject teaching a learning subject and learning feedback data of the learning subject to each educational subject; a dimension determination unit, configured to determine an evaluation dimension of the at least one education subject based on the teaching behavior data and the learning feedback data; An obtaining unit is configured to evaluate the evaluation dimension on the learning feedback data to obtain the dimension value of each educational subject in each evaluation dimension; The value determination unit is configured to determine the teaching effectiveness value of each educational subject based on the dimension value of each educational subject in each evaluation dimension.

11. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 9.

12. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 9.

Images