Classroom evaluation method and device, equipment and storage medium

Abstract

The invention discloses a classroom evaluation method and device, equipment and a storage medium, and the method comprises the steps: obtaining manual evaluation data and a machine analysis result of teaching data of this time, the manual evaluation data comprising index values corresponding to a plurality of manual evaluation indexes, and the machine analysis result comprising sub-analysis results corresponding to a plurality of machine evaluation dimensions; and generating a machine analysis auxiliary text based on the machine analysis result, and generating a classroom evaluation report of the teaching data by using the manual evaluation data, the machine analysis result and the machine analysis auxiliary text. According to the method, the objective classroom evaluation report with rich content can be generated.

Description

Technical Field

[0001] This application relates to the technical field of intelligent classrooms, and in particular to a classroom evaluation method, device, equipment, and storage medium. Background Art

[0002] In the field of education and teaching, classroom evaluation is the core link for teaching quality monitoring and improvement, and its scientificity and comprehensiveness directly affect the improvement of teaching effects. Currently, traditional classroom evaluation methods mainly rely on manual observation and subjective judgment, and the generated evaluation reports often have problems such as single data dimension and insufficient objectivity. Such reports based on limited manual evaluation data are difficult to comprehensively reflect the true quality of classroom teaching. Therefore, how to generate a rich and objective evaluation report is of great practical significance for achieving accurate teaching diagnosis and promoting continuous improvement of teaching quality. Summary of the Invention

[0003] The main technical problem to be solved by this application is to provide a classroom evaluation method, device, equipment, and storage medium that can generate a rich and objective classroom evaluation report.

[0004] To solve the above technical problem, a technical solution adopted by this application is: to provide a classroom evaluation method, the method includes: obtaining artificial evaluation data corresponding to the teaching materials of this lecture, where the artificial evaluation data includes index values corresponding to a number of artificial evaluation indicators; and obtaining the machine analysis result of the teaching materials of this lecture, where the machine analysis result includes sub-analysis results corresponding to a number of machine evaluation dimensions; generating a machine analysis auxiliary text based on the machine analysis result, and the machine analysis auxiliary text includes at least one of the following: explanatory text for explaining the machine evaluation dimension, and evaluation text generated based on the sub-analysis result; using the artificial evaluation data, machine analysis result, and machine analysis auxiliary text of the teaching materials of this lecture to generate a classroom evaluation report for the teaching materials of this lecture.

[0005] To solve the above technical problems, another technical solution adopted by this application is: to provide a classroom evaluation device, including: a first data acquisition module, a second data acquisition module, a text generation module, and a report generation module; the first data acquisition module is used to acquire the manual evaluation data corresponding to the teaching materials of this class, where the manual evaluation data includes the index values corresponding to several manual evaluation indicators; the second data acquisition module is used to acquire the machine analysis results of the teaching materials of this class, where the machine analysis results include sub-analysis results corresponding to several machine evaluation dimensions; the text generation module is used to generate machine analysis auxiliary text based on the machine analysis results, and the machine analysis auxiliary text includes at least one of the following: explanatory text for explaining the machine evaluation dimensions, and evaluation text generated based on the sub-analysis results; the report generation module is used to generate a classroom evaluation report for the teaching materials of this class by using the manual evaluation data, machine analysis results, and machine analysis auxiliary text of the teaching materials of this class.

[0006] To solve the above technical problems, yet another technical solution adopted by this application is: to provide an electronic device, including a memory and a processor that are coupled to each other, and the memory stores program instructions; the processor is used to execute the program instructions stored in the memory to implement the above method.

[0007] To solve the above technical problems, another technical solution adopted by this application is: to provide a computer-readable storage medium for storing program instructions that can be executed to implement the above method.

[0008] The above solution uses the manual evaluation data, machine analysis results, and machine analysis auxiliary text of the teaching materials of this class to generate a report. Compared with the classroom evaluation report that only contains manual evaluation data generated based on manual evaluation data alone, the report generated by this application is richer and more objective in content, and thus is conducive to achieving accurate teaching diagnosis. Further, the machine analysis auxiliary text includes explanatory text for explaining the machine evaluation dimensions and / or corresponding evaluation text, and this auxiliary text is conducive to understanding the content of the report. Description of the Drawings

[0009] Figure 1 is a schematic flowchart of an embodiment of the classroom evaluation method provided by this application; Figure 2 is a schematic diagram of an embodiment of the overall information of the teacher's teaching case provided by this application; Figure 3 is a schematic diagram of an embodiment of the comments of the judges provided by this application; Figure 4 is a schematic diagram of an embodiment of the detailed list of scores of the teaching case provided by this application; Figure 5 is a schematic diagram of the evaluation of an embodiment of the manual evaluation dimension provided by this application; Figure 6a It is an evaluation schematic diagram of an embodiment regarding the project effectiveness and harvest provided by this application; Figure 6b It is an evaluation schematic diagram of an embodiment regarding the quantity of digital teaching resources used provided by this application; Figure 6c It is an evaluation schematic diagram of an embodiment for analyzing the usage types of general teaching tools provided by this application; Figure 6d It is an evaluation schematic diagram of an embodiment for analyzing the number of in-class exercises and the quantity of submitted questions provided by this application; Figure 7 It is an evaluation text regarding online interaction analysis provided by this application; Figure 8 It is an evaluation text regarding the teacher's speaking speed provided by this application; Figure 9 It is a schematic diagram of an embodiment of the word cloud provided by this application; Figure 10 It is a framework schematic diagram of an embodiment of the in-class evaluation device provided by this application; Figure 11 It is a framework schematic diagram of an embodiment of the electronic device provided by this application; Figure 12 It is a framework schematic diagram of the computer-readable storage medium provided by this application. Detailed implementation manners

[0010] To make the purpose, technical solutions and effects of this application clearer and more definite, the following further elaborates on this application with reference to the accompanying drawings and by way of examples.

[0011] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of this application, such descriptions of "first", "second", etc. are only for descriptive purposes and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second" may explicitly or implicitly include at least one such feature. Additionally, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0012] Please refer to Figure 1 , Figure 1 It is a flowchart of an embodiment of the in-class evaluation method provided by this application. It should be noted that if there are substantially the same results, this embodiment is not limited to Figure 1 the process sequence shown. As Figure 1 shown, this embodiment includes: S11: Obtain the manual evaluation data corresponding to the teaching materials for this class. Among them, the manual evaluation data includes the index values corresponding to several manual evaluation indexes.

[0013] The classroom evaluation method provided by this application is used to generate a classroom evaluation report with rich content and objective evaluation content based on the obtained manual evaluation data and machine analysis results of the teaching materials for this class.

[0014] Among them, the generated classroom evaluation report includes manual evaluation data, machine analysis results, and machine analysis auxiliary text generated based on the machine analysis results. The generated machine analysis auxiliary text can help the viewers of the report understand the meaning of the indexes or dimensions, and / or intuitively view the corresponding evaluation content.

[0015] In an implementation scenario, in order to more intuitively express the relevant performance of the teacher in teaching, multiple charts can be used to represent the manual evaluation data and machine analysis results. The finally generated classroom evaluation report includes multiple charts used to represent the manual evaluation data and machine analysis results, and machine analysis auxiliary text generated based on the machine analysis results.

[0016] The manual evaluation data is obtained by several judges' manual evaluation of the teaching materials for this class, and the machine analysis results are obtained by using relevant models or algorithms to conduct machine analysis based on the teaching materials for this class.

[0017] Among them, the judges can manually evaluate the teaching materials for this class through online and / or offline methods (the evaluation content includes scoring and / or written comments). After obtaining the manual evaluation data, the manual evaluation data of all judges can be automatically summarized and statistically analyzed, and the corresponding summary and statistical information can be presented in the form of charts.

[0018] The teaching materials for this class are the lesson example materials of the teacher uploaded by relevant personnel. Among them, the relevant personnel can be the teacher himself / herself, or an administrator responsible for tasks such as creating and managing lesson evaluation tasks and exporting evaluation reports. The teaching materials for this class include the recorded teaching video of the teacher for this class. Of course, it can further include other teaching-related materials, such as lesson plans, etc.

[0019] The classroom evaluation method provided in this application can be used in any scenario where classroom (teaching) evaluation is required, such as in daily teaching and research evaluation scenarios in schools, and can also be used in large-scale competition scenarios. Among them, in order to distinguish the evaluation objects in the competition scenario, a classroom evaluation report for the teaching materials of each individual participating teacher can be generated. Correspondingly, in the competition scenario, the teaching materials of this competition can be the teaching materials of each individual participating teacher in this competition, that is, the teaching materials of this competition correspond to the teaching materials of each participating teacher one by one, and one teaching material of this competition corresponds to the teaching materials of one participating teacher; of course, the teaching materials of this competition can also include the teaching materials of each participating teacher, that is, one teaching material includes multiple teaching materials.

[0020] In one embodiment, for a class competition scenario, a class evaluation report generated for a single participating teacher includes overview information of the teaching materials (which can be understood as class examples) of the participating teacher.

[0021] For example, see Figure 2 , Figure 2 It is a schematic diagram of an embodiment of the teacher lesson summary information provided by the present application. The teacher lesson summary information includes at least one or more of the following information: the name of the participating teacher (to ensure fairness, the competition serial number of the participating class can be used as the teacher's name), the grade (such as elementary school, junior high school, high school, university, etc.), the subject (such as Chinese, mathematics, etc.), the school to which they belong, the total score of the lesson and the ranking of the lesson (ranking among all participating teachers).

[0022] In this embodiment, the manual evaluation data includes indicator values ​​corresponding to a number of manual evaluation indicators.

[0023] In one scenario, the plurality of manual evaluation indicators include qualitative evaluation indicators and / or quantitative scoring indicators for the teaching materials.

[0024] Among them, qualitative evaluation indicators mainly focus on the in-depth understanding of the teaching process. Qualitative evaluation is an evaluation method based on natural observation or systematic description. It deeply analyzes teaching phenomena through comments (in text or non-numerical language), emphasizing the capture of the integrity, internal logic and meaning construction of the teaching process, rather than simple quantification.

[0025] For example, qualitative evaluation indicators include whether the teaching process is clear and organized, whether the key points are highlighted, the quality of classroom interaction (such as harmony between teachers and students and active student thinking), the degree of cultivation of students' non-intellectual factors (such as paying attention to the cultivation of students' interests, habits, and self-confidence), etc.

[0026] In one specific embodiment, see Figure 3 The schematic diagram of the judges' comments is shown in Figure 3As shown, the index value corresponding to the qualitative evaluation index is the evaluation text, which presents the comments (evaluation text) of several judges on the teaching materials for this lecture regarding the qualitative evaluation index.

[0027] In an implementation scenario, during the process of integrating the comments of several judges on the teaching materials for this lecture regarding the qualitative evaluation index, the comments of each judge can be classified according to the qualitative evaluation index, and the comments on the same or similar indexes can be grouped together. For each qualitative evaluation index, the comments of different judges are integrated to form a comprehensive description of this qualitative evaluation index, which helps to quickly identify the advantages and disadvantages of the teaching materials and provide a direction for subsequent improvement.

[0028] Exemplarily, first obtain the comments of each judge, and use relevant models (such as speech recognition models and semantic models, etc.) to understand the comments of each judge to obtain the core viewpoints of each judge. Then, extract the evaluation indexes and corresponding viewpoints that the judges commonly focus on from the comments of each judge. Based on the common evaluation indexes and corresponding comment contents, form the evaluation text of the teaching materials for this lecture. For example, merge the comment contents with the same core viewpoints corresponding to the common evaluation indexes into one comment text, and display the comment contents with different core viewpoints in sequence.

[0029] In another implementation scenario, during the process of integrating the comments of several judges on the teaching materials for this lecture regarding the qualitative evaluation index, the comments of all judges can also be summarized to ensure that no important information is missed. For example, display the comments of all judges regardless of whether the comment contents are the same.

[0030] In an embodiment, several artificial evaluation indexes include several quantitative scoring indexes, and the several quantitative scoring indexes can be divided into at least one artificial evaluation dimension. That is, the index dimensions of the several quantitative scoring indexes may be the same or different.

[0031] In an implementation scenario, the artificial evaluation dimension includes the teaching design dimension, the teaching implementation process dimension, and the teaching effect dimension. That is, in this implementation scenario, several judges mainly conduct artificial quantitative evaluations on these three evaluation dimensions: the teaching design dimension, the teaching implementation process dimension, and the teaching effect dimension. Among them, the index value corresponding to the quantitative scoring index is the scoring value. Generally speaking, the index value corresponding to the quantitative scoring index is the score given by the judge for the relevant index.

[0032] The quantitative scoring indicators under the teaching design dimension include at least one of the following: student situation analysis, topic selection and objectives, teaching evaluation design, teaching preparation and teaching strategies. Teaching strategies include at least one of teaching activities, teaching resources and scaffolding. The quantitative scoring indicators under the teaching implementation process dimension include at least one of the following: formulating teaching plans, guiding teaching practice, teaching reflection, teaching monitoring and management, and teaching works. Teaching works include at least one of teaching work display, work exchange and evaluation. The teaching effectiveness dimension includes goal achievement and innovative application.

[0033] The manual evaluation data corresponding to the teaching materials include manual evaluation data of several judges on the teaching materials, for example, manual evaluation data corresponding to judges A, B and C. In one embodiment, the obtained manual evaluation data of each judge can be presented in the evaluation report, or after the manual evaluation data of each judge is obtained, the manual evaluation data of each judge can be automatically counted and summarized to form corresponding statistical data, and finally only the statistical data is presented.

[0034] In one embodiment, in order to obtain more scientific manual evaluation data, the manual evaluation data of several judges on the teaching materials can be obtained first, and then the evaluation data of several judges can be determined based on the manual evaluation data of each judge; wherein, if the evaluation data of several judges meet the evaluation requirements, the manual evaluation data of the teaching materials of each judge obtained this time will be used as the manual evaluation data corresponding to the teaching materials; but if the evaluation data of several judges does not meet the evaluation requirements, prompt information is sent to the several judges, so that the several judges re-evaluate the teaching materials based on the prompt information, and then re-obtain the manual evaluation data corresponding to the teaching materials.

[0035] Among them, the evaluation data of the judges include at least one of the scorer reliability and the scoring scale. The scorer reliability is used to characterize the consistency of multiple judges in evaluating teaching videos. It should be noted that the higher the scorer reliability, the more consistent the scoring trend of the judges, and the more objectively it can reflect the true situation of the quality of the lesson examples (teaching videos). The specific method of determining the scorer reliability can refer to the existing method of determining consistency, which is not introduced in detail here. The scoring scale reflects the looseness and tightness of the judges' evaluation. Among them, the "sum of squares of deviations from the mean" can be used to represent the looseness and tightness of the judges' evaluation. For all participating teaching materials (lessons), they are loose or tight in one direction. Among them, if the sum of deviations from the mean is positive, it means that the judges' scoring scale is relatively loose, and if the sum of deviations from the mean is negative, it means that the judges' scoring scale is relatively strict.

[0036] In one embodiment, the evaluation requirements include at least one of the following: the rater reliability is not less than a preset reliability value, and the scoring scales among different judges are consistent. That is, the evaluation requirements for several judges include that the rater reliability is not less than a preset reliability value (such as 0.85, etc.), and / or the scoring scales among different judges should be consistent.

[0037] In a specific embodiment, when the evaluation data of several judges do not meet the evaluation requirements, a prompt message is sent to the several judges, such as a re-determined evaluation criterion (evaluation index, definition of the index, or weight corresponding to the index, etc.), or specific evaluation data, so that the several judges re-evaluate the teaching materials of this time based on the prompt message, and then re-obtain the manual evaluation data corresponding to the teaching materials of this time. Among them, the prompt message can be sent to the judges who do not meet the evaluation requirements among the several judges, for example, only sent to the judges whose scoring scales are different from those of other judges, or the prompt message can be sent to all the judges participating in this evaluation.

[0038] In an implementation scenario, the evaluation data of several judges can be presented to a specific user, or presented in the classroom evaluation report corresponding to the teaching materials of this time. The specific user can be a participating teacher, so that the participating teacher can understand the comprehensive evaluation of the teaching quality by the judges, or a teaching manager, or the judge himself / herself, so that the judge can review his / her own manual evaluation data, reflect on the evaluation process, check the consistency and accuracy of the evaluation, etc. Of course, it can also be other specific users set according to the actual application scenario or needs.

[0039] S12: Obtain the machine analysis result of the teaching materials of this time; wherein, the machine analysis result includes sub-analysis results corresponding to several machine evaluation dimensions.

[0040] It should be noted that there is no strict execution order between step S11 and step S12 of this application, that is, there is no strict sequence between the acquisition times of the manual evaluation data and the machine analysis result.

[0041] In one implementation manner, at least one of the machine evaluation dimensions and the relevant items of the manual evaluation index is configured through a configuration interface. The relevant items of the manual evaluation index include the manual evaluation index and the value range corresponding to the manual evaluation index. That is, at least one of the machine evaluation dimensions and the relevant items of the manual evaluation index is configurable, so as to meet the evaluation requirements of different types of classroom teaching modes through flexible configuration of relevant indexes and evaluation dimensions. Specifically, it can be adaptively configured according to the evaluation objective (requirement).

[0042] In one embodiment, the items related to the manual evaluation index at least include the manual evaluation index and the corresponding index value range. For example, the value range of index A is 0 - 10, and the corresponding score values of each judge during quantitative scoring should be between 0 and 10.

[0043] Furthermore, the items related to the manual evaluation index can also include the index definition, so as to be able to adjust the index definition according to the adjustment of the understanding of the index during the application process.

[0044] In addition, the items related to the manual evaluation index can also include the index weight, so as to be able to adjust the weights of each index in combination with the actual situation during the actual application process.

[0045] In a specific embodiment, several manual evaluation indexes include several quantitative scoring indexes, and the items related to the manual evaluation index include the weights corresponding to each quantitative scoring index. When summarizing the manual evaluation data of multiple indexes, weighted processing can be performed based on the evaluation values of each index and the weights corresponding to each index to obtain the summary data.

[0046] In one embodiment, several machine evaluation dimensions include at least one of the following: the usage situation of digital teaching resources, the usage situation of digital teaching tools, online interaction situation, teacher's speaking speed, word cloud, and the proportion of teacher-student behavior duration. That is, at least one of the usage situation of digital teaching resources, online interaction situation, teacher's speaking speed, word cloud, and the proportion of teacher-student behavior duration can be used as the machine evaluation object, and machine analysis is performed based on the teaching materials of this lecture to obtain the corresponding machine analysis results.

[0047] In other embodiments, the machine evaluation dimensions can also include evaluation dimensions such as the number of online praises during the teaching period, the number of in-class exercises, the number of in-class exercise questions, the participation rate of in-class exercises, the scoring rate of in-class exercises, the number of words in the lecture, and the teaching duration.

[0048] Among them, the above-mentioned usage situation mainly refers to the usage times and / or usage formats.

[0049] Exemplarily, the usage situation of digital teaching resources mainly refers to the usage times of digital teaching resources during the teaching period and the usage formats of teaching resources.

[0050] The usage times are, for example, the number of times the teacher uses the smart classroom to open resources. Digital resources are, for example, cloud resources, school-based resources, provincial platforms, and subject network resources in the pc and android resource centers. The buried point technology can be used to count the number of times resources are opened. Among them, each trigger of the buried point for opening digital resources is counted once, and resources with the same resource id are only counted once.

[0051] In one embodiment, to avoid accidental triggering of resource opening operations, it can be considered that a digital resource has been used once when the data point for triggering the opening of the digital resource is triggered and the preset time is reached.

[0052] The usage formats are, for example, courseware, online courses, teaching videos, etc.

[0053] In a specific embodiment, the usage of digital teaching tools includes: the usage of general tools and subject-specific tools by teachers respectively. The usage of teaching tools mainly refers to the number of times of using teaching tools. Of course, it can also include specific teaching tools.

[0054] Among them, general tools are tools applicable to the needs of all subjects, and subject-specific tools are tools serving specific subjects. The usage of general tools refers to the number of times of using general tools. General tools may include at least one of the following: paintbrush, screen sharing, focusing function, photo explanation function, AI recording function, timer, writing board, and screenshot.

[0055] In an implementation scenario, general tools are opened in the toolbar of the smart classroom and the toolbar of the electronic whiteboard. General tools include: photo explanation, AI recording, focusing, timer, screenshot sharing, screen sharing, paintbrush, screen locking, physical display stand, etc. in the bottom toolbar. Among them, when counting the number of times of using general tools during the teaching period, as long as the data point is triggered by clicking the tool entry, the usage count is triggered and automatically accumulated according to the click frequency.

[0056] The usage of subject-specific tools mainly refers to the number of times of using subject-specific tools. In an implementation scenario, the number of times of using feature tools refers to the number of times of using subject tools on the whiteboard and subject applications in the application center. Among them, as long as the data point is triggered by clicking the entry, the usage count is triggered and automatically accumulated according to the click frequency.

[0057] For example, using subject applications - opening junior high school history maps, using subject applications - opening Changyan Chemistry, or opening Fa Zhitong, etc.

[0058] In one embodiment, the online interaction situation includes: teacher-student interaction situation and student-student interaction situation. Among them, the interaction situation includes the number of interactions and the type of interaction.

[0059] The number of teacher-student interactions is the number of times of initiating different interaction types such as quiz, random selection, hierarchical selection, voting, fill-in-the-blank, classification activity, connection activity, flip card, gallery activity, word dictation, character dictation, etc. within the statistically counted teaching period. Among them, each initiation is counted once.

[0060] The number of student-student interactions is the number of times of using different interaction types such as discussion, student presentation, PK board, etc. within the statistically counted teaching period. Among them, each initiation is counted once.

[0061] In one embodiment, the ratio of the number of words the teacher speaks within a preset duration to the speaking duration can be used as the teacher's speaking speed. Among them, the number of words spoken can be determined based on the transcribed text of the teaching materials for this lecture. A relevant speech recognition model can be used to perform speech recognition on the teacher's lecture speech in the teaching materials for this lecture to obtain the transcribed text of the lecture speech. The transcribed text corresponds to the teacher's lecture content. The number of words spoken is obtained by counting the number of characters (punctuation marks can be excluded) in the transcribed text within the preset duration, and the speaking duration can be the duration corresponding to the teacher's lecture speech within the preset duration.

[0062] Exemplarily, the preset duration is 5 minutes, the number of words spoken is the total number of characters in the transcribed text within a certain 5 minutes, and the speaking duration is the duration corresponding to the lecture speech, for example, 3 minutes.

[0063] In one embodiment, the word cloud is determined based on each keyword extracted from the transcribed text of the teaching materials for this lecture. Exemplarily, each noun is extracted from the transcribed text, and the word cloud is determined according to the usage frequency of each noun, etc.

[0064] The proportion of the teacher-student behavior duration includes the proportion of the teacher's behavior duration (the ratio between the teacher's behavior duration and the total teacher-student behavior duration) and the proportion of the student's behavior duration (the ratio between the student's behavior duration and the total teacher-student behavior duration).

[0065] S13: Generate machine analysis auxiliary text based on the machine analysis results. The machine analysis auxiliary text includes at least one of the following: explanatory text for explaining the machine evaluation dimension, and evaluative text generated based on the sub-analysis results.

[0066] The machine analysis results include sub-analysis results corresponding to several machine evaluation dimensions.

[0067] The machine analysis auxiliary text generated based on the machine analysis results includes: evaluative text generated based on the sub-analysis results.

[0068] In one implementation manner, evaluation templates related to each machine evaluation dimension can be pre-stored. The evaluation template contains several fields to be filled in. Then, based on the sub-analysis results of each machine evaluation dimension, the corresponding fields to be filled in are filled in to obtain the corresponding evaluative text.

[0069] Specifically, generating machine analysis auxiliary text based on the machine analysis results includes: obtaining an evaluation template associated with each machine evaluation dimension, where the evaluation template contains several fields to be filled in; based on the sub-analysis results corresponding to each machine evaluation dimension, filling in the corresponding fields to be filled in to obtain evaluative text.

[0070] Exemplarily, the evaluation template for one machine evaluation dimension is as follows: This evaluation dimension reflects Field 1 in the past Field 2 within Field 3 the teachers have conducted Field 4 times of online comments Field 5 The average value of this area (the average is Field 6 times), and a total of Field 7 types of comment types have been used, indicating Field 8 , it is recommended Field 9 .

[0071] Among them, the above fields 1, 2,..., 9 are all fields to be filled in the evaluation template.

[0072] Furthermore, the evaluation template also includes explanatory information for each field to be filled in. Exemplarily, please refer to Table 1 below:

[0073] It should be noted that the above-mentioned corresponding fields to be filled in are filled based on the sub-analysis results corresponding to each machine evaluation dimension to obtain the evaluation text. For example, based on the sub-analysis results and the explanatory information of each field to be filled in, the sub-analysis results are filled into the fields to be filled in the corresponding evaluation template to obtain the evaluation text of this machine evaluation dimension.

[0074] Furthermore, the explanatory text for explaining the machine evaluation dimension can be the explanatory text pre-configured for each machine evaluation dimension, and presenting this explanatory text is beneficial for the report viewer to understand each evaluation dimension.

[0075] S14: Generate the classroom evaluation report for this teaching material by using the manual evaluation data, machine analysis results, and machine analysis auxiliary text of this teaching material.

[0076] In an implementation scenario, the classroom evaluation report includes multiple charts and machine analysis auxiliary text, and the multiple charts are used to represent the manual evaluation data and machine analysis results.

[0077] That is, in this implementation scenario, the presentation content of the classroom evaluation report for this teaching material includes: multiple charts for representing the manual evaluation data and machine analysis results, and machine analysis auxiliary text generated based on the machine analysis results. Among them, the charts are generated by using the manual evaluation data and machine analysis results.

[0078] That is, in the generated classroom evaluation report, there are charts that can intuitively display the manual evaluation data and machine analysis results, as well as evaluation text showing the machine analysis results for the convenience of users to understand, and / or, explanatory text for the machine evaluation dimension.

[0079] It is understandable that various visualization charts can intuitively express the situation of teachers in the teaching process, such as digital teaching resources, teaching tools, teaching interaction organization, in-class exercises, teaching language and speaking speed, etc. Further, corresponding evaluation texts can be generated based on the sub-analysis results and relevant reference standards (such as evaluation templates).

[0080] The above solution uses the manual evaluation data, machine analysis results, and machine analysis auxiliary text of this teaching material to generate a report. Compared with the classroom evaluation report that only contains manual evaluation data generated based on manual evaluation data alone, the report generated by this application is richer and more objective in content, which is conducive to realizing accurate teaching diagnosis. Further, the machine analysis auxiliary text includes explanatory text for explaining the machine evaluation dimension and / or corresponding evaluation text, which is helpful for understanding the report content.

[0081] In one embodiment, the classroom evaluation method provided by this application further includes determining the controversial detection result of this teaching material, where the controversial detection result is used to characterize whether this teaching material belongs to controversial teaching material.

[0082] In one implementation manner, several manual evaluation indicators in step S11 include qualitative evaluation indicators and quantitative scoring indicators. The index value corresponding to the qualitative evaluation indicator is the evaluation text, and the index value corresponding to the quantitative scoring indicator is the scoring value. Several machine evaluation dimensions include target machine evaluation dimensions; in this implementation manner, the controversial detection result of this teaching material can be determined based on at least one of the index value corresponding to the quantitative scoring indicator, the index value corresponding to the qualitative evaluation indicator, and the machine analysis result of this teaching material, specifically including the following steps: Step 1: Obtain the target detection data of this teaching material. The target detection data includes at least one of the following: the difference in scoring values of the same quantitative scoring indicator among different reviewers, the keyword conflict detection result in the evaluation texts of the same qualitative evaluation indicator among different reviewers, and the matching degree between the scoring value of the quantitative scoring indicator and the sub-analysis result of the target machine evaluation dimension.

[0083] Among them, the scoring value difference may refer to the variance or standard deviation between scoring values. The keyword conflict detection result indicates whether there is a keyword conflict in the evaluation texts of the same qualitative evaluation indicator among different reviewers.

[0084] The target machine evaluation dimension may include at least one of the following: the frequency of teacher-student interaction, student participation, and the time allocation of teaching links. Among them, the sub-analysis results of the above target machine evaluation dimensions in the teaching video can be analyzed by using computer vision and / or natural speech processing technology.

[0085] Exemplarily, the number of times a teacher asks questions and students answer can be counted through speech recognition and speaker separation technologies to obtain interactive frequency data; student engagement can be determined through facial expression recognition and body movement analysis (such as student concentration, confusion, raising hand frequency, etc.); further, the teaching video's written text can be automatically segmented, and teaching introduction segments, explanation segments, discussion segments, etc. can be determined based on the semantics of each text segment, and the duration ratio of each segment can be determined based on the time stamps of the speech corresponding to the text.

[0086] The matching degree between the scoring value of the quantitative scoring index and the sub-analysis result of the target machine evaluation dimension, for example, the quantitative score of the judge regarding student engagement is 90 points, but in the student engagement analyzed by the machine, the proportion of students' confused expressions is 30%, and the corresponding score is, for example, 30 points, indicating that the matching degree between the two is relatively low.

[0087] Step 2: Determine whether the target detection data meets the dispute conditions.

[0088] The dispute conditions include at least one of the following: the scoring value difference is greater than the preset threshold, there are conflicting keywords in the evaluation texts of the same qualitative evaluation index among different judges, and the matching degree is less than the degree threshold. In this embodiment, the specific preset threshold and degree threshold can be set according to experience and are not specifically limited here.

[0089] Step 3: In response to the target detection data meeting the dispute conditions, determine that this teaching material belongs to controversial teaching material.

[0090] In one embodiment, the controversial detection result of this teaching material can be presented to a specific user or presented in the corresponding classroom evaluation report.

[0091] Of course, in other embodiments, after obtaining the manual evaluation data and machine analysis results corresponding to this teaching material, the evaluation data and analysis results can be retained to compare with the previously saved evaluation data and analysis results (historical data) after obtaining the evaluation data and analysis results of new teaching materials subsequently.

[0092] In addition, before conducting classroom evaluation, an evaluation task list can be created to add each teaching material to be evaluated to the task list, and after obtaining the corresponding evaluation report, save the corresponding evaluation report, manual evaluation data, and machine analysis results, so that the information of each teaching material can be viewed through this evaluation task list.

[0093] To facilitate understanding of the classroom evaluation report of this application, taking the scenario of a teaching competition as an example, the presentation content in the finally generated classroom evaluation report can include at least some of the following: I. Overview information of the evaluation object (a certain teacher).

[0094] See also Figure 2 , Figure 2 Schematic diagram of an embodiment of the teacher's lesson overview information provided by this application. Figure 2 As shown, the teacher's lesson overview information includes the participating teacher's name (Quality Lesson 04), grade level (junior high school), subject (Chinese), school to which he belongs, the total score of the lesson (68.89) and the ranking of the lesson (4th out of 6).

[0095] 2. Manual evaluation data.

[0096] In one implementation scenario, the quantitative scoring values ​​of the judges for the quantitative scoring indicators can be presented in the form of a graph and / or table in the classroom evaluation report. Figure 4 The lesson score breakdown table shown can present the dimensions of manual evaluation, the quantitative scoring indicators included in each dimension, the score values ​​of the judges for each quantitative scoring indicator, the score rate of each quantitative scoring indicator, and the overall ranking of teachers in each dimension.

[0097] Among them, the scoring values ​​of multiple judges can be combined to determine the scoring values ​​of each quantitative scoring indicator, such as Figure 4 As shown in the figure, the score of each quantitative scoring indicator given by the judges (corresponding to the several judges mentioned above) is determined by combining the score of multiple judges, such as the average of the score of multiple judges, or the average of the remaining score after removing the highest score and the lowest score; the teacher's overall ranking in each manual evaluation dimension is the teacher's ranking among all teachers in the competition.

[0098] The score details of the above teaching materials presented in the report can meet the needs of viewers to quickly understand the detailed scores of the evaluation objects. Users can query the scores of each indicator of the teacher through the detailed table, as well as query the individual rankings under each dimension.

[0099] Furthermore, relevant types of diagrams can be used to further display the teacher's individual scores under each indicator and the average level among multiple participating teachers, as well as the gap with the highest level of this time, and can be further supplemented with text for explanatory explanation. The details are as follows: See also Figure 5 The evaluation chart of the manual evaluation dimension (project design and preparation dimension) shown in the figure can present the manual evaluation dimension and multiple quantitative scoring indicators and corresponding value ranges under the evaluation dimension through a chart (which can be but not limited to a radar chart, or a bar chart, etc.), for example Figure 5 The highest score for the academic situation analysis shown is 6 points, the highest score for topic selection and goals is 12 points, etc.; the scoring rate of each quantitative scoring indicator, the average scoring rate and the highest scoring rate of multiple participating teachers can also be displayed through graphs.

[0100] In one embodiment, evaluative text regarding manual evaluation data may be further presented in the evaluation report to provide explanatory descriptions through the text. Exemplarily, the evaluative text of the manual evaluation data is, for example, "The teacher's scoring rate in teaching design and preparation is 70.49%, which is generally average. Among them, the analysis of students' learning situation (4.46 points), topic selection and objectives (8.92 points), teaching activities, resources and scaffolds (7.14 points), teaching evaluation design (6.17 points), and teaching preparation (5.03 points) have relatively low scores and need improvement."

[0101] Among them, the method of generating the evaluative text regarding the manual evaluation data may refer to the method of generating the evaluative text of the machine evaluation dimension above. In addition, the presentation of the evaluation data of other manual evaluation dimensions may refer to Figure 5 the project design and preparation dimension shown, and no further elaboration and picture presentation will be made here. Among them, Figure 4 and Figure 5 the project shown refers to teaching.

[0102] In some embodiments, the evaluation text of the qualitative evaluation indicators by the judges may also be presented in the report. Please refer to Figure 3 the schematic diagram of the judges' comments shown. The evaluation text presents the comments (evaluation text) of several judges on the teaching materials of this lecture regarding the qualitative evaluation indicators.

[0103] III. Machine analysis results.

[0104] In one implementation scenario, the classroom evaluation report may also present the sub-analysis results corresponding to each machine evaluation dimension using various types of diagrams, such as radar charts, bar charts, pie charts, trend charts, etc. Exemplarily, please refer to Figure 6a 、 6b 、6c and 6d.

[0105] IV. Machine analysis auxiliary text.

[0106] Among them, the machine analysis auxiliary text includes explanatory text for explaining the machine evaluation dimension and / or evaluative text generated based on the sub-analysis results of the machine evaluation dimension.

[0107] Exemplarily, please refer to Figure 7 . For the machine evaluation dimension of online interaction analysis, based on the sub-analysis results of online interaction analysis, the generated evaluative text is, for example: This class initiated 2 (Field 1) online interactions, which is 42.86% (Field 2) less than the overall average number. The types of online interactions used include "Random Selection (Field 3)". In addition, 5 (Field 4) person-times were commented on online. Among them, the number "2" in Field 1, the number "42.86%" in Field 2, "Random Selection" in Field 3, and the number "5" in Field 4 are all sub-analysis results of the online interactions.

[0108] In some implementation scenarios, the evaluation text in the machine evaluation dimension not only includes sub-analysis results but also relevant suggestions generated based on the sub-analysis results.

[0109] Exemplarily, please refer to Figure 8 , for the machine evaluation dimension of the teacher's speaking speed, based on the sub-analysis results of the online interaction analysis, the generated evaluation text is, for example: "In this class, the highest speaking speed of the teacher was 182 words per minute, and the average speaking speed was 94 words per minute. The overall speaking speed was slightly slow. It is recommended that the teacher adjust the speaking speed according to the content and students' feedback to find a suitable teaching rhythm."

[0110] Another example, for the machine evaluation dimension of the word cloud, based on the sub-analysis results of the word cloud, the generated evaluation text is, for example: "According to the word cloud, among the high-frequency words, 'rule', 'color', and 'potted flower' are closely related to the classroom content, reflecting the teaching key points and practical operations. Personal pronouns such as'student' and 'teacher' appear frequently, showing the characteristics of interactive teaching. Subject nouns such as 'arithmetic formula' and 'data' also appear relatively more, highlighting the application of mathematical logic. Generally speaking, these high-frequency words effectively reflect the main content and teaching methods of the course."

[0111] Among them, the presentation form of the word cloud can be referred to Figure 9 .

[0112] Another example, for the machine evaluation dimension of the proportion of teacher-student behaviors, based on the sub-analysis results of the online interaction analysis, the generated evaluation text is, for example: "In this class, the teacher's behavior duration (accounting for 61%) is greater than the student's behavior duration (accounting for 39%), indicating that this class is a teacher-led class, and the overall performance of this class is a dialogue-based class.

[0113] The classroom data shows that you mainly adopted the method of multimedia presentation in this course, accounting for as high as 90.48%, while the proportions of traditional classroom lectures and blackboard writing are relatively low. Although multimedia can enrich the teaching content and improve students' learning interest, over-reliance may reduce students' thinking space and interaction opportunities.

[0114] It is recommended that you appropriately increase the proportion of classroom lectures and blackboard writing. Especially when explaining complex concepts or formulas, blackboard writing can more intuitively help students understand and remember.

[0115] Your walking trajectory is mainly concentrated in the podium area. It is recommended that you intersperse walking among the students during the explanation to provide instant problem-solving or group discussions. This can not only shorten the distance with the students but also instantly understand the students' learning status, improving the interactivity of the classroom and the students' sense of participation.

[0116] No more examples will be given for other machine analysis dimensions. However, as can be seen from the above, the evaluation text corresponding to the machine analysis dimension is generated by using the evaluation template associated with the machine analysis dimension and the sub-analysis results of the machine analysis dimension.

[0117] Among them, for different machine analysis dimensions, their corresponding associated evaluation templates are different, and the evaluation templates of the machine analysis dimensions can be specifically set according to actual needs.

[0118] Among them, in order to facilitate the understanding of the meaning of the machine evaluation dimension, explanatory text of the machine evaluation dimension can be set to be presented in the classroom evaluation report. Exemplarily, in order to facilitate the understanding of the meaning of the online interaction analysis, a machine evaluation dimension, explanatory text such as "This indicator reflects the teacher's use of digital technology to support online interaction" can be set to be presented in the classroom evaluation report.

[0119] Please refer to Figure 10 , Figure 10 which is a schematic framework diagram of an embodiment of the classroom evaluation device provided by this application. In this embodiment, the classroom evaluation device 100 includes a first data acquisition module 10, a second data acquisition module 20, a text generation module 30, and a report generation module 40. The first data acquisition module 10 is used to acquire the manual evaluation data corresponding to the teaching materials of this lecture. Among them, the manual evaluation data includes the index values corresponding to several manual evaluation indicators; the second data acquisition module 20 is used to acquire the machine analysis results of the teaching materials of this lecture. Among them, the machine analysis results include the sub-analysis results corresponding to several machine evaluation dimensions; the text generation module 30 is used to generate machine analysis auxiliary text based on the machine analysis results. The machine analysis auxiliary text includes at least one of the following: explanatory text for explaining the machine evaluation dimension, evaluation text generated based on the sub-analysis results; the report generation module 40 is used to generate a classroom evaluation report for the teaching materials of this lecture by using the manual evaluation data, machine analysis results, and machine analysis auxiliary text of the teaching materials of this lecture.

[0120] In some embodiments, the several manual evaluation indicators include qualitative evaluation indicators and quantitative scoring indicators. The indicator value corresponding to the qualitative evaluation indicator is an evaluation text, and the indicator value corresponding to the quantitative scoring indicator is a score value. The classroom evaluation device 100 is further configured to determine the controversy detection result of the teaching materials for this class based on at least one of the indicator value corresponding to the quantitative scoring indicator of the teaching materials for this class, the indicator value corresponding to the qualitative evaluation indicator, and the machine analysis result. Among them, the controversy detection result is used to indicate whether the teaching materials for this class are controversial teaching materials.

[0121] In some embodiments, the manual evaluation data corresponding to the teaching materials for this class obtained by the first data acquisition module 10 includes the manual evaluation data of several judges on the teaching materials for this class respectively. The several machine evaluation dimensions include the target machine evaluation dimension. Determining the controversy detection result of the teaching materials for this class based on at least one of the indicator value corresponding to the quantitative scoring indicator of the teaching materials for this class, the indicator value corresponding to the qualitative evaluation indicator, and the machine analysis result includes: obtaining the target detection data of the teaching materials for this class, where the target detection data includes at least one of the following: the score value difference between different judges for the same quantitative scoring indicator, the keyword conflict detection result in the evaluation texts of different judges for the same qualitative evaluation indicator, and the matching degree between the score value of the quantitative scoring indicator and the sub-analysis result of the target machine evaluation dimension; determining whether the target detection data meets the controversy condition; in response to the target detection data meeting the controversy condition, determining that the teaching materials for this class are controversial teaching materials. Among them, the controversy condition includes at least one of the following: the score value difference is greater than a preset threshold, there are conflicting keywords in the evaluation texts of different judges for the same qualitative evaluation indicator, and the matching degree is less than the degree threshold.

[0122] In some embodiments, at least one of the inter-rater reliability and scoring scale of several judges, and the controversy detection result of the teaching materials for this class is presented to a specific user or presented in the classroom evaluation report; and / or, the target machine evaluation dimension includes at least one of the frequency of teacher-student interaction, student participation, and teaching link time allocation.

[0123] In some embodiments, the manual evaluation data corresponding to the teaching materials acquired by the first data acquisition module 10 includes manual evaluation data of the teaching materials respectively obtained by several judges; and / or, the first data acquisition module 10 acquires the manual evaluation data corresponding to the teaching materials, including: acquiring manual evaluation data of the teaching materials respectively obtained by several judges; determining evaluation data for several judges based on the manual evaluation data of each of the judges; the evaluation data includes at least one of the scorer reliability and scoring scale of the several judges; in response to the evaluation data meeting the evaluation requirements, using the manual evaluation data of the teaching materials obtained by each judge as the manual evaluation data corresponding to the teaching materials; in response to the evaluation data not meeting the evaluation requirements, sending prompt information to the several judges, so that the several judges re-evaluate the teaching materials based on the prompt information, and then re-acquire the manual evaluation data corresponding to the teaching materials; wherein, the evaluation requirements include at least one of the following: the scorer reliability is not less than a preset reliability value, and the scoring scales between different judges are consistent.

[0124] In some embodiments, the several manual evaluation indicators include qualitative evaluation indicators and several quantitative scoring indicators, and the several quantitative scoring indicators are divided into at least one manual evaluation dimension; wherein the manual evaluation dimension includes teaching design dimension, teaching implementation process dimension and teaching effect dimension; the quantitative scoring indicators under the teaching design dimension include at least one of the following: student situation analysis, topic selection and objectives, teaching evaluation design, teaching preparation and teaching strategies, the teaching strategies include at least one of teaching activities, teaching resources and scaffolding, the quantitative scoring indicators under the teaching implementation process dimension include at least one of the following: specifying teaching plans, guiding teaching practices, teaching reflection, teaching monitoring management and teaching works, the teaching works include at least one of teaching work display, work exchange and evaluation, and the teaching effect dimension includes goal achievement and innovative application.

[0125] In some embodiments, the teaching materials include the teaching video; the several machine evaluation dimensions include at least one of the following: usage of digital teaching resources, usage of digital teaching tools, online interaction, teacher's speaking speed, word cloud and proportion of teacher-student behavior time.

[0126] In some embodiments, the machine analysis auxiliary text includes the evaluative text; the text generation module 30 generates the machine analysis auxiliary text based on the machine analysis results, including: obtaining an evaluation template associated with each of the machine evaluation dimensions, the evaluation template containing a number of fields to be filled in; based on the sub-analysis results corresponding to each of the machine evaluation dimensions, filling in the corresponding fields to be filled in to obtain the evaluative text.

[0127] In some embodiments, the usage of the digital teaching tools includes: the usage of general tools and subject-specific tools by teachers; and / or, the online interaction includes: teacher-student interaction and student-student interaction; and / or, the teacher's speaking speed is the ratio of the number of words the teacher speaks in a preset duration to the speaking duration, and the number of words spoken is determined based on the transcribed text of the teaching materials for this lecture; and / or, the word cloud is determined based on each keyword extracted from the transcribed text of the teaching materials for this lecture.

[0128] In some embodiments, the usage includes at least one of the usage frequency and the usage format, and the interaction includes the interaction frequency and the interaction type; the general tools are tools applicable to all subject requirements, and the general tools include at least one of a paintbrush, screen sharing, focus function, photo-explanation function, AI lecture recording function, timer, scratch pad, and screenshot.

[0129] Please refer to Figure 11 , Figure 11 FIG. is a schematic framework diagram of an embodiment of the electronic device provided in the present application. In this embodiment, the electronic device 110 includes a memory 111 and a processor 112 that are coupled to each other.

[0130] The memory 111 stores program instructions, and the processor 112 is configured to execute the program instructions stored in the memory 111 to implement the steps of any of the above method embodiments. In a specific implementation scenario, the electronic device 110 may include, but is not limited to: a microcomputer, a server. In addition, the electronic device 110 may also include mobile devices such as a laptop computer, a tablet computer, etc., which are not limited herein.

[0131] Specifically, the processor 112 is configured to control itself and the memory 111 to implement the steps of any of the above embodiments. The processor 112 may also be referred to as a CPU (Central Processing Unit). The processor 112 may be an integrated circuit chip with signal processing capabilities. The processor 112 may also be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Additionally, the processor 112 may be implemented jointly by integrated circuit chips.

[0132] Please refer toFigure 12 , Figure 12 is a schematic framework diagram of the computer-readable storage medium provided by this application. The computer-readable storage medium 120 of the embodiments of this application stores program instructions 121, and when the program instructions 121 are executed, the methods provided by any one of the above embodiments and any non-conflicting combinations are implemented. Among them, the program instructions 121 can form a program file and be stored in the above computer-readable storage medium 120 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) can execute all or part of the steps of the methods of various embodiments of this application. The aforementioned computer-readable storage medium 120 includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0133] The above solution uses the manual evaluation data, machine analysis results, and machine analysis auxiliary text of this teaching material to generate a report. Compared with the classroom evaluation report that only contains manual evaluation data generated based on only manual evaluation data, the report generated by this application is richer and more objective in content, and thus is beneficial to realizing accurate teaching diagnosis. Further, the machine analysis auxiliary text includes explanatory text for explaining the machine evaluation dimension and / or corresponding evaluation text, and this auxiliary text is beneficial to understanding the report content.

[0134] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0135] The above descriptions of the various embodiments tend to emphasize the differences between the various embodiments. Their similarities or similarities can be referred to each other. For the sake of brevity, they will not be repeated in this article.

[0136] In several embodiments provided by this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0137] The unit described as a separation component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., which can store program codes.

[0140] The above is only the embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be included in the patent protection scope of the present application by the same token.

Claims

1. A classroom evaluation method, characterized in that, The method includes: Obtaining the manual evaluation data corresponding to the teaching materials for this class, where the manual evaluation data includes the index values corresponding to a number of manual evaluation indexes; and, Obtaining the machine analysis result of the teaching materials for this class, where the machine analysis result includes sub-analysis results corresponding to a number of machine evaluation dimensions; Generating a machine analysis auxiliary text based on the machine analysis result, where the machine analysis auxiliary text includes at least one of the following: explanatory text for explaining the machine evaluation dimension, and evaluation text generated based on the sub-analysis result; Using the manual evaluation data, the machine analysis result, and the machine analysis auxiliary text of the teaching materials for this class to generate a classroom evaluation report for the teaching materials for this class.

2. The method according to claim 1, characterized in that, The number of manual evaluation indexes includes qualitative evaluation indexes and quantitative scoring indexes, the index value corresponding to the qualitative evaluation index is evaluation text, and the index value corresponding to the quantitative scoring index is a scoring value; The method further includes: Determining a controversy detection result of the teaching materials for this class based on at least one of the index value corresponding to the quantitative scoring index of the teaching materials for this class, the index value corresponding to the qualitative evaluation index, and the machine analysis result; where the controversy detection result is used to characterize whether the teaching materials for this class are controversial teaching materials.

3. The method according to claim 2, wherein The manual evaluation data corresponding to the teaching materials for this class includes the manual evaluation data of a number of reviewers for the teaching materials for this class respectively, and the number of machine evaluation dimensions includes a target machine evaluation dimension; The determining the controversy detection result of the teaching materials for this class based on at least one of the index value corresponding to the quantitative scoring index of the teaching materials for this class, the index value corresponding to the qualitative evaluation index, and the machine analysis result includes: Obtaining target detection data of the teaching materials for this class, where the target detection data includes at least one of the following: the difference in scoring values between different reviewers for the same quantitative scoring index, the keyword conflict detection result in the evaluation text for the same qualitative evaluation index between different reviewers, and the matching degree between the scoring value of the quantitative scoring index and the sub-analysis result of the target machine evaluation dimension; Determining whether the target detection data meets the controversy condition; In response to the target detection data meeting the controversy condition, determining that the teaching materials for this class are controversial teaching materials; Where the controversy condition includes at least one of the following: the scoring value difference is greater than a preset threshold, there are conflicting keywords in the evaluation text for the same qualitative evaluation index between different reviewers, and the matching degree is less than a degree threshold.

4. The method according to claim 3, characterized in that At least one of the inter-rater reliability and scoring scale of a number of reviewers, and the controversy detection result of the teaching materials for this class is presented to a specific user or presented in the classroom evaluation report; And / or, the target machine evaluation dimension includes at least one of the frequency of teacher-student interaction, student participation, and the time allocation of teaching links.

5. The method according to claim 1, wherein The manual evaluation data corresponding to the teaching materials for this class includes the manual evaluation data of a number of reviewers for the teaching materials for this class respectively; And / or, obtaining the manual evaluation data corresponding to the teaching materials of this lecture includes: Obtaining the manual evaluation data of several judges for the teaching materials of this lecture respectively; Based on the manual evaluation data of each judge, determining the evaluation data of several judges; the evaluation data includes at least one of the rater reliability and scoring scale of several judges; In response to the evaluation data meeting the evaluation requirements, taking the manual evaluation data of each judge for the teaching materials of this lecture as the manual evaluation data corresponding to the teaching materials of this lecture; In response to the evaluation data not meeting the evaluation requirements, sending a prompt message to the several judges so that the several judges re-evaluate the teaching materials of this lecture based on the prompt message, and then re-obtaining the manual evaluation data corresponding to the teaching materials of this lecture; Wherein, the evaluation requirements include at least one of the following: the rater reliability is not less than the preset reliability value, and the scoring scales among different judges are consistent.

6. The method according to claim 1, wherein The several manual evaluation indicators include qualitative evaluation indicators and several quantitative scoring indicators, and the several quantitative scoring indicators are divided into at least one manual evaluation dimension; Wherein, the manual evaluation dimension includes the teaching design dimension, the teaching implementation process dimension and the teaching effect dimension; The quantitative scoring indicators under the teaching design dimension include at least one of the following: learning situation analysis, topic selection and objectives, teaching evaluation design, teaching preparation and teaching strategies, and the teaching strategies include at least one of teaching activities, teaching resources and scaffolds; the quantitative scoring indicators under the teaching implementation process dimension include at least one of the following: formulating teaching plans, guiding teaching practice, teaching reflection, teaching monitoring and management, and teaching works, and the teaching works include at least one of teaching work demonstrations, work exchanges and evaluations; the teaching effect dimension includes goal achievement and innovative application.

7. The method according to claim 1, wherein The teaching materials of this lecture include the teaching video of this lecture; The several machine evaluation dimensions include at least one of the following: the usage of digital teaching resources, the usage of digital teaching tools, the online interaction situation, the teacher's speaking speed, the word cloud, and the proportion of the teacher-student behavior duration; 8. The method according to claim 1 or 7, characterized in that, The machine analysis auxiliary text includes the evaluation text; generating the machine analysis auxiliary text based on the machine analysis result includes: Obtaining an evaluation template associated with each machine evaluation dimension, and the evaluation template contains several fields to be filled in; Filling in the corresponding fields to be filled in based on the sub-analysis results corresponding to each machine evaluation dimension to obtain the evaluation text.

9. The method according to claim 7, wherein The usage of digital teaching tools includes: the usage of general tools and subject-specific tools by the teacher respectively; And / or, the online interaction situation includes: teacher-student interaction situation and student-student interaction situation; And / or, the teacher's speaking speed is the ratio of the number of words the teacher speaks during a preset duration to the speaking duration, and the number of words spoken is determined based on the transcribed text of the teaching materials of this lecture; And / or, the word cloud is determined according to each keyword extracted from the transcribed text of the teaching materials of this lecture.

10. The method according to claim 9, characterized in that, The usage includes at least one of the usage times and usage formats, and the interaction situation includes the interaction times and interaction types. The general tool is a tool applicable to the needs of all disciplines, and the general tool includes at least one of a paintbrush, screen sharing, focusing function, photo-explanation function, AI lesson recording function, timer, scratchpad, and screenshot.

11. A classroom evaluation device, characterized in that, The device includes: A first data acquisition module, configured to acquire artificial evaluation data corresponding to the teaching materials of this class, where the artificial evaluation data includes index values corresponding to a number of artificial evaluation indexes; A second data acquisition module, configured to acquire the machine analysis result of the teaching materials of this class, where the machine analysis result includes sub-analysis results corresponding to a number of machine evaluation dimensions; A text generation module, configured to generate machine analysis auxiliary text based on the machine analysis result, and the machine analysis auxiliary text includes at least one of the following: explanatory text for explaining the machine evaluation dimension, and evaluative text generated based on the sub-analysis result; A report generation module, configured to generate a classroom evaluation report for the teaching materials of this class by using the artificial evaluation data, the machine analysis result, and the machine analysis auxiliary text of the teaching materials of this class.

12. An electronic device, characterized in that, It includes a memory and a processor that are mutually coupled, The memory stores program instructions; The processor is configured to execute the program instructions stored in the memory to implement the method according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program instructions that can be run by a processor, and the program instructions can be executed by the processor to implement the method according to any one of claims 1-10.

Images