Turnover teaching evaluation method and device suitable for remote digital learning service

Abstract

The invention relates to the field of flipping teaching, in particular to a flipping teaching evaluation method and device suitable for remote digital learning service. Comprising the steps of obtaining a teaching course and an inspection rule associated with a current classroom; obtaining a first cue word set and a second cue word set according to the classroom record; a first test exercise set related to the first cue word set and a second test exercise set related to the second cue word set are obtained, the first test exercise set and the second test exercise set are generated through exercise generation rules and are randomly issued to the user terminals, and exercises displayed by each user terminal are stored in the user terminals; the cluster number division is not higher than a first preset value; and determining a first evaluation value and a second evaluation value in the flipping teaching process based on the test result of the exercises displayed by the user terminal, wherein the first evaluation value and the second evaluation value are the difference between the individual learning effect and the overall learning result. Therefore, the problems of lack of objectivity, poor accuracy and untimely feedback in traditional teaching evaluation are solved.

Description

Technical Field

[0001] The present invention relates to the field of flipped teaching, and in particular to a flipped teaching evaluation method and device suitable for remote digital learning services. Background Art

[0002] Flipped teaching is an emerging teaching model that emphasizes the subject status of students, encourages students to actively participate in learning, and deepens their understanding and mastery of knowledge through independent learning, cooperative exploration, etc. Its specific form is that students learn independently by watching teaching videos, animations, audio and other teaching resources before class, and conduct in-depth learning activities such as problem solving and cooperative exploration under the guidance of teachers in class. It can improve the efficiency of classroom time and promote students' in-depth learning and understanding. For this teaching model, traditional manual evaluation methods such as questionnaires and classroom listening are no longer suitable for the new teaching model. In traditional questionnaires, the evaluation of teaching is easily mixed with subjective opinions. In addition, the limited understanding and expression ability of students will also affect the teaching evaluation results. At the same time, the manual feedback time is not very timely, so that teachers cannot make teaching adjustments according to the feedback results at any time.

[0003] In view of the above problems, the present invention proposes a flipped teaching evaluation method and device suitable for remote digital learning services. It can effectively solve the problems of lack of objectivity, poor accuracy and untimely feedback in traditional teaching evaluation. In addition, due to the characteristics of flipped teaching, this method can be applied to remote digital learning services. Summary of the invention

[0004] At least one aspect or advantage of the invention will be set forth in part in the following description, or may be obvious from the description, or may be learned by practice of the disclosed subject matter.

[0005] According to a first aspect of the present invention, a flipped teaching evaluation method applicable to remote digital learning services comprises: Acquire the teaching courses and test rules associated with the current class, wherein the test rules include exercise generation rules associated with the teaching courses, and the exercise generation rules include a number of matching keywords; Acquire a first prompt word set and a second prompt word set according to the classroom recording, wherein the first prompt word set is generated based on the student speech translation text in the classroom recording, and the second prompt word set is generated based on the teacher speech translation text in the classroom recording; Acquire a first test question set associated with a first prompt word set, and a second test question set associated with a second prompt word set, wherein the first test question set and the second test question set are generated by a question rule and randomly distributed to interactive user terminals, and the questions displayed corresponding to each user terminal have a cluster number division not higher than a first preset value; Determine a first evaluation value and a second evaluation value in the flipped teaching process based on the test results of the exercises displayed by the user terminal, wherein the first evaluation value and the second evaluation value are the differences between the individual learning effect and the overall learning result; The first evaluation value is obtained based on the analysis of the test results of the first test exercise, and the second evaluation value is obtained based on the analysis of the test results of the second test exercise set.

[0006] According to one embodiment of the present invention, the process of generating the first test question set includes: Determining a first word set and a second word set according to the frequency of the first prompt word set in the student's voice-translated text, wherein in the student's voice-translated text, the frequency of occurrence of words in the first word set is higher than the frequency of occurrence of words in the second word set; Determine a first exercise generation rule list associated with the first word set, and generate a first test exercise list based on the first exercise generation rule list; Determine a second exercise generation rule list associated with the second word set, and generate a second test exercise list based on the second exercise generation rule list; The first test question list and the second test question list are merged to obtain a first test question set.

[0007] According to an embodiment of the present invention, the first exercise generation rule list does not include the exercise generation rules in the first exercise generation list.

[0008] According to an embodiment of the present invention, the process of acquiring the first prompt word set and the second prompt word set includes: Determine the user speech time interval sets of students and teachers respectively based on the speech records of the user terminals; Determine the teacher's speech translation text and the student's speech translation text based on the user's speech time interval set; Segment the teacher's voice translation text, and obtain a second prompt word set based on the matching of the segmentation result and the exercise generation rule; The student's speech translation text is segmented, and the first prompt word set is obtained based on the matching of the segmentation result and the exercise generation rule.

[0009] According to one embodiment of the present invention, the process of generating the second test question set includes: Determine a third exercise generation rule list associated with the second prompt word set; removing the exercise generation rules in the third exercise generation rule list that are repeated with the exercise generation rules used to generate the first test exercise set; A second test exercise set is generated according to the third exercise generation rule list.

[0010] According to an embodiment of the present invention, the number of clusters is divided into the total number of categories into which the exercises displayed on the user terminal are divided when the first test exercise set and the second test exercise set are clustered according to the exercise generation rule; The clustering according to the exercise generation rule includes: Setting keywords corresponding to the exercises in the first test exercise set and the second test set based on the exercise generation rules for generating the first test exercise set and the second test set; The exercises are clustered based on the keywords corresponding to the exercises in the first test exercise set and the second test exercise set to obtain a clustering result.

[0011] According to an embodiment of the present invention, the first evaluation value is obtained in the following manner: The first test question set is grouped according to keywords corresponding to the questions in the first test question set, and based on the answer results of the first test question set, an overall answer accuracy dictionary corresponding to the questions in the grouping results is obtained; Acquire a sequence of correct answer rates of the user terminal, wherein the sequence of correct answer rates includes the correct answer rates of the user terminal in answering the questions in the first test question set and the overall correct answer rates of the questions in the first test question set for which the user terminal's answer results are incorrect; The variance is determined as the first evaluation value based on the answer accuracy sequence.

[0012] According to an embodiment of the present invention, the second evaluation value is obtained in the following manner: Obtaining the first answer accuracy rate of all user terminals in answering questions in the second test question set; Obtaining the second answer accuracy rate of the user terminal in answering the questions in the second test question set; The ratio of the second answer accuracy rate to the first answer accuracy rate is used as the second evaluation value.

[0013] According to a second aspect of the present invention, a flipped teaching evaluation device applicable to remote digital learning services comprises: A rule unit, used to obtain teaching courses and test rules associated with the current class, wherein the test rules include exercise generation rules associated with the teaching courses, and the exercise generation rules include a number of matching keywords; A prompt word acquisition unit, used to acquire a first prompt word set and a second prompt word set according to the classroom recording, wherein the first prompt word set is generated based on the student speech translation text in the classroom recording, and the second prompt word set is generated based on the teacher speech translation text in the classroom recording; An evaluation content generating unit is used to obtain a first test exercise set related to a first prompt word set and a second test exercise set related to a second prompt word set, wherein the first test exercise set and the second test exercise set are generated by an exercise rule and are randomly distributed to interactive user terminals, and the exercises displayed corresponding to each user terminal have a cluster number division not higher than a first preset value; A teaching evaluation unit, which determines a first evaluation value and a second evaluation value in a flipped teaching process based on a test result of an exercise displayed by a user terminal, wherein the first evaluation value and the second evaluation value are differences between individual learning effects and overall learning results; The first evaluation value is obtained based on the analysis of the test results of the first test exercise, and the second evaluation value is obtained based on the analysis of the test results of the second test exercise set. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flow chart of a flipped teaching evaluation method applicable to remote digital learning services is shown; Figure 2 A virtual structural diagram of a flipped teaching evaluation device suitable for remote digital learning services is shown. DETAILED DESCRIPTION

[0015] The present disclosure will now be discussed with reference to several exemplary embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and thus implement the present disclosure, rather than implying any limitation on the scope of the present disclosure.

[0016] As used herein, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to". The term "based on" is to be interpreted as "based at least in part on". The terms "one embodiment" and "an embodiment" are to be interpreted as "at least one embodiment". The term "another embodiment" is to be interpreted as "at least one other embodiment". The orientation or position relationship indicated by the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "vertical", "horizontal", "lateral", "longitudinal" and the like is based on the orientation or position relationship shown in the accompanying drawings. These terms are mainly for better describing the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation. In addition, in addition to being used to indicate an orientation or position relationship, some of the above terms may also be used to indicate other meanings, such as the term "upper" may also be used to indicate a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to the specific circumstances. In addition, the terms "install", "set", "provided with", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection, or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be an internal connection between two devices, elements or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances. In addition, the terms "first", "second", etc. are mainly used to distinguish different devices, elements or components (the specific types and structures may be the same or different), and are not used to indicate or imply the relative importance and quantity of the indicated devices, elements or components. Unless otherwise specified, "plurality" means two or more.

[0017] In a first aspect, the present invention provides a flipped teaching evaluation method applicable to remote digital learning services, comprising: Acquire the teaching courses and test rules associated with the current class, wherein the test rules include exercise generation rules associated with the teaching courses, and the exercise generation rules include a number of matching keywords; Acquire a first prompt word set and a second prompt word set according to the classroom recording, wherein the first prompt word set is generated based on the student speech translation text in the classroom recording, and the second prompt word set is generated based on the teacher speech translation text in the classroom recording; Acquire a first test question set associated with a first prompt word set, and a second test question set associated with a second prompt word set, wherein the first test question set and the second test question set are generated by a question rule and randomly distributed to interactive user terminals, and the questions displayed corresponding to each user terminal have a cluster number division not higher than a first preset value; Determine a first evaluation value and a second evaluation value in the flipped teaching process based on the test results of the exercises displayed by the user terminal, wherein the first evaluation value and the second evaluation value are the differences between the individual learning effect and the overall learning result; The first evaluation value is obtained based on the analysis of the test results of the first test exercise, and the second evaluation value is obtained based on the analysis of the test results of the second test exercise set.

[0018] In this embodiment, a flipped teaching evaluation method suitable for remote digital learning services is proposed. First, the teaching courses and test rules of the current class are obtained. The test rules include rules for exercise generation, and the exercise generation rules include corresponding keywords. Then, the first prompt word set is obtained based on the student voice translation text in the classroom recording, and the second prompt word set is obtained from the teacher voice translation text. Then, according to the exercise generation rules, the first test exercise set related to the first prompt word set and the second test exercise set related to the second prompt word set are obtained, and the two test exercise sets are sent to the user terminal. Finally, the first evaluation value and the second evaluation value are determined based on the test exercise results displayed by the user terminal. The evaluation of the flipped teaching results is completed through the first evaluation value and the second evaluation value.

[0019] Specifically, flipped teaching is a new teaching model that emphasizes the subject status of students, encourages students to actively participate in learning, and deepens their understanding and mastery of knowledge through independent learning, cooperative exploration, etc. Its specific form is that students conduct independent learning by watching teaching videos, animations, audio and other teaching resources before class, and conduct in-depth learning activities such as problem solving and cooperative exploration under the guidance of teachers in class. It can improve the efficiency of classroom time utilization and promote students' in-depth learning and understanding.

[0020] Specifically, the verification rules are the knowledge points that need to be mastered in the teaching content of this lesson in the syllabus, the homework that needs to be completed, or the in-class exercises that need to be completed. Therefore, the verification rules can also be used to obtain the relevant exercise content of this lesson, that is, the verification rules include exercise generation rules, and the exercise generation rules are to match the relevant keywords in the exercise database to obtain the corresponding test exercises, so the exercise generation rules should also include matching keywords.

[0021] Specifically, classroom recordings include teacher recordings and student recordings. Based on the teacher recordings, the teacher's voice translation text is obtained. Based on the knowledge point keywords involved in the syllabus or related keywords such as in-class exercise keywords, the second prompt word set related to the teaching content of this class can be extracted from the teacher's voice translation text. Similarly, the first prompt word set can be obtained. Therefore, the essence of the first prompt word set is a set of keywords related to the course content mentioned by students, and the essence of the second prompt word set is a set of keywords related to the content mentioned by teachers.

[0022] Specifically, after obtaining the first prompt word set and the second prompt word set, the exercise set can be obtained by matching the relevant keywords in the two sets in the exercise database, that is, the first test exercise set and the second test exercise set are obtained according to the exercise generation rules, and these exercises are randomly distributed to the user terminal.

[0023] Specifically, the number of categories of exercises distributed to the user terminal cannot be higher than the first preset value. In actual application scenarios, the content of each 45-minute class generally includes 3-5 knowledge points, and the exercises are obtained based on the relevant keywords of the knowledge points. Therefore, when dividing the number of clusters of exercises, they should also be divided based on the keywords of the knowledge points to avoid students' thoughts being too scattered when doing the exercises, which affects the efficiency of the class on the one hand and is not conducive to the content teaching of the class on the other hand.

[0024] Specifically, the first preset value can be set based on the different subjects and the difficulty of the course. For example: a mathematics class related to permutations and combinations is relatively difficult and is generally divided into 3-4 class hours for teaching. Therefore, the content of a class may only involve one or two knowledge points, so the first preset value is preferably 3. Another example: a geography class about monsoons and the climate types they affect, whose relevant knowledge points include the types of monsoons, the wind direction of monsoons, the cold or warm currents carried by monsoons, the seasons of monsoons, the impact of monsoons and other knowledge points, then the first preset value needs to be set slightly larger, preferably 5. Because if the knowledge points are too scattered, it will be detrimental to classroom teaching.

[0025] Specifically, based on the exercise test results of the user terminal, the first evaluation value and the second evaluation value are determined.

[0026] Specifically, the first evaluation value is used to evaluate the overall learning situation of students, and the deviation degree of individual students can be known based on the first evaluation value. The second evaluation value is used to evaluate the learning situation of individual students, and the overall deviation degree of students can be understood based on the second evaluation value combined with the first evaluation value.

[0027] Specifically, through the combination of the first evaluation value and the second evaluation value, the evaluation results of each class in flipped teaching can be obtained in a timely and objective manner, which can provide a data basis for teachers to adjust their teaching strategies and make targeted adjustments for individual students.

[0028] Specifically, due to the characteristics of flipped teaching, this method can be applied to remote digital learning services.

[0029] According to one embodiment of the present invention, the process of generating the first test question set includes: Determining a first word set and a second word set according to the frequency of the first prompt word set in the student's voice-translated text, wherein in the student's voice-translated text, the frequency of occurrence of words in the first word set is higher than the frequency of occurrence of words in the second word set; Determine a first exercise generation rule list associated with the first word set, and generate a first test exercise list based on the first exercise generation rule list; Determine a second exercise generation rule list associated with the second word set, and generate a second test exercise list based on the second exercise generation rule list; The first test question list and the second test question list are merged to obtain a first test question set.

[0030] In this embodiment, the generation process of the first test exercise set is described. First, the first word set and the second word set are determined according to the frequency of the first prompt word set in the student's speech translation text. Then, the first exercise generation rule list is generated by the first word set, and the first test exercise list is obtained based on the matching of the first exercise generation rule list; similarly, the second exercise generation rule list is generated by the second word set, and the first test exercise list is obtained based on the matching of the second exercise generation rule list. Finally, the two lists are merged to obtain the first test exercise set.

[0031] Specifically, the first prompt word set is a set of keywords related to some knowledge points that appear in the student's voice-translated text. According to the frequency of occurrence of these keyword sets, the words with higher frequency of occurrence are determined as the first word set, and the word set with lower frequency of occurrence is determined as the second word set. For example, in a math class about trigonometric functions, according to the student's voice-translated text, the first prompt word set includes sin, cos, tan, trigonometric functions, Pythagorean theorem, etc., among which sin, cos, and trigonometric functions appear more frequently than tan and Pythagorean theorem. Therefore, sin, cos, and trigonometric functions are determined as the first word set, and tan and Pythagorean theorem are determined as the second word set.

[0032] Specifically, after obtaining the first word set, the first exercise generation rule list is determined according to the keywords in the set, that is, the keywords in the first word set are used as matching keywords in the first exercise generation rule list and presented in the form of a list, and then the first exercise generation rule list is matched with the exercise list related to the matching keywords in the exercise database to obtain the first test exercise list. The second test exercise list is obtained in the same way. According to one embodiment of the present invention, the first exercise generation rule list does not contain the exercise generation rules in the first exercise generation list.

[0033] In this embodiment, the matching keywords in the second exercise generation rule list do not include the matching keywords in the first exercise generation rule list, so as to avoid duplicate exercise lists when matching the exercise database.

[0034] According to an embodiment of the present invention, the process of acquiring the first prompt word set and the second prompt word set includes: Determine the user speech time interval sets of students and teachers respectively based on the speech records of the user terminals; Determine the teacher's speech translation text and the student's speech translation text based on the user's speech time interval set; Segment the teacher's voice translation text, and obtain a second prompt word set based on the matching of the segmentation result and the exercise generation rule; The student's speech translation text is segmented, and the first prompt word set is obtained based on the matching of the segmentation result and the exercise generation rule.

[0035] In this embodiment, the process of obtaining the first prompt word set and the second prompt word set is described. First, the speech time area sets of students and teachers are respectively confirmed based on the speech records of the user terminal. Then, the speech of students and teachers is distinguished by the speech time area set to distinguish the student speech translation text and the teacher speech translation text. Finally, the student speech translation text is segmented, and based on the matching of the segmented results and the exercise generation rules, that is, using several matching keywords contained in the exercise generation rules to match the segmented results, all matching segmentation results are used as the first prompt word set. The second prompt word set is obtained in the same way.

[0036] Specifically, in actual application scenarios, the time intervals of the teacher and student speeches are determined based on the speech records of the user terminal, and then the speech in different time intervals is translated into text, and the teacher speech translation text and the student speech translation text are obtained by distinguishing them. For example: in a 45-minute class, the teacher's main speaking time intervals are 00:00~02:30, 10:13~15:28, 25:30~31:55, 43:33~45:00, then the speech in the above time periods is translated into text as the teacher speech translation text, and the speech in the rest of the time is translated into text as the student speech translation text.

[0037] Specifically, the teacher's voice-translated text is segmented. For example, in the teacher's voice-translated text, there is a sentence "Today, we are going to learn four idioms and their allusions, namely, Ye Gonghaolong, Buying the Box and Returning the Pearl, Zheng Renmai Shoes, and Learning to Walk in Handan". The sentence is segmented and the segmentation results obtained include: today, we, want to, learn, four, idioms, and, allusions, respectively, are, Ye Gonghaolong, Buying the Box and Returning the Pearl, Zheng Renmai Shoes, and, Learning to Walk in Handan. These segmentation results are matched with the matching keywords in the exercise generation rules to obtain the first prompt word set.

[0038] Specifically, word segmentation refers to the process of recombining continuous Chinese character sequences into independent word sequences according to certain specifications. There are many ways to segment words, including: dictionary-based word segmentation method, statistical-based word segmentation method, rule-based word segmentation method, word segmentation method based on character annotation, word segmentation method based on artificial intelligence technology, etc. In the actual application process, it can also be selected and optimized according to the course category.

[0039] Specifically, dividing the first word set and the second word set based on the frequency of occurrence of various words related to the matching keywords in the translated text can make the two test exercise lists based on the two word sets more comprehensive and avoid missing any obscure knowledge points or test points.

[0040] According to one embodiment of the present invention, the process of generating the second test question set includes: Determine a third exercise generation rule list associated with the second prompt word set; removing the exercise generation rules in the third exercise generation rule list that are repeated with the exercise generation rules used to generate the first test exercise set; A second test exercise set is generated according to the third exercise generation rule list.

[0041] In this embodiment, the process of generating the second test exercise set is described. First, the third exercise generation rule list is determined according to the second prompt word set, that is, the matching keywords in the third exercise generation rule list are determined according to the keywords in the second prompt word set, and then the matching keywords in the third exercise generation rule list and the matching keywords in the first test exercise generation rule list are deduplicated, and finally the second test exercise set is obtained by matching the exercise database according to the deduplicated third exercise generation rule list.

[0042] Specifically, the first prompt word set and the second prompt word set are obtained based on the voice translation texts of the students and teachers, respectively. In the same class, the topics or contents described by the teachers and students are definitely the same. Therefore, the first prompt word set and the second prompt word set obtained based on the voice translation texts of the teachers and students are bound to have duplicates, resulting in duplicate matching keywords in the first exercise generation rule list and the third exercise generation rule list. If deduplication is not performed, the second test exercise set and the first test exercise set will have duplicate exercises. In order to avoid this phenomenon, it is necessary to remove the matching keywords in the third exercise generation rule list that are duplicated with the matching keywords in the first exercise generation rule list.

[0043] According to an embodiment of the present invention, the number of clusters is divided into the total number of categories into which the exercises displayed on the user terminal are divided when the first test exercise set and the second test exercise set are clustered according to the exercise generation rule; The clustering according to the exercise generation rule includes: Setting keywords corresponding to the exercises in the first test exercise set and the second test set based on the exercise generation rules for generating the first test exercise set and the second test set; The exercises are clustered based on the keywords corresponding to the exercises in the first test exercise set and the second test exercise set to obtain a clustering result.

[0044] In this embodiment, it is shown that the cluster number division is based on the total number of categories into which the exercises displayed on the user terminal are divided when the first test exercise set and the second test exercise set are clustered according to the exercise generation rule.

[0045] Specifically, clustering according to exercise rules requires first setting keywords corresponding to the exercises in the first test set and the second test set based on the exercise generation rules of the first test exercise set and the second test exercise set; then clustering can be performed based on these keywords to obtain clustering results.

[0046] Specifically, in a class, the content involved in the class basically revolves around 3-5 knowledge points, so the number of categories of exercises, that is, the results of clustering, generally will not appear many. For example, in an English class, the relevant knowledge points of the course include: present continuous tense, past continuous tense, past tense and present perfect tense, then the final results of the exercises will also appear around these 4 knowledge points, that is, the number of clusters of exercises should be around 4.

[0047] According to an embodiment of the present invention, the first evaluation value is obtained in the following manner: The first test question set is grouped according to keywords corresponding to the questions in the first test question set, and based on the answer results of the first test question set, an overall answer accuracy dictionary corresponding to the questions in the grouping results is obtained; Acquire a sequence of correct answer rates of the user terminal, wherein the sequence of correct answer rates includes the correct answer rates of the user terminal in answering the questions in the first test question set and the overall correct answer rates of the questions in the first test question set for which the user terminal's answer results are incorrect; The variance is determined as the first evaluation value based on the answer accuracy sequence.

[0048] In this embodiment, a method for obtaining the first evaluation value is described. First, the questions are grouped according to the keywords corresponding to the questions in the first test question set, and the grouped first test question set is distributed to the user terminal for answering. Based on the user terminal's answer results to the grouped first test question set, an overall answer accuracy dictionary for the corresponding questions in each group is obtained. Then, based on the overall answer accuracy dictionary, an overall answer accuracy sequence is obtained, and the answer accuracy sequence includes the answer accuracy of the entire question and the overall answer accuracy of the wrong question. Finally, the variance of the overall answer accuracy of the entire question and the answer accuracy of the wrong question in the answer accuracy sequence is used as the first evaluation value.

[0049] Specifically, the purpose of grouping exercises is to prevent the questions from being too scattered, so that the final statistical results have too little data to serve as data support.

[0050] Specifically, by grouping questions based on keywords, we can understand the students' mastery of the keywords involved in each group of questions based on the answer results. For example, a physics lesson on buoyancy includes three knowledge points: Archimedes' principle, calculation formula, and the state of objects in liquids. The first test exercise set is divided into three groups based on the corresponding keywords. The correct rate of students in each group of exercises can be used to understand the students' learning status and self-study ability on this knowledge point.

[0051] Specifically, the overall answer accuracy dictionary contains the user terminal corresponding to each set of questions and the answer accuracy of the user terminal. Therefore, according to the overall answer accuracy dictionary, the answer accuracy sequence of the user terminal can be obtained.

[0052] Specifically, the answer accuracy sequence includes the accuracy rate of the user terminal's answers to the exercises in the first test exercise set and the overall answer accuracy rate of the exercises in the first test exercise set whose answers are incorrect. The accuracy rate of the correctly answered questions can reflect the knowledge points with better self-study situation, and the accuracy rate of the incorrect exercises can indicate how many students as a whole have mastered the knowledge points corresponding to the exercises with errors.

[0053] Specifically, using the variance of the answer accuracy as the first evaluation value can more intuitively discover the overall self-study situation from a holistic perspective, as well as the overall situation of whether the mastery of a certain knowledge point is good or poor.

[0054] According to an embodiment of the present invention, the second evaluation value is obtained in the following manner: Obtaining the first answer accuracy rate of all user terminals in answering questions in the second test question set; Obtaining the second answer accuracy rate of the user terminal in answering the questions in the second test question set; The ratio of the second answer accuracy rate to the first answer accuracy rate is used as the second evaluation value.

[0055] In this embodiment, a method for obtaining the second evaluation value is described. First, the overall correct rate of answers to the questions in the second test question set by all user terminals is obtained, that is, the first answer correct rate. Then, the individual correct rate of the questions in the second test question set of a single user terminal is obtained, that is, the second answer correct rate, and the ratio of the second answer correct rate to the first answer correct rate is used as the second evaluation value.

[0056] Specifically, through the first answer accuracy rate, when evaluating with variance, we can get the overall self-study situation and the degree of deviation of the individual self-study situation from the overall self-study situation. The result represented by this degree of deviation can be that the individual self-study situation is good or poor. And through the second evaluation value, we can know whether this deviation is good or bad. By comparing the second answer accuracy rate with the first answer accuracy rate, we can know that if the ratio is greater than 1, it means that the individual self-study situation is good during this deviation, and the larger the ratio, the better the self-study situation. On the contrary, if the ratio is less than 1, it means that the individual self-study situation is lower than the average level, and the smaller the ratio, the worse the self-study situation, or even no self-study before class.

[0057] In a second aspect, the present invention provides a flipped teaching evaluation device suitable for remote digital learning services, comprising: A rule unit, used to obtain teaching courses and test rules associated with the current class, wherein the test rules include exercise generation rules associated with the teaching courses, and the exercise generation rules include a number of matching keywords; A prompt word acquisition unit, used to acquire a first prompt word set and a second prompt word set according to the classroom recording, wherein the first prompt word set is generated based on the student speech translation text in the classroom recording, and the second prompt word set is generated based on the teacher speech translation text in the classroom recording; An evaluation content generating unit is used to obtain a first test exercise set related to a first prompt word set and a second test exercise set related to a second prompt word set, wherein the first test exercise set and the second test exercise set are generated by an exercise rule and are randomly distributed to interactive user terminals, and the exercises displayed corresponding to each user terminal have a cluster number division not higher than a first preset value; A teaching evaluation unit, which determines a first evaluation value and a second evaluation value in the flipped teaching process based on the test results of the exercises displayed by the user terminal, wherein the first evaluation value and the second evaluation value are the differences between the individual learning effect and the overall learning result; The first evaluation value is obtained based on the analysis of the test results of the first test exercise, and the second evaluation value is obtained based on the analysis of the test results of the second test exercise set.

[0058] The beneficial effects of the present invention are: through the method and device of the present invention, on the one hand, the results of flipped teaching can be objectively and effectively evaluated without being restricted to the subjective evaluation of traditional questionnaires or student surveys, and on the other hand, feedback on the flipped teaching effect of each class can be obtained immediately, and teachers can formulate corresponding strategies in time according to the feedback for supplementation and improve the subsequent flipped teaching details according to the feedback. In addition, due to the characteristics of flipped teaching, this method can be applied to remote digital learning services.

[0059] Those of ordinary skill in the art will appreciate that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0060] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0061] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0062] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0063] In addition, each functional module in the embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0064] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the energy-saving signal sending / receiving method of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0065] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

[0066] It should be understood that the size of the sequence number of each step in the content of the invention and the embodiments of the present invention does not absolutely mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention. For the purpose of example and description, the foregoing description of the implementation of the present disclosure has been given. The foregoing description is not exhaustive and is not intended to limit the present disclosure to the exact form disclosed. Various deformations and modifications may exist according to the above teachings, or various deformations and modifications may be obtained from the practice of the present disclosure. These embodiments are selected and described to illustrate the principles of the present disclosure and its practical application, so that those skilled in the art can use the present disclosure in various embodiments and various modifications suitable for the specific purpose conceived.

Claims

1. A flipped teaching evaluation method for remote digital learning services, characterized in that: include: Acquire the teaching courses and test rules associated with the current class, wherein the test rules include exercise generation rules associated with the teaching courses, and the exercise generation rules include a number of matching keywords; Acquire a first prompt word set and a second prompt word set according to the classroom recording, wherein the first prompt word set is generated based on the student speech translation text in the classroom recording, and the second prompt word set is generated based on the teacher speech translation text in the classroom recording; Acquire a first test question set associated with a first prompt word set, and a second test question set associated with a second prompt word set, wherein the first test question set and the second test question set are generated by a question generation rule and are randomly distributed to interactive user terminals, and the questions displayed corresponding to each user terminal have a cluster number division not higher than a first preset value; Determine a first evaluation value and a second evaluation value in the flipped teaching process based on the test results of the exercises displayed by the user terminal, wherein the first evaluation value and the second evaluation value are the differences between the individual learning effect and the overall learning result; The first evaluation value is obtained based on the analysis of the test results of the first test exercise, and the second evaluation value is obtained based on the analysis of the test results of the second test exercise set.

2. The flipped teaching evaluation method for remote digital learning services according to claim 1, characterized in that: The generation process of the first test exercise set includes: Determining a first word set and a second word set according to the frequency of the first prompt word set in the student's voice-translated text, wherein in the student's voice-translated text, the frequency of occurrence of words in the first word set is higher than the frequency of occurrence of words in the second word set; Determine a first exercise generation rule list associated with the first word set, and generate a first test exercise list based on the first exercise generation rule list; Determine a second exercise generation rule list associated with the second word set, and generate a second test exercise list based on the second exercise generation rule list; The first test question list and the second test question list are merged to obtain a first test question set.

3. The flipped teaching evaluation method for remote digital learning services according to claim 2, characterized in that: The second exercise generation rule list does not include the exercise generation rules in the first exercise generation rule list.

4. The flipped teaching evaluation method for remote digital learning services according to claim 1, characterized in that: The process of obtaining the first prompt word set and the second prompt word set includes: Determine the user speech time interval sets of students and teachers respectively based on the speech records of the user terminals; Determine the teacher's speech translation text and the student's speech translation text based on the user's speech time interval set; Segment the teacher's voice translation text, and obtain a second prompt word set based on the matching of the segmentation result and the exercise generation rule; The student's speech translation text is segmented, and the first prompt word set is obtained based on the matching of the segmentation result and the exercise generation rule.

5. The flipped teaching evaluation method for remote digital learning services according to claim 1, characterized in that: The generation process of the second test exercise set includes: Determine a third exercise generation rule list associated with the second prompt word set; removing the exercise generation rules in the third exercise generation rule list that are repeated with the exercise generation rules used to generate the first test exercise set; A second test exercise set is generated according to the third exercise generation rule list.

6. The flipped teaching evaluation method for remote digital learning services according to claim 1, characterized in that: The number of clusters is the total number of categories into which the exercises displayed on the user terminal are divided when the first test exercise set and the second test exercise set are clustered according to the exercise generation rule; The clustering according to the exercise generation rule includes: Setting keywords corresponding to the exercises in the first test exercise set and the second test set based on the exercise generation rules for generating the first test exercise set and the second test set; The exercises are clustered based on the keywords corresponding to the exercises in the first test exercise set and the second test exercise set to obtain a clustering result.

7. The flipped teaching evaluation method for remote digital learning services according to claim 1, characterized in that: The first evaluation value is obtained as follows: The first test question set is grouped according to keywords corresponding to the questions in the first test question set, and based on the answer results of the first test question set, an overall answer accuracy dictionary corresponding to the questions in the grouping results is obtained; Acquire a sequence of correct answer rates of the user terminal, wherein the sequence of correct answer rates includes the correct answer rates of the user terminal in answering the questions in the first test question set and the overall correct answer rates of the questions in the first test question set for which the user terminal's answer results are incorrect; The variance is determined as the first evaluation value based on the answer accuracy sequence.

8. The flipped teaching evaluation method for remote digital learning services according to claim 1, characterized in that: The second evaluation value is obtained as follows: Obtaining the first answer accuracy rate of all user terminals in answering questions in the second test question set; Obtaining the second answer accuracy rate of the user terminal in answering the exercises in the second test exercise set; The ratio of the second answer accuracy rate to the first answer accuracy rate is used as the second evaluation value.

9. A flipped teaching evaluation device suitable for remote digital learning services, characterized in that: include: A rule unit, used to obtain teaching courses and test rules associated with the current class, wherein the test rules include exercise generation rules associated with the teaching courses, and the exercise generation rules include a number of matching keywords; A prompt word acquisition unit, used to acquire a first prompt word set and a second prompt word set according to the classroom recording, wherein the first prompt word set is generated based on the student speech translation text in the classroom recording, and the second prompt word set is generated based on the teacher speech translation text in the classroom recording; An evaluation content generating unit is used to obtain a first test exercise set related to a first prompt word set and a second test exercise set related to a second prompt word set, wherein the first test exercise set and the second test exercise set are generated by an exercise rule and are randomly distributed to interactive user terminals, and the exercises displayed corresponding to each user terminal have a cluster number division not higher than a first preset value; A teaching evaluation unit, which determines a first evaluation value and a second evaluation value in a flipped teaching process based on a test result of an exercise displayed by a user terminal, wherein the first evaluation value and the second evaluation value are differences between individual learning effects and overall learning results; The first evaluation value is obtained based on the analysis of the test results of the first test exercise, and the second evaluation value is obtained based on the analysis of the test results of the second test exercise set.

Images