Knowledge point mastering degree evaluation method and device, equipment and storage medium

Abstract

The invention provides a knowledge point mastering degree evaluation method and device, equipment and a storage medium, which are applied to electronic equipment provided with a first camera and a second camera, and are used for performing linkage analysis on an operation image collected by the first camera and a user image collected by the second camera. According to the method, four different dimensions of data including user behavior data, interruption behavior data, correction results and answering time corresponding to the question are obtained, and the mastering degree of the knowledge points corresponding to the question by the user is obtained by integrating the four dimensions of data, so that the real knowledge point mastering degree of the user is reflected more comprehensively; and comprehensiveness and accuracy of knowledge point mastering degree evaluation are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent teaching technology, and in particular to a method, device, equipment and storage medium for evaluating the degree of mastery of knowledge points. Background Art

[0002] With the rapid development of technology, the use of intelligent learning devices, such as learning machines and smart tablets, is becoming increasingly popular in education. Using intelligent learning devices to complete homework and conduct independent learning has become a new trend in modern education, providing a new way to improve learning efficiency and optimize learning outcomes.

[0003] However, despite their increasingly widespread applications, the smart learning devices currently on the market still have certain functional limitations. Most smart learning devices are limited to providing basic functions such as electronic teaching materials, online courses, and question bank resources, making it difficult to accurately and comprehensively assess students' true mastery of knowledge points. Summary of the Invention

[0004] In view of this, the present application provides a method, device, equipment and storage medium for evaluating the degree of mastery of knowledge points to solve the above technical problems.

[0005] In a first aspect of the present application, a method for evaluating the degree of mastery of a knowledge point is provided, which is applied to an electronic device equipped with a first camera and a second camera, the method comprising:

[0006] Determining a reference question marked as being answered in the homework image captured by the first camera at the current moment;

[0007] For each reference question, obtaining user behavior data corresponding to the reference question based on user images captured by the second camera after the reference question is marked as being answered, and determining whether there has been a change in the answer traces for the reference question based on the work images captured by the first camera at the current moment and the previous moment;

[0008] If there is a change, the interruption behavior data corresponding to the reference question is updated according to the current interruption duration corresponding to the reference question, and the reference question is corrected and the correction result is updated; wherein the interruption duration is used to represent the length of time the reference question is interrupted during the answering process;

[0009] If there is no change, the interruption time corresponding to the reference question is updated. If the updated interruption time exceeds the set interruption time, and the number of times the target behavior data appears in the user behavior data does not exceed the set number of times, the mark of the reference question is updated from answering to completed answering and the answering time is obtained. For the reference question marked as completed answering, the user's mastery of the knowledge points of the reference question is obtained based on the user behavior data, interruption behavior data, correction results and answering time corresponding to the reference question.

[0010] According to one embodiment of the present application, the method further includes:

[0011] If the updated interruption duration exceeds the set interruption duration, and the number of occurrences of the target behavior data in the user behavior data exceeds the set number of occurrences, updating the flag of the reference question from "being answered" to "not answering", wherein the target behavior data includes first expression data that satisfies the first determination condition and is used to represent an emotion of uncertainty;

[0012] For the reference questions marked as unanswerable, the answer contents of the reference questions and / or other questions with relevant knowledge points to the reference questions are recommended to the user.

[0013] According to one embodiment of the present application, the interruption behavior data includes the number of occurrences of the question-answering interruption behavior and the duration of each question-answering interruption behavior; updating the interruption behavior data corresponding to the reference question according to the interruption duration currently corresponding to the reference question includes:

[0014] If the interruption duration currently corresponding to the reference question exceeds the first threshold, a question-answering interruption behavior is recorded, and after the duration of this question-answering interruption behavior is obtained based on the interruption duration, the interruption duration is reset to zero.

[0015] According to one embodiment of the present application, the method further includes:

[0016] For a reference question marked as completed, display the correction result of the reference question, control the second camera to capture a user image during the display of the correction result, and obtain user expression data related to the correction result based on the user image during the display of the correction result;

[0017] If the user expression data includes any of the following expression data: first expression data for representing uncertainty emotions that meets the first determination condition, and second expression data for representing negative emotions that meets the second determination condition, then adjusting the grading strategy to re-grade the reference question to obtain a secondary grading result;

[0018] If the difference between the second grading result and the grading result exceeds a second threshold, the second grading result is used as the final grading result of the reference question and the final grading result is displayed.

[0019] According to one embodiment of the present application, obtaining the user's mastery of the knowledge points of the reference question based on the user behavior data, interruption behavior data, correction results, and answering time corresponding to the reference question includes:

[0020] Calculating a first score based on the user behavior data corresponding to the reference question, the first score being used to represent the frequency of occurrence of specified expression data in the user behavior data, the specified expression data including first expression data for representing an uncertain emotion that meets a first determination condition and / or second expression data for representing a negative emotion that meets a second determination condition;

[0021] Calculating a second score based on the interruption behavior data corresponding to the reference question, wherein the second score is used to characterize the intensity of the interruption behavior during the answering process of the reference question;

[0022] Calculating a third score based on the correction result of the reference question, wherein the third score is used to represent the degree of deviation between the correction result and the set correction result;

[0023] Calculating a fourth score based on the answering time of the reference question, the fourth score being used to indicate the extent to which the answering time exceeds the set answering time;

[0024] The user's mastery of the knowledge points of the reference question is obtained based on the first score, the second score, the third score, the fourth score, and the weight coefficients corresponding to the scores.

[0025] According to one embodiment of the present application, after obtaining the user's mastery of the knowledge points of the reference question, the method further includes:

[0026] If the user's mastery of the knowledge points of the reference question is within a first set range, recommending at least one first question to the user, where the knowledge points involved in the first question are a subset of the knowledge points involved in the reference question;

[0027] If the user's mastery of the knowledge points of the reference question is within a second set range, recommending at least one second question to the user, where the second question involves the same knowledge points as the reference question;

[0028] If the user's mastery of the knowledge points of the reference question is within a third set range, at least one third question is recommended to the user, and the number of knowledge points or the difficulty coefficient of the knowledge points involved in the third question exceeds that of the reference question.

[0029] According to one embodiment of the present application, the method further includes:

[0030] For the fourth question that is not marked in the homework image captured by the first camera at the current moment, if there is no trace of answering the question in the homework image captured at the previous moment, and there is trace of answering the question in the homework image captured at the current moment, then the question is marked as being answered.

[0031] In a second aspect of the present application, a knowledge point mastery degree assessment device is provided, which is applied to an electronic device equipped with a first camera and a second camera, and includes:

[0032] a determining unit, configured to determine a reference question marked as being answered in the homework image captured by the first camera at a current moment;

[0033] a judgment unit configured to, for each reference question, obtain user behavior data corresponding to the reference question based on user images captured by the second camera after the reference question is marked as being answered, and to judge whether there has been a change in the answer trace of the reference question based on the work images captured by the first camera at the current moment and the previous moment;

[0034] A first processing unit is configured to update the interruption behavior data corresponding to the reference question according to the interruption duration currently corresponding to the reference question, and to correct the reference question and update the correction result if a change occurs; wherein the interruption duration is used to represent the duration of the interruption in the process of answering the reference question;

[0035] The second processing unit is used to update the interruption duration corresponding to the reference question if there is no change. If the updated interruption duration exceeds the set interruption duration and the number of times the target behavior data appears in the user behavior data does not exceed the set number of times, the mark of the reference question is updated from being answered to completed answering and the answering time is obtained. For the reference question marked as completed answering, the user's mastery of the knowledge points of the reference question is obtained based on the user behavior data, interruption behavior data, correction results and answering time corresponding to the reference question.

[0036] In a third aspect of the present application, an electronic device is provided, comprising a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor is used to execute the machine-executable instructions to implement the steps of the method proposed in the above embodiment.

[0037] In a fourth aspect of the present application, a machine-readable storage medium is provided, wherein the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a processor, the steps of the method proposed in the above embodiment are implemented.

[0038] It can be seen from the above technical solution that by determining the reference question marked as being answered in the homework image captured by the first camera at the current moment; obtaining user behavior data based on the user image captured by the second camera after the reference question is marked as being answered; judging whether the answer traces of the reference question have changed based on the homework images captured by the first camera at the current moment and the previous moment respectively; if changed, the interruption behavior data corresponding to the reference question is updated according to the current interruption duration corresponding to the reference question, and the reference question is corrected and the correction result is updated; if not changed, the interruption duration corresponding to the reference question is updated. If the updated interruption duration exceeds the set interruption duration, and the number of times the target behavior data appears in the user behavior data does not exceed the set number, the mark of the reference question is updated to completed answering and the answering time is obtained. Finally, based on the user behavior data, interruption behavior data, correction results and answering time corresponding to the reference question, the user's mastery of the knowledge points of the reference question is obtained. By jointly analyzing the homework images captured by the first camera and the user images captured by the second camera, we can obtain data in four different dimensions, namely, user behavior data corresponding to the question, interruption behavior data, correction results, and answering time. By integrating the data from the above four dimensions, we can obtain the user's mastery of the knowledge points corresponding to the question, thereby more comprehensively reflecting the user's actual mastery of the knowledge points and improving the comprehensiveness and accuracy of the knowledge point mastery assessment.

[0039] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a method for evaluating the mastery of knowledge points provided in an embodiment of the present application;

[0041] Figure 2 This is a flowchart of a method for recommending Q&A content provided in an embodiment of the present application;

[0042] Figure 3 This is a flow chart of optimizing the correction results provided by an embodiment of the present application;

[0043] Figure 4 This is a flowchart of calculating the degree of mastery of a knowledge point provided by an embodiment of the present application;

[0044] Figure 5This is a schematic diagram of the structure of a knowledge point mastery evaluation device provided in an embodiment of the present application;

[0045] Figure 6 It is a schematic diagram of the hardware structure of an electronic device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0046] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0047] The terms used in this application are for the purpose of describing particular embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0048] In order to enable those skilled in the art to better understand the technical solutions provided by the embodiments of the present application, and to make the above-mentioned purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application are further described in detail below with reference to the accompanying drawings.

[0049] With the rapid development of technology, the use of intelligent learning devices, such as learning machines and smart tablets, is becoming increasingly popular in education. Using intelligent learning devices to complete homework and conduct independent learning has become a new trend in modern education, providing a new way to improve learning efficiency and optimize learning outcomes.

[0050] However, despite its increasingly widespread application, the smart learning devices currently on the market still have certain functional limitations. Most smart learning devices are limited to providing basic functions such as electronic teaching materials, online courses, and question bank resources. It is difficult to accurately assess students' true mastery of knowledge points, which makes it difficult to provide students with personalized tutoring content and cannot fully meet students' diverse learning needs.

[0051] In view of this, an embodiment of the present application discloses a method for evaluating the degree of mastery of knowledge points to solve the above technical problems.

[0052] like Figure 1 As shown, Figure 1 This is a flow chart of a method for evaluating the degree of mastery of knowledge points provided in an embodiment of the present application.

[0053] The method for evaluating the degree of mastery of knowledge points is applied to an electronic device equipped with a first camera and a second camera.

[0054] The embodiments of this application do not specifically limit the type of electronic device. For example, the electronic device may include a tablet electronic device, such as a tablet computer, a tablet learning device, a tablet game console, or a portable electronic device, such as a smartphone, an e-reader, or the like.

[0055] Furthermore, the embodiments of this application do not specifically limit the manner in which the first camera and the second camera are mounted on the electronic device. For example, the first camera and the second camera may be integrated as inherent components of the electronic device, or may be detachable components that are detachably connected to the electronic device via a standardized interface.

[0056] In addition, the embodiments of the present application do not specifically limit the locations where the first camera and the second camera are installed on the electronic device. For example, taking a tablet-type electronic device as an example, the tablet-type electronic device may include a tablet body and an external camera module, wherein the external camera module may include a first camera and a second camera, and the location where the external camera module is installed on the tablet body includes but is not limited to the front, back, or frame. For example, the external camera module is installed on the frame of the tablet body, specifically, it can be installed on one of the top frames when the tablet body is in use.

[0057] It should be noted that for electronic devices equipped with a first camera and a second camera, the second camera can be oriented toward the user to capture images of the user, including but not limited to image information such as the user's sitting posture, demeanor, and facial expressions. The first camera can be oriented toward the desktop in front of the user to capture images of homework assignments on the desktop in front of the user. These images are images of homework assignments completed by the user, including but not limited to image information such as the questions and traces of answers.

[0058] The method for evaluating the degree of mastery of a knowledge point may include the following steps:

[0059] S101: Determine a reference question marked as being answered in the homework image captured by the first camera at the current moment.

[0060] The shooting direction of the first camera can face the desktop in front of the user, and is used to capture the homework image on the desktop. The homework image is an image frame of the homework answered by the user.

[0061] In some embodiments, the first camera can obtain the operation image in real time or timed acquisition, that is, the first camera can continuously acquire the operation image on the desktop in real time, or acquire the operation image on the desktop once at a set time interval, wherein the set time (that is, the acquisition time interval) is a configurable parameter and can be adjusted according to the specific application scenario and actual needs.

[0062] In some embodiments, after obtaining the job image captured by the first camera, the job image captured by the first camera may be preprocessed, such as scaling to a fixed size, color space conversion, noise suppression, and image data standardization.

[0063] In some embodiments, question detection and recognition can be performed on the homework image captured by the first camera at the current moment to obtain all questions contained in the homework image. The correspondence between questions and tag information can be stored, and for each obtained question, a query is performed to determine whether corresponding tag information already exists for the question. If corresponding tag information exists for the question, a further determination is made as to whether the tag information corresponding to the question indicates that the question is currently being answered. If the tag information corresponding to the question indicates that the question is currently being answered, the question is determined to be a reference question marked as being answered in the homework image captured by the first camera at the current moment.

[0064] In some embodiments, for a question that does not have a mark in the homework image captured by the first camera at the current moment, if there is no trace of answering the question in the homework image captured at the previous moment, and there is a trace of answering the question in the homework image captured at the current moment, then the question is marked as being answered.

[0065] Specifically, the homework image captured by the first camera at the current moment can be used to detect and identify questions, and all questions contained in the homework image can be obtained. The correspondence between the questions and the marking information can be stored, and for each question obtained, it is queried whether the corresponding marking information already exists for the question. If there is no corresponding marking information for the question, it is determined whether there are traces of answering the question in the homework images captured at the previous moment and the current moment. If there are no traces of answering the question in the homework image captured at the previous moment, and there are traces of answering the question in the homework image captured at the current moment, a correspondence between the question and the marking information "answering" is established, so that the question is marked as being answered. When the marking information of a question is "answering", it indicates that the user is answering the question.

[0066] It should be noted that due to differences in users' answering speed and ability, and the fact that the first camera can acquire the homework image in real time or at a scheduled time, there may be only one or multiple reference questions marked as being answered in the homework image captured by the first camera at the current moment.

[0067] S102: For each reference question, based on the user image captured by the second camera after the reference question is marked as being answered, obtain the user behavior data corresponding to the reference question, and based on the homework images captured by the first camera at the current moment and the previous moment respectively, determine whether the answer traces of the reference question have changed.

[0068] After the reference question is marked as being answered, the second camera can be controlled to capture user images, and user behavior data corresponding to the reference question can be obtained based on the user images captured by the second camera from the time the reference question is marked as being answered to the current moment.

[0069] Exemplarily, user behavior data includes at least user expression data. User behavior data can be recorded in time series, with each moment associated with a set of user behavior data. Each set of user behavior data can include information of one or more dimensions, including at least user expression data, such as happiness, joy, confusion, hesitation, anger, rage, etc. Of course, user behavior data can also include user sitting posture data, user holding items data, user leaving the table data, etc., which are not specifically limited in the embodiments of the present application.

[0070] In some embodiments, a user image captured by the second camera after the reference question is marked as being answered can be fed into a pre-trained face detection model, such as a multi-task cascaded convolutional neural network (MTCNN) or a retina network (RetinaNet). This model can identify the facial region in the user image and output the corresponding facial bounding box coordinates. Based on the face detection results, the facial image is cropped from the user image and pre-processed, such as image alignment, illumination correction, and size normalization. The pre-processed facial image is fed into a pre-trained expression recognition model, such as VGG-Face or FaceNet, which can recognize and output user expressions, including but not limited to happiness, joy, confusion, hesitation, anger, and rage. The resulting user expression data is associated with the corresponding user image capture time to form a complete set of user behavior data. The resulting user behavior data is then associated with the reference question to obtain the user behavior data corresponding to the reference question.

[0071] In some embodiments, for each reference question, the homework images captured by the first camera at the current moment and the previous moment can be respectively detected and identified to locate the answer area in the homework images captured at the two moments before and after the reference question. Subsequently, handwriting detection can be performed on the two answer areas respectively, and the handwriting features in the two answer areas can be compared and analyzed to determine whether the answer traces have changed, where changes in the answer traces include the addition of new handwriting or the modification of the original handwriting. If the handwriting features in the two answer areas have changed, it can be determined that the answer traces of the reference question have changed; otherwise, it is determined that the answer traces of the reference question have not changed.

[0072] Of course, the embodiments of the present application do not specifically limit the method of "determining whether the answer traces of the reference questions have changed". For example, image difference technology, deep learning models and other methods can also be used to determine whether the answer traces of the reference questions have changed.

[0073] S103: If a change occurs, the interruption behavior data corresponding to the reference question is updated according to the current interruption duration corresponding to the reference question, and the reference question is corrected and the correction result is updated; wherein the interruption duration is used to represent the duration of the interruption of the reference question during the answering process.

[0074] Regarding the interruption duration, each reference question has a corresponding interruption duration, which is used to represent the duration of the interruption in the process of answering the reference question. The initial value of the interruption duration can be pre-set according to actual needs. For example, the initial value of the interruption duration can be set to 0. The interruption duration can be updated in two ways. One is to reset the interruption duration to zero after updating the interruption behavior data corresponding to the reference question according to the current interruption duration corresponding to the reference question; the other is to update when the answer trace of the reference question has not changed. The update steps in this case will be described in detail below and will not be further explained here.

[0075] In an embodiment of the present application, if the answer trace of a reference question changes, the interruption behavior data corresponding to the reference question is updated based on the current interruption duration corresponding to the reference question. The interruption behavior data refers to data related to the interruption behavior of answering questions, which is used to record and analyze the characteristics of the user's interruption behavior during the answering process.

[0076] For example, the interruption behavior data may include the number of interruptions and the duration of each interruption. Of course, the embodiments of the present application are not limited to this. For example, the interruption behavior data may also include the average duration of interruptions, the longest interruption, etc.

[0077] In some embodiments, updating the interruption behavior data corresponding to the reference topic according to the current interruption duration corresponding to the reference topic includes:

[0078] If the interruption time corresponding to the current reference question exceeds the first threshold, a question-answering interruption behavior is recorded, and after the duration of this question-answering interruption behavior is obtained based on the interruption time, the interruption time is reset to zero.

[0079] Specifically, if the answer trace of the reference question changes, and the current interruption duration corresponding to the reference question exceeds the preset first threshold, the first threshold is set to exclude unexpected situations and can be set according to actual needs. For example, the first threshold can be set to 0, 5 seconds, etc., which means that before the answer trace changes this time, the answer trace has not changed, resulting in an update of the interruption duration, and the updated interruption duration exceeds the first threshold. At this time, it is considered that before the answer trace changes this time, an effective answer interruption behavior occurred, and an answer interruption behavior is recorded, and the duration of this answer interruption behavior is obtained based on the interruption duration. For example, the current interruption duration corresponding to the reference question can be directly used as the duration of this answer interruption behavior.

[0080] For example, assuming that the first threshold is set to 3 seconds according to actual needs, and the first camera collects a homework image every 2 seconds. If the answer traces of the reference question in the homework images at the 4th and 2nd seconds do not change, the interruption duration corresponding to the reference question can be updated to 2 seconds. If the answer traces of the reference question in the homework images at the 6th and 4th seconds do not change, the interruption duration corresponding to the reference question can be updated again to 4 seconds. If the answer traces of the reference question in the homework images at the 8th and 6th seconds change, since the current interruption duration corresponding to the reference question is 4 seconds, which exceeds the first threshold of 3 seconds, it is determined that a valid answer interruption occurred before the answer trace changed this time, and an answer interruption behavior is recorded, and the current interruption duration corresponding to the reference question is used as the duration of this answer interruption behavior, and finally the interruption duration corresponding to the reference question is reset to zero.

[0081] In another example, if the answer trace for the reference question in the homework image at the 4th and 2nd seconds remains unchanged, the interruption duration corresponding to the reference question is updated to 2 seconds. If the answer trace for the reference question in the homework image at the 6th and 4th seconds changes, since the interruption duration corresponding to the reference question is currently 2 seconds, which does not exceed the first threshold of 3 seconds, the interruption behavior data is not recorded, and the interruption duration corresponding to the reference question is simply reset to zero.

[0082] In an embodiment of the present application, the reference topic is corrected and the correction result is updated.

[0083] In some embodiments, a multi-level search strategy can be used to obtain the correct answer information corresponding to the reference questions. Specifically, the pre-set question bank can contain two types of answer information: full-page answer information organized by page, and single-question answer information organized by question. Each full-page answer information contains the answer information for all questions on the corresponding page.

[0084] The process of obtaining the correct answer information corresponding to the reference question can be carried out in the following steps:

[0085] First, a full-page search is performed, including: identifying the job image captured by the first camera at the current moment, and extracting the page information of the book page where the reference question is located, including but not limited to the page number, chapter number, header / footer information, etc.; based on the page information of the book page where the reference question is located, searching for matching items in the full-page answer information contained in the question bank to obtain the full-page answer information corresponding to the book page. For example, the corresponding full-page answer information can be directly matched by page number based on the index of the page number; based on the question feature information such as the question number or question content corresponding to the reference question, the correct answer information corresponding to the reference question is determined from the full-page answer information.

[0086] If the correct answer information corresponding to the reference question cannot be obtained through the whole-page search, that is, the whole-page search cannot be completed due to objective conditions, for example, the page number, chapter number and other content in the homework image are blocked, resulting in the inability to extract the page information of the page where the reference question is located; or due to the error in matching the whole-page answer information, the correct answer information corresponding to the reference question cannot be found from the whole-page answer information, then a single-question search is performed, including: based on the question feature information such as the question number or question content corresponding to the reference question, searching for matching items in the single-question answer information contained in the question bank to obtain the correct answer information corresponding to the reference question.

[0087] If the correct answer to a reference question still cannot be obtained through single-question search, a large language model can be used to obtain the correct answer. For example, the content of the reference question is input into a pre-trained large language model. The large language model uses its natural language understanding capabilities to understand and analyze the reference question, extracting key information such as the question type, known conditions, and the solution goal. It then uses its knowledge base and reasoning capabilities to generate the correct answer to the reference question.

[0088] In this embodiment, a multi-level search strategy is used to obtain the correct answer information corresponding to the reference questions. Among them, full-page search is given priority to improve the efficiency of obtaining correct answer information; and when the full-page search fails, single-question search is used as a supplement to ensure the robustness of the search; and reasoning based on the large language model is used as the final guarantee to handle complex problems that the first two search methods cannot solve, further improving the versatility and reliability of the system.

[0089] After obtaining the correct answer information corresponding to the reference question, the correct answer information is used to correct the answer traces of the reference question in the homework image captured by the first camera at the current moment, obtaining a correction result and updating the correction result. If the same reference question has been corrected multiple times, updating the correction result means that the last correction result is used as the final correction result for the reference question.

[0090] For example, the grading results include but are not limited to scores, grades, etc.

[0091] In an embodiment of the present application, if the answer trace of a reference question changes, the interruption behavior data corresponding to the reference question is updated based on the current interruption duration corresponding to the reference question, and the reference question is corrected and the correction results are updated. In this way, the interruption behavior data and correction results corresponding to each reference question can be obtained, and based on this data, the user's mastery of the knowledge points of the question can be analyzed in subsequent steps, thereby achieving an accurate and comprehensive assessment of the user's mastery of the knowledge points.

[0092] S104: If no change occurs, the interruption duration corresponding to the reference question is updated. If the updated interruption duration exceeds the set interruption duration, and the number of times the target behavior data appears in the user behavior data does not exceed the set number of times, the mark of the reference question is updated from being answered to completed answering and the answering time is obtained. For the reference question marked as completed answering, the user's mastery of the knowledge points of the reference question is obtained based on the user behavior data, interruption behavior data, correction results and answering time corresponding to the reference question.

[0093] If the answer traces of the reference question have not changed, the interruption duration corresponding to the reference question is updated. In some embodiments, the interruption duration corresponding to the reference question can be accumulated based on the collection time interval between the current moment and the previous moment. For example, the initial value of the interruption duration is set to 0, and the collection time interval is set to 2 seconds. If the answer traces of the reference question in the homework images at the 4th second and the 2nd second have not changed, the interruption duration corresponding to the reference question is accumulated from 0 to 2 seconds; if the answer traces of the reference question in the homework images at the 6th second and the 4th second have not changed, the interruption duration corresponding to the reference question is accumulated from 2 seconds to 4 seconds, and so on.

[0094] In an embodiment of the present application, the target behavior data may be data in the user behavior data that is used to characterize the user's uncertainty about the reference topic.

[0095] For example, the user behavior data may include user expression data, and the target behavior data may be first expression data in the user expression data that satisfies the first determination condition and is used to represent an uncertain emotion. For example, the first expression data may include confusion, bewilderment, hesitation, etc.

[0096] A first determination condition may be pre-set to obtain first expression data that satisfies the first determination condition and is used to characterize uncertain emotions from the user expression data. In some embodiments, the first determination condition may be defined based on the Facial Action Coding System (FACS). For a user expression data, if the user expression data contains a specific action unit AU (Action Units) combination for characterizing uncertain emotions, the user expression data is determined to meet the first determination condition. Exemplarily, the specific AU combination for characterizing uncertain emotions includes but is not limited to AU1 (eyebrow lift) + AU4 (brow frown) + AU7 (eyelid tightening), AU18 (pouting) - AU23 (tightening lips), and the like. It should be noted that the embodiments of the present application do not specifically limit the definition of the first determination condition. In actual applications, the first determination condition may also be defined based on emotion dimensions, intensity scores, key facial features, and the like.

[0097] In an embodiment of the present application, if the updated interruption duration exceeds the set interruption duration, and the number of occurrences of the target behavior data in the user behavior data does not exceed the set number, it indicates that the user has not answered the reference question for a long time, and the user has not repeatedly expressed uncertainty about the reference question, such as the user has not repeatedly expressed confusion, bewilderment, hesitation, etc. In this case, it can be considered that the user has completed answering the reference question, and the reference question mark is updated from answering to completed, and the answering time is obtained.

[0098] In some embodiments, the number of times the target behavior data appears does not exceed the set number may include: the cumulative number of times the target behavior data appears does not exceed the set number, or the number of consecutive times the target behavior data appears does not exceed the set number.

[0099] In some embodiments, the answering time corresponding to the reference question can be obtained based on the current time and the time when the reference question is marked as being answered.

[0100] In an embodiment of the present application, for reference questions marked as completed, the user behavior data, interruption behavior data, correction results and answering time corresponding to the reference questions can be integrated to obtain the user's mastery of the knowledge points of the reference questions.

[0101] For example, the degree of mastery of a knowledge point may be presented in the form of a score or a grade.

[0102] In some embodiments, user behavior data, interruption behavior data, grading results, and answering time can be assigned corresponding weights and a comprehensive score can be calculated. This comprehensive score can be used directly as a quantitative representation of the user's mastery of the reference question knowledge points, or the comprehensive score can be mapped to a specific set knowledge point mastery level.

[0103] Of course, the embodiments of the present application do not specifically limit the method for "deriving the user's mastery of the knowledge points of the reference questions based on the user behavior data, interruption behavior data, correction results, and answering time corresponding to the reference questions." For example, a rule-based method can be used, i.e., a series of rules are set to combine and determine the user's mastery of the knowledge points of the reference questions. Alternatively, a machine learning-based method can be used, i.e., a machine learning classification algorithm, such as a decision tree, random forest, support vector machine, etc., is used to train a model using user behavior data, interruption behavior data, correction results, and answering time as feature inputs to predict the user's mastery of the knowledge points.

[0104] In an embodiment of the present application, the reference question marked as being answered in the homework image captured by the first camera at the current moment is determined; user behavior data is obtained based on the user image captured by the second camera after the reference question is marked as being answered; based on the homework images captured by the first camera at the current moment and the previous moment respectively, it is determined whether the answer trace of the reference question has changed; if it has changed, the interruption behavior data corresponding to the reference question is updated according to the current interruption duration corresponding to the reference question, and the reference question is corrected and the correction result is updated; if it has not changed, the interruption duration corresponding to the reference question is updated. If the updated interruption duration exceeds the set interruption duration, and the number of times the target behavior data appears in the user behavior data does not exceed the set number, the mark of the reference question is updated to completed answering and the answering time is obtained. Finally, based on the user behavior data, interruption behavior data, correction result and answering time corresponding to the reference question, the user's mastery of the knowledge points of the reference question is obtained. By jointly analyzing the homework images captured by the first camera and the user images captured by the second camera, we can obtain data in four different dimensions, namely, user behavior data corresponding to the question, interruption behavior data, correction results, and answering time. By integrating the data from the above four dimensions, we can obtain the user's mastery of the knowledge points corresponding to the question, thereby more comprehensively reflecting the user's actual mastery of the knowledge points and improving the comprehensiveness and accuracy of the knowledge point mastery assessment.

[0105] like Figure 2 As shown, Figure 2 This is a flowchart of a method for recommending question-and-answer content provided in an embodiment of the present application.

[0106] S201: If the updated interruption duration exceeds the set interruption duration, and the number of times the target behavior data appears in the user behavior data exceeds the set number of times, the mark of the reference question is updated from being answered to not being answered, wherein the target behavior data includes first expression data that meets the first judgment condition and is used to represent uncertainty emotions.

[0107] In an embodiment of the present application, the target behavior data may be data in the user behavior data that is used to characterize the user's uncertainty about the reference topic.

[0108] For example, the user behavior data may include user expression data, and the target behavior data may be first expression data in the user expression data that satisfies the first determination condition and is used to represent an uncertain emotion. For example, the first expression data may include confusion, bewilderment, hesitation, etc.

[0109] If the updated interruption duration exceeds the set interruption duration, and the target behavior data appears more than the set number of times in the user's behavior data, it indicates that the user has not answered the reference question for a long time and the user has repeatedly expressed uncertainty about the reference question, such as repeatedly showing confusion, bewilderment, hesitation, etc. In this case, it can be assumed that the user will not answer the reference question, and the reference question's flag will be updated from answering to not answering.

[0110] S202: For the reference questions marked as unanswerable, recommending to the user the answer content of the reference questions and / or other questions with relevant knowledge points to the reference questions.

[0111] Exemplarily, a question bank is pre-set, which not only stores questions, knowledge points, and question-answering content, but also establishes a relationship between the three. Other questions with knowledge points related to the reference questions include questions in the question bank that have the same knowledge points as the reference questions and / or questions that involve knowledge points that are a subset of the knowledge points involved in the reference questions.

[0112] For example, the Q&A content includes but is not limited to basic Q&A information, such as standard answers to questions, detailed problem-solving steps, analysis of relevant knowledge points, etc.; multimedia explanation resources, such as graphic and text explanation materials, video analysis tutorials, interactive demonstration animations, etc.

[0113] In some embodiments, after a reference question is marked as not being answered, the reference question and / or other questions with knowledge points related to the reference question can be displayed on one side of the display screen of the electronic device, and the user can select any of the displayed questions. When the user's selection operation is detected, the question and answer content corresponding to the selected question is obtained from the question bank in response to this selection operation and displayed to the user.

[0114] For example, the user may select any displayed question by clicking, touching, or other interactive methods, which is not specifically limited in the embodiments of the present application.

[0115] In this embodiment, if the updated interruption duration exceeds the set interruption duration, and the number of times the target behavior data appears in the user behavior data exceeds the set number of times, the mark of the reference question will be updated from being answered to not being answered, and for the reference questions marked as not being answered, the user will be recommended the answer content of the reference questions and / or other questions with relevant knowledge points to the reference questions, so as to accurately identify the difficulties and obstacles encountered by the user in the answering process, and make personalized recommendations for the questions that the user does not know how to answer, so as to help the user solve the doubts in the answering process in a timely manner, deepen the understanding and mastery of the knowledge points, thereby enhancing the learning effect and improving the learning efficiency.

[0116] like Figure 3 As shown, Figure 3 This is a flow chart of optimizing the correction results provided by an embodiment of the present application.

[0117] S301: For a reference question marked as completed, display the correction result of the reference question, control the second camera to capture the user image during the display of the correction result, and obtain user expression data related to the correction result based on the user image during the display of the correction result.

[0118] After the mark of the reference question is updated from being answered to completed, the correction result of the reference question can be displayed on the display screen of the electronic device. The display time of the correction result can be flexibly adjusted according to the difficulty of the reference question, user settings or system default values.

[0119] During the display of the correction result, the second camera is controlled to capture the user image, and the user image obtained during the display of the correction result is recognized to obtain the user expression data during the process of the user viewing the correction result.

[0120] S302: If the user expression data contains any of the following expression data: first expression data for representing uncertainty emotions that meets the first judgment condition, and second expression data for representing negative emotions that meets the second judgment condition, then adjust the correction strategy to re-correct the reference question to obtain a secondary correction result.

[0121] It is determined whether there is first expression data for representing uncertainty emotions that meets a first determination condition in the user expression data related to the correction result. For example, the first expression data includes but is not limited to expressions such as doubt and frowning that can represent the user's uncertainty emotions.

[0122] In some embodiments, a first determination condition is pre-set, and the first determination condition can be defined based on FACS. For user expression data related to a correction result, if the user expression data contains a specific AU combination used to represent an undefined emotion, the user expression data is determined to meet the first determination condition. Exemplary specific AU combinations used to represent undefined emotions include, but are not limited to, AU1+AU4+AU7, AU18-AU23, and so on.

[0123] It is determined whether there is second expression data that satisfies a second determination condition and is used to represent a negative emotion in the user expression data related to the correction result. For example, the second expression data includes but is not limited to expressions that can represent the user's negative emotion, such as anger and rage.

[0124] In some embodiments, a second judgment condition is pre-set, and the second judgment condition can be defined based on FACS. For a piece of user expression data related to a correction result, if the user expression data contains a specific AU combination used to represent negative emotions, then the user expression data is determined to meet the second judgment condition. Exemplary specific AU combinations used to represent negative emotions include but are not limited to AU4+AU7+AU23, AU9 (nose wrinkled)+AU10 (upper lip raised)+AU17 (lower lip raised), etc.

[0125] It should be noted that the embodiments of the present application do not specifically limit the definition method of the first / second judgment conditions. In actual applications, the first / second judgment conditions can also be defined based on emotional dimensions, intensity scores, key facial features, etc.

[0126] If the user's facial expression data associated with the grading result contains either the first or second facial expression data, it is considered that the user has objections to the grading result of the currently displayed reference question, and the grading result may contain significant errors. In this case, the grading strategy is adjusted, and the reference question is re-graded based on the adjusted grading strategy to obtain a second grading result.

[0127] S303: If the difference between the second grading result and the grading result exceeds a second threshold, the second grading result is used as the final grading result of the reference question and the final grading result is displayed.

[0128] The original grading result is compared with the obtained second grading result. If the difference between the original grading result and the second grading result does not exceed the set second threshold, it is considered that the user's expression of doubt or anger at this time may be due to other non-grading factors, and no correction is made to the original grading result. If the difference between the original grading result and the second grading result exceeds the second threshold, it is considered that there is a deviation in the original grading result, and the obtained second grading result is used as the final grading result of the reference question and displayed.

[0129] In this embodiment, by capturing users' facial expressions in response to grading results, especially identifying uncertainty or negative emotions, we achieve grading result optimization based on user expressions. This allows for timely detection and correction of potential grading errors, effectively reducing the misjudgment rate and improving the accuracy and reliability of grading results.

[0130] like Figure 4 As shown, Figure 4 This is a flowchart of calculating the degree of mastery of knowledge points provided in an embodiment of the present application.

[0131] S401: Calculate a first score based on the user behavior data corresponding to the reference topic, where the first score is used to characterize the frequency of occurrence of specified expression data in the user behavior data, where the specified expression data includes first expression data that meets a first judgment condition and is used to characterize uncertain emotions and / or second expression data that meets a second judgment condition and is used to characterize negative emotions.

[0132] For a detailed description of the first expression data satisfying the first determination condition and used to represent uncertain emotions, and the second expression data satisfying the second determination condition and used to represent negative emotions, please refer to the above text and will not be repeated here.

[0133] In some embodiments, the user behavior data includes at least user expression data, and the user expression data can be traversed to filter out specified expression data from the user expression data, including first expression data that meets the first judgment condition and is used to represent uncertain emotions and / or second expression data that meets the second judgment condition and is used to represent negative emotions. The number of occurrences of the specified expression data is counted, and a first score is obtained based on the number of occurrences of the specified expression data and the total number of user expression data. Exemplarily, the first score = number of occurrences of the specified expression data / total number of user expression data. The higher the first score, the higher the frequency of occurrence of the specified expression data in the user behavior data.

[0134] Of course, the intensity, duration, etc. of the specified expression data may also be considered when calculating the first score. The embodiments of the present application do not specifically limit the method of "calculating the first score based on the user behavior data corresponding to the reference topic."

[0135] S402: Calculate a second score based on the interruption behavior data corresponding to the reference question, where the second score is used to characterize the intensity of the interruption behavior during the process of answering the reference question.

[0136] In some embodiments, the interruption behavior data includes the number of occurrences of the question-answering interruption behavior and the duration of each question-answering interruption behavior. Based on the number of occurrences of the question-answering interruption behavior, the number of question-answering interruption behaviors that occur per unit time can be calculated to measure the frequency of the question-answering interruption behavior. At the same time, the total duration of all question-answering interruptions can be accumulated or the average duration of the question-answering interruptions can be calculated to measure the severity of the question-answering interruption behavior. A weighted or normalized method can be used to integrate the above two data into a composite parameter, namely the second score, to reflect the intensity of the question-answering interruption behavior. The higher the second score, the higher the intensity of the question-answering interruption behavior in the process of answering the reference question.

[0137] Of course, in addition to the number of interruptions and the duration of each interruption, other interruption behavior data, such as those listed above, can also be considered. Furthermore, methods such as machine learning and time series analysis can also be used to calculate the second score. The embodiments of this application do not specifically limit the method of "calculating the second score based on the interruption behavior data corresponding to the reference question."

[0138] S403: Calculating a third score according to the correction result of the reference question, wherein the third score is used to represent the degree of deviation between the correction result and the set correction result.

[0139] A set grading result is a pre-set benchmark used to evaluate a user's performance. This can be defined in a variety of ways, depending on the assessment objective. For example, when the grading result is presented as a score, the set grading result could be a full score, or a passing score based on expert opinion or pre-set rules, such as a minimum score required to assess mastery of core knowledge points.

[0140] The embodiments of the present application do not specifically limit the method of "calculating the third score based on the correction results of the reference questions". The difference between the set correction results and the correction results of the reference questions can be directly used as the third score; or, a probability distribution can be introduced to quantify the degree of deviation by comparing the probability distributions, such as regarding the set correction results as the expected distribution, and the actual correction results of the reference questions as the observed distribution, calculating the distance metric (such as Euclidean distance, Chebyshev distance, etc.) or divergence metric (such as Kullback-Leible divergence, Jensen-Shannon divergence, etc.) between the two, and converting the obtained distance or divergence value into the third score, and so on. The higher the third score, the greater the degree of deviation between the correction results of the reference questions and the set correction results.

[0141] S404: Calculate a fourth score based on the answering time of the reference question, where the fourth score is used to represent the extent to which the answering time exceeds the set answering time.

[0142] Setting a time limit for answering a question refers to a pre-set benchmark reference value used to evaluate the efficiency of a user's answering. Setting a time limit for answering a question can be determined based on a variety of factors. For example, setting a time limit for answering a question can be based on the characteristics of the question itself (such as the difficulty of the question, the coverage of knowledge points, etc.), or based on historical large-scale answer data, etc.

[0143] In some embodiments, the ratio of the difference between the answering time of the reference question and the set answering time to the set answering time can be directly used as the fourth score.

[0144] Of course, you can also set a tolerance interval and calculate the fourth score based on the portion of the answering time that exceeds the tolerance interval; or divide the timeout into multiple intervals and weight them differently to calculate the fourth score. The embodiments of this application do not specifically limit the method of "calculating the fourth score based on the answering time of the reference question."

[0145] S405: Obtaining the user's mastery of the knowledge points of the reference question based on the first score, the second score, the third score, the fourth score, and the weight coefficients corresponding to the scores.

[0146] The first score, the second score, the third score, and the fourth score are assigned corresponding weight coefficients w1, w2, w3, and w4, respectively. The weight coefficients can be determined based on expert experience, historical data analysis, or a machine learning model.

[0147] The final weighted value (S) is obtained based on the first score, the second score, the third score, the fourth score, and the weight coefficients corresponding to each score. For example, the final weighted value S = w1·first score + w2·second score + w31·third score + w4·fourth score.

[0148] The final weighted value S is negatively correlated with the user's mastery of the reference question knowledge points. The larger the S value, the lower the user's mastery of the reference question knowledge points. The smaller the S value, the higher the user's mastery of the reference question knowledge points.

[0149] For example, the degree of mastery of a knowledge point may be presented in the form of a score or a grade.

[0150] If the degree of mastery of a knowledge point is presented in the form of a score, the S value can be mapped into a knowledge point mastery score based on a percentage system through linear conversion. The closer the knowledge point mastery score is to 100, the higher the degree of mastery of the knowledge point.

[0151] If the mastery of a knowledge point is expressed in a graded form, the S value can be divided into discrete levels of mastery using a preset threshold interval. For example, the mastery levels of a knowledge point include: proficient, S∈[0,0.2); average, S∈[0.2,0.5); and unproficient, S≧0.5.

[0152] In this embodiment, by calculating the scores corresponding to the four dimensions of data, namely user behavior data, interruption behavior data, correction results and answering time, and performing multi-dimensional data fusion based on preset weight coefficients, the user's mastery of the knowledge points of the question is finally generated. This can more comprehensively reflect the user's actual mastery of the knowledge points and improve the comprehensiveness and accuracy of the knowledge point mastery assessment.

[0153] In some embodiments, after obtaining the user's mastery of the knowledge points of the reference question, it also includes: if the user's mastery of the knowledge points of the reference question is in a first set range, recommending at least one first question to the user, and the knowledge points involved in the first question are a subset of the knowledge points involved in the reference question; if the user's mastery of the knowledge points of the reference question is in a second set range, recommending at least one second question to the user, and the knowledge points involved in the second question are the same as the reference question; if the user's mastery of the knowledge points of the reference question is in a third set range, recommending at least one third question to the user, and the number of knowledge points involved in the third question or the difficulty coefficient of the knowledge points exceeds that of the reference question.

[0154] It should be noted that the mastery level of knowledge points corresponding to the third setting interval is higher than that of the second setting interval, and the mastery level of knowledge points corresponding to the second setting interval is higher than that of the first setting interval.

[0155] Exemplarily, the degree of mastery of a knowledge point can be presented in the form of a score or a grade. If the degree of mastery of a knowledge point is presented in the form of a score, the first setting interval, the second setting interval, and the third setting interval can be defined as a score interval, for example, the first setting interval (0-60 points), the second setting interval (60-85 points), and the third setting interval (85-100 points). If the degree of mastery of a knowledge point is presented in the form of a grade, each setting interval can be defined as a corresponding level of mastery of the knowledge point, for example, the first setting interval (unskilled), the second setting interval (general), and the third setting interval (skilled).

[0156] The knowledge points covered in the first question are a subset of the knowledge points covered in the reference question. A subset of knowledge points means that the set of knowledge points covered in the question is a proper subset of the set of knowledge points in the reference question, meaning that all the knowledge points contained in the former belong to the latter and the number of elements is strictly less than that in the latter. For example, if the reference question covers knowledge points A, B, and C, then the first question includes questions covering knowledge points A, B, C, A and B, A and C, or B and C.

[0157] The second question involves the same knowledge points as the reference question. The same refers to the same number and content of the knowledge points. For example, if the reference question involves knowledge points A, B, and C, then the second question includes questions involving knowledge points A, B, and C.

[0158] The third question involves more knowledge points or a higher difficulty coefficient than the reference question. For example, the third question includes a question with one more knowledge point or one more difficulty coefficient than the reference question, that is, a question that is slightly more difficult than the reference question.

[0159] In this embodiment, by recommending questions of different difficulty levels based on the user's mastery of the knowledge points of the reference questions, it is possible to provide users with personalized learning content recommendations that are adapted to the current user's understanding level, thereby improving the user's learning efficiency, helping users better consolidate knowledge points, and optimizing the learning experience.

[0160] The above content describes the method provided by this application. The following describes the device provided by this application:

[0161] See Figure 5 , is a structural diagram of a knowledge point mastery level assessment device provided in an embodiment of the present application.

[0162] like Figure 5 As shown, the device may include:

[0163] The determining unit 510 is configured to determine a reference question marked as being answered in the homework image captured by the first camera at the current moment;

[0164] The judgment unit 520 is configured to obtain, for each reference question, user behavior data corresponding to the reference question based on user images captured by the second camera after the reference question is marked as being answered, and to determine whether there has been a change in the answer trace for the reference question based on the work images captured by the first camera at the current moment and the previous moment;

[0165] The first processing unit 530 is configured to update the interruption behavior data corresponding to the reference question according to the current interruption duration corresponding to the reference question, and to correct the reference question and update the correction result if a change occurs; wherein the interruption duration is used to represent the length of time the reference question is interrupted during the answering process;

[0166] The second processing unit 540 is used to update the interruption duration corresponding to the reference question if there is no change. If the updated interruption duration exceeds the set interruption duration and the number of times the target behavior data appears in the user behavior data does not exceed the set number of times, the mark of the reference question is updated from being answered to completed answering and the answering time is obtained. For the reference question marked as completed answering, the user's mastery of the knowledge points of the reference question is obtained based on the user behavior data, interruption behavior data, correction results and answering time corresponding to the reference question.

[0167] Optionally, the second processing unit 540 is further configured to:

[0168] If the updated interruption duration exceeds the set interruption duration, and the number of occurrences of the target behavior data in the user behavior data exceeds the set number of occurrences, updating the flag of the reference question from "being answered" to "not answering", wherein the target behavior data includes first expression data that satisfies the first determination condition and is used to represent an emotion of uncertainty;

[0169] For the reference questions marked as unanswerable, the answer contents of the reference questions and / or other questions with relevant knowledge points to the reference questions are recommended to the user.

[0170] Optionally, the interruption behavior data includes the number of occurrences of the interruption behavior in answering questions and the duration of each interruption behavior in answering questions;

[0171] The first processing unit 530 is specifically configured to:

[0172] If the interruption duration currently corresponding to the reference question exceeds the first threshold, a question-answering interruption behavior is recorded, and after the duration of this question-answering interruption behavior is obtained based on the interruption duration, the interruption duration is reset to zero.

[0173] Optionally, the device further includes an optimization unit, wherein the optimization unit is specifically configured to:

[0174] For a reference question marked as completed, display the correction result of the reference question, control the second camera to capture a user image during the display of the correction result, and obtain user expression data related to the correction result based on the user image during the display of the correction result;

[0175] If the user expression data includes any of the following expression data: first expression data for representing uncertainty emotions that meets the first determination condition, and second expression data for representing negative emotions that meets the second determination condition, then adjusting the grading strategy to re-grade the reference question to obtain a secondary grading result;

[0176] If the difference between the second grading result and the grading result exceeds a second threshold, the second grading result is used as the final grading result of the reference question and the final grading result is displayed.

[0177] Optionally, the second processing unit 540 is specifically configured to:

[0178] Calculating a first score based on the user behavior data corresponding to the reference question, the first score being used to represent the frequency of occurrence of specified expression data in the user behavior data, the specified expression data including first expression data for representing an uncertain emotion that meets a first determination condition and / or second expression data for representing a negative emotion that meets a second determination condition;

[0179] Calculating a second score based on the interruption behavior data corresponding to the reference question, wherein the second score is used to characterize the intensity of the interruption behavior during the answering process of the reference question;

[0180] Calculating a third score based on the correction result of the reference question, wherein the third score is used to represent the degree of deviation between the correction result and the set correction result;

[0181] Calculating a fourth score based on the answering time of the reference question, the fourth score being used to indicate the extent to which the answering time exceeds the set answering time;

[0182] The user's mastery of the knowledge points of the reference question is obtained based on the first score, the second score, the third score, the fourth score, and the weight coefficients corresponding to the scores.

[0183] Optionally, the device further includes a recommendation unit, wherein the recommendation unit is specifically configured to:

[0184] If the user's mastery of the knowledge points of the reference question is within a first set range, recommending at least one first question to the user, where the knowledge points involved in the first question are a subset of the knowledge points involved in the reference question;

[0185] If the user's mastery of the knowledge points of the reference question is within a second set range, recommending at least one second question to the user, where the second question involves the same knowledge points as the reference question;

[0186] If the user's mastery of the knowledge points of the reference question is within a third set range, at least one third question is recommended to the user, and the number of knowledge points or the difficulty coefficient of the knowledge points involved in the third question exceeds that of the reference question.

[0187] Optionally, the device further includes a marking unit, wherein the marking unit is specifically configured to:

[0188] For a question for which there is no marked mark in the homework image captured by the first camera at the current moment, if there is no trace of answering the question in the homework image captured at the previous moment, and there is trace of answering the question in the homework image captured at the current moment, the question will be marked as being answered.

[0189] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0190] The embodiment of the present application also provides a hardware structure. Figure 6 , Figure 6 This is a structural diagram of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the hardware structure may include: a processor and a machine-readable storage medium, the machine-readable storage medium storing machine-executable instructions that can be executed by the processor; the processor is used to execute the machine-executable instructions to implement the method disclosed in the above example of this application.

[0191] Based on the same application concept as the above method, an embodiment of the present application also provides a machine-readable storage medium, on which a number of computer instructions are stored. When the computer instructions are executed by a processor, the method disclosed in the above example of the present application can be implemented.

[0192] Exemplarily, the machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that may contain or store information, such as executable instructions, data, and the like. For example, the machine-readable storage medium may be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, a storage drive (such as a hard disk drive), a solid-state drive, any type of storage disk (such as a CD, DVD, etc.), or similar storage media, or a combination thereof.

[0193] It should be noted that, in this document, relational terms such as target and objective are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0194] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for evaluating the degree of mastery of knowledge points, characterized in that: Applied to an electronic device equipped with a first camera and a second camera, the method includes: Determining a reference question marked as being answered in the homework image captured by the first camera at the current moment; For each reference question, obtaining user behavior data corresponding to the reference question based on user images captured by the second camera after the reference question is marked as being answered, and determining whether there has been a change in the answer traces for the reference question based on the work images captured by the first camera at the current moment and the previous moment; If there is a change, the interruption behavior data corresponding to the reference question is updated according to the current interruption duration corresponding to the reference question, and the reference question is corrected and the correction result is updated; wherein the interruption duration is used to represent the length of time the reference question is interrupted during the answering process; If there is no change, the interruption time corresponding to the reference question is updated. If the updated interruption time exceeds the set interruption time, and the number of times the target behavior data appears in the user behavior data does not exceed the set number of times, the mark of the reference question is updated from answering to completed answering and the answering time is obtained. For the reference question marked as completed answering, the user's mastery of the knowledge points of the reference question is obtained based on the user behavior data, interruption behavior data, correction results and answering time corresponding to the reference question.

2. The method according to claim 1, characterized in that The method further comprises: If the updated interruption duration exceeds the set interruption duration, and the number of occurrences of the target behavior data in the user behavior data exceeds the set number of occurrences, updating the flag of the reference question from "being answered" to "not answering", wherein the target behavior data includes first expression data that satisfies the first determination condition and is used to represent an emotion of uncertainty; For the reference questions marked as unanswerable, the answer contents of the reference questions and / or other questions with relevant knowledge points to the reference questions are recommended to the user.

3. The method according to claim 1, characterized in that The interruption behavior data includes the number of occurrences of the interruption behavior and the duration of each interruption behavior; Updating the interruption behavior data corresponding to the reference topic according to the current interruption duration corresponding to the reference topic, including: If the interruption duration currently corresponding to the reference question exceeds the first threshold, a question-answering interruption behavior is recorded, and after the duration of this question-answering interruption behavior is obtained based on the interruption duration, the interruption duration is reset to zero.

4. The method according to claim 1, wherein The method further comprises: For a reference question marked as completed, display the correction result of the reference question, control the second camera to capture a user image during the display of the correction result, and obtain user expression data related to the correction result based on the user image during the display of the correction result; If the user expression data includes any of the following expression data: first expression data for representing uncertainty emotions that meets the first determination condition, and second expression data for representing negative emotions that meets the second determination condition, then adjusting the grading strategy to re-grade the reference question to obtain a secondary grading result; If the difference between the second grading result and the grading result exceeds a second threshold, the second grading result is used as the final grading result of the reference question and the final grading result is displayed.

5. The method according to claim 1, wherein The user's mastery of the knowledge points of the reference question is obtained based on the user behavior data, interruption behavior data, correction results, and answering time corresponding to the reference question, including: Calculating a first score based on the user behavior data corresponding to the reference question, the first score being used to represent the frequency of occurrence of specified expression data in the user behavior data, the specified expression data including first expression data for representing an uncertain emotion that meets a first determination condition and / or second expression data for representing a negative emotion that meets a second determination condition; Calculating a second score based on the interruption behavior data corresponding to the reference question, wherein the second score is used to characterize the intensity of the interruption behavior during the answering process of the reference question; Calculating a third score based on the correction result of the reference question, wherein the third score is used to represent the degree of deviation between the correction result and the set correction result; Calculating a fourth score based on the answering time of the reference question, the fourth score being used to indicate the extent to which the answering time exceeds the set answering time; The user's mastery of the knowledge points of the reference question is obtained based on the first score, the second score, the third score, the fourth score, and the weight coefficients corresponding to the scores.

6. The method according to claim 1 or 5, characterized in that After obtaining the user's mastery of the knowledge points of the reference question, the method further includes: If the user's mastery of the knowledge points of the reference question is within a first set range, recommending at least one first question to the user, where the knowledge points involved in the first question are a subset of the knowledge points involved in the reference question; If the user's mastery of the knowledge points of the reference question is within a second set range, recommending at least one second question to the user, where the second question involves the same knowledge points as the reference question; If the user's mastery of the knowledge points of the reference question is within a third set range, at least one third question is recommended to the user, and the number of knowledge points or the difficulty coefficient of the knowledge points involved in the third question exceeds that of the reference question.

7. The method according to claim 1, characterized in that The method further comprises: For a question for which there is no marked mark in the homework image captured by the first camera at the current moment, if there is no trace of answering the question in the homework image captured at the previous moment, and there is trace of answering the question in the homework image captured at the current moment, the question will be marked as being answered.

8. A knowledge point mastery evaluation device, characterized in that: Applicable to an electronic device equipped with a first camera and a second camera, the device includes: a determining unit, configured to determine a reference question marked as being answered in the homework image captured by the first camera at a current moment; a judgment unit configured to, for each reference question, obtain user behavior data corresponding to the reference question based on user images captured by the second camera after the reference question is marked as being answered, and to judge whether there has been a change in the answer trace of the reference question based on the work images captured by the first camera at the current moment and the previous moment; A first processing unit is configured to update the interruption behavior data corresponding to the reference question according to the interruption duration currently corresponding to the reference question, and to correct the reference question and update the correction result if a change occurs; wherein the interruption duration is used to represent the duration of the interruption in the process of answering the reference question; The second processing unit is used to update the interruption duration corresponding to the reference question if there is no change. If the updated interruption duration exceeds the set interruption duration and the number of times the target behavior data appears in the user behavior data does not exceed the set number of times, the mark of the reference question is updated from being answered to completed answering and the answering time is obtained. For the reference question marked as completed answering, the user's mastery of the knowledge points of the reference question is obtained based on the user behavior data, interruption behavior data, correction results and answering time corresponding to the reference question.

9. An electronic device, characterized in that: The system comprises a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor is configured to execute the machine-executable instructions to implement the method according to any one of claims 1 to 7.

10. A machine-readable storage medium, characterized in that The machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images