Education-based common error question image generation method

Abstract

The application discloses an education-based common error question image generation method. It relates to the technical field of image processing. The education-based common error question image generation method comprises the following steps: screening common error questions for educating students from an error question set according to a teacher's question selection requirement, wherein the common error questions are used to indicate error questions selected by multiple students; generating a text image of the common error questions; performing fusion processing on the text image and an identification image used for identifying the error questions to generate a common error question image; and displaying the common error question image to an expected arrangement object of the teacher.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to an education-based common error question image generation method. BACKGROUND

[0002] In the modern education system, error question management is a crucial link, which not only helps students identify and fill in the weak links in the learning process, but also assists teachers in accurately positioning teaching difficulties and optimizing teaching strategies. However, the traditional method is particularly cumbersome and inefficient in dealing with this task. For a long time, the sorting of error questions mainly relies on manual operation, and teachers need to manually select and record error questions in each homework, test or examination. This method not only consumes time and effort, but also is prone to omissions or misjudgments.

[0003] Although the traditional error question management system attempts to introduce technical means to simplify the process, it still faces many challenges in the key image generation link. These systems often take the form of directly converting error questions into static images, which lack flexibility and interactivity. Once a particular error question needs to be highlighted or modified, it must be traced back to the original file for reprocessing, which not only increases the additional workload, but also may lead to resource waste. At the same time, this single image generation mode is highly dependent on powerful computing power and storage space, which is costly for schools or educational institutions in the long run, and is difficult to adapt to rapidly changing teaching needs.

[0004] In view of the technical problems in the prior art that generating static error question images results in high cost, resource waste and high limitation, no effective solutions have been proposed so far. SUMMARY

[0005] The embodiments of the present application provide an education-based common error question image generation method to at least solve the technical problems in the prior art that generating static error question images results in high cost, resource waste and high limitation.

[0006] According to one aspect of an embodiment of the present application, an education-based common error question image generation method is provided, comprising: selecting common error questions for educating students from an error question set according to teacher selection requirements, wherein the common error questions are used to indicate error questions selected by multiple students; generating a text image of the common error questions; performing fusion processing on the text image and an identification image used to identify the error questions to generate a common error question image; and displaying the common error question image to a teacher's expected arrangement object.

[0007] According to another aspect of the embodiments of the present application, a computer device is also provided, which includes a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above method.

[0008] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0009] According to another aspect of the embodiments of the present application, a computer program product is also provided, which includes a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0010] According to another aspect of the embodiments of the present application, an education-based common mistake image generation device is also provided, which includes: a mistake recommendation module, configured to filter common mistakes for educating students from a mistake set according to a teacher's topic selection requirement, wherein the common mistakes are used to indicate mistakes selected by multiple students; a first image production module, configured to generate a text image of the common mistakes; a second image generation module, configured to perform fusion processing on the text image and an identification image used to identify the mistakes, to generate a common mistake image; and a mistake sending module, configured to display the common mistake image to an expected arrangement object of the teacher.

[0011] According to another aspect of the embodiments of the present application, an education-based common mistake image generation device is also provided, which includes: a processor; and a memory connected with the processor, configured to provide the processor with instructions for processing the following processing steps: filtering common mistakes for educating students from a mistake set according to a teacher's topic selection requirement, wherein the common mistakes are used to indicate mistakes selected by multiple students; generating a text image of the common mistakes; performing fusion processing on the text image and an identification image used to identify the mistakes, to generate a common mistake image; and displaying the common mistake image to an expected arrangement object of the teacher.

[0012] In the embodiments of the present application, first, by generating the common mistakes into a text image, the understanding obstacle possibly caused by pure text information is overcome, especially when facing low-grade students or non-native learners, the image presentation method is easier to understand and remember. Second, the technical solution converts the filtered common mistakes into high-definition text images. Unlike the traditional one-time static image generation, the present solution adopts a layered processing technology to separate the mistake content and the annotation information, and generates a basic text image and a dynamic identification image respectively. The system also allows the teacher to adjust the annotation content or add new annotations at any time without the need to rebuild the entire image, greatly improving the immediacy and flexibility of teaching interaction, avoiding resource waste, and reducing the limitations of image generation. BRIEF DESCRIPTION OF DRAWINGS

[0013] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0014] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to Embodiment 1 of the application;

[0015] Figure 2 is a schematic diagram of an image generation system according to Embodiment 1 of the application;

[0016] Figure 3 is a flowchart of an education-based common mistake image generation method according to the first aspect of Embodiment 1 of the application;

[0017] Figure 4 is an application interface diagram according to Embodiment 1 of the application regarding teacher topic selection requirements;

[0018] Figure 5 is a schematic diagram of a common mistake image according to Embodiment 1 of the application;

[0019] Figure 6A is an application interface diagram according to Embodiment 1 of the application regarding a knowledge point tree;

[0020] Figure 6B is an application interface diagram according to Embodiment 1 of the application regarding a homework tree;

[0021] Figure 7 is an application interface diagram according to Embodiment 1 of the application regarding a variant question;

[0022] Figure 8 is a schematic diagram of an education-based common mistake image generation device according to Embodiment 2 of the application; and

[0023] Figure 9 is a schematic diagram of an education-based common mistake image generation device according to Embodiment 3 of the application. DETAILED DESCRIPTION

[0024] In order to enable persons skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] Embodiment 1

[0027] According to the present embodiment, a method embodiment of an education-based common mistake image generation method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0028] The method embodiment provided by the present embodiment can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Figure 1 A hardware structure block diagram of a computing device for implementing an education-based common mistake image generation method is shown. As shown in Figure 1 , the computing device can include one or more processors (the processor can include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, and a transmission device for communication functions. In addition, it can also include a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which can be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, which does not limit the structure of the above-mentioned electronic device. For example, the computing device can also include more or fewer components than those shown in Figure 1 , or have a different configuration than Figure 1 .

[0029] It should be noted that the one or more processors and / or other data processing circuitry described above can be referred to herein generically as "data processing circuitry." The data processing circuitry can be embodied as software, hardware, firmware, or any combination thereof, in whole or in part. Moreover, the data processing circuitry can be a single standalone processing module, or incorporated in whole or in part within any one of other elements of the computing device. As referred to in the embodiments of the present application, the data processing circuitry serves as a processor to control, for example, the selection of the variable resistance terminal path connected to the interface.

[0030] The memory can be used to store software programs of application software and modules, such as program instructions / data storage means corresponding to the education-based common error question image generation method of the application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implements the education-based common error question image generation method of the application program described above. The memory can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory can further include a memory remotely arranged with respect to the processor, which can be connected to the computing device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0031] The transmission device is used to receive or send data via a network. Specific examples of the above-mentioned network can include a wireless network provided by a communication provider of the computing device. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet in a wireless manner.

[0032] The display can be, for example, a touch screen type liquid crystal display (LCD), which can enable a user to interact with the user interface of the computing device.

[0033] It should be noted that in some optional embodiments, the above-mentioned Figure 1 The computing device shown can include hardware elements (including circuitry), software elements (including computer code stored on a computer readable medium), or combinations of both hardware and software elements. It should be noted that Figure 1 is merely one example of a particular implementation and is intended to provide an example of the types of components that can be present in the computing device described above.

[0034] Figure 2This is a schematic diagram of the image generation system according to this embodiment. (Refer to...) Figure 2 As shown, the system includes: an image fusion module 110, an identifier addition module 120, a wrong question collection module 130, a wrong question recommendation module 140, and a wrong question distribution module 150.

[0035] The image fusion module 110 is used to fuse the text image generated based on common mistakes with the identification image to generate a common mistake image.

[0036] The labeling module 120 is used to add labels at the corresponding positions of common incorrect questions and generate label images.

[0037] The error collection module 130 is used to collect students' incorrect answers.

[0038] The "Incorrect Question Recommendation Module 140" is used to recommend incorrect questions to teachers based on their question selection requirements.

[0039] The error distribution module 150 is used to distribute images of common errors recommended by teachers to designated students.

[0040] It should be noted that the image fusion module 110, the identifier addition module 120, the incorrect question collection module 130, the incorrect question recommendation module 140, and the incorrect question distribution module 150 in the system can all be adapted to the hardware structure described above.

[0041] Under the aforementioned operating environment, according to the first aspect of this embodiment, a method for generating images of common incorrect questions in education is provided. This method consists of... Figure 2 The image generation system shown is implemented. Figure 3 A flowchart illustrating the method is shown below. (Refer to...) Figure 3 As shown, the method includes:

[0042] S302: Select common incorrect questions from the incorrect question collection for use in educating students, according to the teacher's question selection requirements. Common incorrect questions are used to indicate incorrect questions jointly selected by multiple students.

[0043] S304: Generate text images of common incorrect answers;

[0044] S306: Fuse the text image with the identification image used to identify incorrect questions to generate a common incorrect question image; and

[0045] S308: Show images of common incorrect questions to the students who are expected to be assigned tasks by the teacher.

[0046] Specifically, the students answer the test papers and generate the answer results. Then the teachers correct the answer results of the test papers and generate the correction results. Then the staffs input the answer results of the test papers and the corresponding correction results into the wrong question collection module 130. Further, the wrong question collection module 130 determines the wrong questions in the corresponding test papers according to the correction results and generates the wrong question set.

[0047] Further, the teachers enter the system for recommending wrong questions for teachers through an application program on a terminal device. The application program is the front end of the system for recommending wrong questions for teachers. The teachers select from the preset elements corresponding to the teacher's selection requirements on the application program interface, so as to determine the selected teacher's selection requirements. The preset elements corresponding to the teacher's selection requirements include knowledge points, homework, specific time ranges, classes, class stratifications, students, the number of answerers and scores of grades, question types, and wrong reasons. And the teacher's selection requirements are one or more specific preset elements selected from the preset elements.

[0048] Wherein Figure 4 The interface of the application program is shown. Referring to Figure 4 As shown, for example, the teacher selects "Grade 2 Class 02 / Excellent", "Nearly a year", "Single-choice question", and "All wrong reasons" in the option boxes corresponding to the preset elements.

[0049] Thus, the teacher's selection requirements determined are:

[0050] (1) Specific time range: nearly a year;

[0051] (2) Class: Grade 2 Class 02;

[0052] (3) Class stratification: excellent;

[0053] (4) Question type: single-choice question;

[0054] (5) Wrong reason: all wrong reasons.

[0055] Further, the wrong question recommendation module 140 obtains the teacher's selection requirements selected by the teacher on the application program interface, and screens the corresponding common wrong questions from the wrong question set according to the teacher's selection requirements. And the common wrong questions are used to indicate the wrong questions commonly selected by multiple students. Then the wrong question recommendation module 140 sends the screened common wrong questions to the image fusion module 110. The common wrong questions are texts.

[0056] Further, after receiving the common incorrect question, the image fusion module 110 processes it to generate a corresponding image (i.e., a text image). Then, the labeling module 120 generates a corresponding label image for labeling the incorrect question. The image fusion module 110 then fuses the text image and the label image to generate a common incorrect question image that includes both the incorrect question and the label. Finally, the image fusion module 110 sends the common incorrect question image to the incorrect question distribution module 150.

[0057] Furthermore, teachers select the desired objects for placement on the application interface. These desired objects can be determined based on factors such as class, class level, and students.

[0058] For example, if the teacher selects all students in Class 02 of Grade 2 as the target group for assignment, the error distribution module 150 will obtain the target group selected on the application interface and then send the common error images sent by the error recommendation module 140 to the terminal device of the target group.

[0059] The goal is for students to answer the questions in the common error-prone question image using an application on their terminal device. After completing the task, students are expected to upload their answers to the error-collection module 130. Teachers can then grade the papers based on the answers and upload the graded results to the error-collection module 130.

[0060] Optionally, the operation of fusing the text image with the label image used to identify incorrect questions to generate a common incorrect question image includes: using the text image as a background image; generating a corresponding label image according to the label type and using the label image as a foreground image; and fusing the foreground image with the background image to generate a common incorrect question image. The operation of generating a corresponding label image according to the label type and using the label image as the foreground image includes: when the label type is a level of the number of incorrect questions, generating a first label at a first label node position according to the level of the number of incorrect questions; generating a label image as the foreground image based on the first label; and when the label type is a level of key knowledge, generating a second label at a second label node position according to the level of key knowledge; and generating a label image as the foreground image based on the second label.

[0061] Specifically, the labels in the label image generated by the label adding module 120 are of two types, including: the number of students who answered questions incorrectly and the level of key knowledge.

[0062] Therefore, refer to Figure 5 As shown, the labeling module 120 generates a corresponding label (i.e., the first label) at the labeling position of the number of students who answered questions incorrectly in the labeling image (i.e., the first labeling node position).

[0063] For the wrong question number level, the wrong question number level includes: first level, second level and third level. For example, the wrong question number level is first level, which means that the number of students who make mistakes in the question is less than or equal to one third of the total number of students in the whole grade, and the corresponding identification is one star; the wrong question number level is second level, which means that the number of students who make mistakes in the question is greater than one third and less than two thirds of the total number of students in the whole grade, and the corresponding identification is two stars; the wrong question number level is third level, which means that the number of students who make mistakes in the question is greater than or equal to two thirds of the total number of students in the whole grade, and the corresponding identification is three stars.

[0064] For the key knowledge level, a wrong question may involve multiple knowledge points, so the identification adding module 120 adds key knowledge identification (i.e., the second identification) at the position corresponding to each knowledge point in the question in the identification image (i.e., the second identification node position) according to the importance of each knowledge point, for example, increases the undercoat.

[0065] Therefore, the image fusion module 110 takes the identification image including the identification of the key knowledge level and the identification of the wrong question number level as the foreground image, and takes the text image as the background image. Then the image fusion module 110 fuses the foreground image and the background image, thereby generating the common wrong question image.

[0066] As described in the background, although the traditional wrong question management system attempts to introduce technical means to simplify the process, it still faces many challenges in the key image generation link. These systems often take the form of directly converting wrong questions into static images, lacking flexibility and interactivity. Once the key annotation or modification of a certain wrong question is needed, it must be backtracked to the original file for reprocessing, which not only increases the additional workload, but also may lead to resource waste, and there is a great limitation to the wrong question image. At the same time, this single image generation mode is highly dependent on powerful computing power and storage space, which is costly for schools or educational institutions in the long run, and is difficult to adapt to rapidly changing teaching needs.

[0067] In view of the above technical problems, through the technical scheme of the embodiments of the present application, first, by generating the common wrong question into a text image, the understanding barrier that pure text information may bring is overcome, especially when facing low-grade students or non-native learners, the image presentation method is easier to understand and remember. Secondly, the technical scheme converts the screened common wrong question into a high-definition text image. Unlike the traditional one-time static image generation, this scheme adopts a layered processing technology to separate the wrong question content and the annotation information, and generates a basic text image and a dynamic identification image respectively. The system also allows teachers to adjust the annotation content or add new annotations at any time without the need to rebuild the entire image, greatly improving the immediacy and flexibility of teaching interaction, avoiding resource waste and reducing the limitations of image generation.

[0068] Optionally, in the case of identifying the type as the key knowledge level, the operation of generating the second mark at the second mark node position according to the key knowledge level comprises: identifying the text information of the common error question, determining the key knowledge information in the text information; determining the position information of the key knowledge information in the text image; determining the second mark node position corresponding to the position information in the mark image according to the position information in the text image; and generating the second mark at the second mark node position according to the key knowledge level.

[0069] Specifically, the mark adding module 120 will identify the text information (i.e. the question text) of each common error question received before generating the mark corresponding to the key knowledge level, and determine the importance of each knowledge point embodied in the question of the common error question and the corresponding text (i.e. the key knowledge information) according to the importance of each knowledge point recorded in the database.

[0070] Further, the mark adding module 120 marks the position information of each key knowledge information in the text image, so as to determine the second mark node position corresponding to the position information in the mark image according to the position information, and generate the mark of the key knowledge level corresponding to the knowledge point at the position at the second mark node position.

[0071] Thus, the technical solution can distinguish each key knowledge information and attract the attention and attention of students by marking the position of the key knowledge information in the question.

[0072] Optionally, the operation of generating the second mark at the second mark node position according to the key knowledge level comprises: generating the second mark of the corresponding color for the key knowledge information according to the key knowledge level.

[0073] Specifically, in the question, the key knowledge level corresponding to different key knowledge information will also be different, so that the mark adding module 120 is pre-set with the color of the mark of different key knowledge levels. For example, the key knowledge level includes low, medium and high. Then the colors of the marks of low, medium and high are different. Thus, the technical solution can quickly lock the key knowledge information through the color of the mark.

[0074] Optionally, the method further comprises: receiving the answer result and the correction result generated by scanning the test paper by the scanning device; determining the first error question in the test paper according to the correction result; and generating an error question set according to the first error question and the corresponding answer result.

[0075] Specifically, taking paper test paper as an example, after the student answers and the teacher corrects, the scanning device scans the test paper, identifies each test question in the test paper and the corresponding answer result and correction result. Then, the scanning device uploads the answer result and the correction result of the test question to the wrong question collection module 130. Wherein the test paper also includes the identification code of the student, so that the scanning device can scan the identification code of the student, so as to associate the answer result and the correction result of the test question with the student. Wherein the scanning device can be a scanner.

[0076] Further, the wrong question collection module 130 determines the right or wrong result and the score of the test question according to the type of the test question and the correction result, and screens the wrong question (i.e. the first wrong question) from all test questions in the test paper according to the right or wrong result and the score.

[0077] More specifically, for the selection judgment type, the teacher's correction result only includes the overall score of the type, and there is no right or wrong result about each small question. Therefore, the wrong question collection module 130 matches the answer result of the student for the selection judgment question with the correct answer, if consistent, full score, if completely inconsistent, zero score, if partially consistent, score according to the proportion, so as to determine the score of each selection judgment question. For fill-in-the-blank or short answer type, the wrong question collection module 130 identifies the right or wrong identification and score of the teacher's correction on the test paper, and finally, the correction result and the score of each small question in a fill-in-the-blank or short answer question are summarized to obtain the score of the big question.

[0078] Further, the wrong question collection module 130 enters the first wrong question and the answer result of each student into the wrong question set. Wherein the wrong question set includes the first wrong question entered this time and the wrong question entered before.

[0079] Therefore, the technical solution scans the test paper by the scanner, identifies the answer result of the student and the correction result of the teacher. In the prior art, the wrong question is collected and sorted by using intelligent pen and high-speed scanner, etc. However, the high-speed scanner can only collect one homework at a time, which is low in efficiency. However, the scanner in the technical solution can quickly collect a large number of wrong question homework in a few seconds, which improves the efficiency.

[0080] Optionally, the operation of screening common wrong questions for educating students from the wrong question set according to the teacher's selected requirements includes: associating the first wrong question in the wrong question set with the preset element corresponding to the teacher's selected requirements through a preset big data model, wherein the teacher's selected requirements include at least any one of knowledge points, homework, specific time range, class, class stratification, student, number of answerers and scores of grades, type and wrong reason; obtaining the teacher's selected teacher's selected requirements, determining the second wrong question corresponding to the teacher's selected requirements according to the preset element corresponding to the teacher's selected requirements; and recommending the second wrong question to the teacher as a common wrong question.

[0081] Specifically, the error question recommendation module 140 receives the first error questions sent by the error question collection module 130, and then inputs the first error questions into a preset big data model. Then the error question recommendation module 140 classifies each first error question according to each preset element through the big data model, so as to associate each preset element with the first error question.

[0082] For example, for the type of question (i.e., a preset element), the error question recommendation module 140 determines through the big data model whether the type of each first error question is a multiple-choice question, a judgment question, a fill-in-the-blank question, or a short-answer question, thereby associating the first error question with its corresponding type of question; for the student (i.e., a preset element), the error question recommendation module 140 determines the student ID of each first error question through the big data model, and associates the student ID with the corresponding error question; for the knowledge point (i.e., a preset element), the error question recommendation module 140 determines the knowledge point of each first error question through the big data model, which can be, for example, “definition of opposite number”, “solution of a binary linear equation”, or “absolute value of a number”, etc. It should be noted that for the knowledge point of the preset element, one error question can be associated with multiple knowledge points.

[0083] Thus, in the above manner, the error question recommendation module 140 associates other preset elements with each first error question, which will not be described here.

[0084] Further, the teacher selects the teacher's question requirements in the preset elements corresponding to the teacher's question requirements on the application interface, thereby determining the teacher's question requirements.

[0085] Further, the error question recommendation module 140 obtains the teacher's question requirements selected by the teacher on the application interface, and screens the corresponding error questions (i.e., second error questions) from all error questions in the error question set according to the teacher's question requirements. For example, the teacher's question requirements can be that the teacher selects “second grade 02 class / excellent”, “in the past year”, “single-choice question”, and “all error reasons” as the teacher's question requirements in the option boxes corresponding to the preset elements.

[0086] Further, the error question recommendation module 140 sends the screened second error questions as common error questions to the image fusion module 110. After receiving the common error questions, the image fusion module 110 processes the common error questions to generate corresponding images (i.e., text images). Then, the identification adding module 120 generates corresponding identification images for identifying error questions, and then the image fusion module 110 fuses the text images with the identification images to generate common error question images that include both error questions and identification. Then the image fusion module 110 sends the common error question images to the error question distribution module 150.

[0087] Therefore, the technical scheme associates each wrong question with a preset element, so that the teacher can quickly screen the wrong question set according to the teacher's selected question requirement after the teacher selects the teacher's selected question requirement, accurately provides the teacher with a question that meets the teacher's requirement, and improves the question selection efficiency.

[0088] Optionally, in the case where the preset element is a knowledge point, the operation of associating the first wrong question in the wrong question set with the preset element corresponding to the teacher's selected question requirement through the preset big data model includes: associating the first wrong question in the wrong question set with the knowledge point through the big data model to generate a knowledge point tree, wherein each knowledge point node on the knowledge point tree is associated with the first wrong question.

[0089] Specifically, Figure 6A An application interface of the knowledge point tree is shown. Referring to Figure 6A As shown, the wrong question recommendation module 140 inputs the first wrong question into the big data model, associates the first wrong question with the knowledge point of the preset element through the big data model, and generates a knowledge point tree with the knowledge point as a node. The knowledge point nodes at least include: "definition of opposite number", "solution of binary linear equation", and "absolute value of a number".

[0090] Therefore, the wrong question recommendation module 140 lists each knowledge point node on the application interface, and when the teacher selects a corresponding knowledge point node, the wrong question recommendation module 140 determines a wrong question (i.e., a second wrong question) associated with the knowledge point node from the wrong question set.

[0091] Therefore, the technical scheme displays each knowledge point node and the wrong question associated therewith by using the knowledge point tree, so that the teacher can intuitively select and determine the knowledge point, quickly select the teacher's selected question requirement, and improve the question selection efficiency.

[0092] Optionally, in the case where the preset element is a homework, the operation of associating the first wrong question in the wrong question set with the preset element corresponding to the teacher's selected question requirement through the preset big data model includes: associating the first wrong question in the wrong question set with the homework through the big data model to generate a homework tree, wherein each homework node on the homework tree is associated with the first wrong question.

[0093] Specifically, Figure 6B An application interface of the homework tree is shown. Referring to Figure 6B As shown, the wrong question recommendation module 140 inputs the first wrong question into the big data model, associates the first wrong question with the homework of the preset element through the big data model, and generates a homework tree with the homework as a node. The homework nodes at least include: "homework 1 on May 17", "homework 2 on May 17", and "second unit test".

[0094] Thus, the wrong question recommendation module 140 lists each homework node on the application interface, and when the teacher selects a corresponding homework node, the wrong question recommendation module 140 determines a wrong question (i.e., a second wrong question) associated with the homework node from the wrong question set.

[0095] Thus, the technical solution displays each homework node and the wrong question associated therewith using the homework tree, so that the teacher can intuitively select and determine the homework and quickly select the teacher's selection requirements, thereby improving the selection efficiency.

[0096] Alternatively, in the case of a preset element being a student, the operation of associating the first wrong question in the wrong question set and the preset element corresponding to the teacher's selection requirement by the preset big data model includes: associating the first wrong question in the wrong question set with the student by the big data model to generate grade data, wherein the operation of generating the grade data includes: calculating the correctness of the first wrong question according to the scores of the multiple sub-questions in the first wrong question associated with the student and the full scores of the multiple sub-questions; and calculating the grade data according to the correctness of the first wrong question and the number of students.

[0097] Specifically, the wrong question recommendation module 140 inputs the first wrong question into the big data model and associates the first wrong question with the students of the preset element by the big data model. For example, the wrong question recommendation module 140 determines the student ID of each first wrong question by the big data model and associates the student ID with the corresponding wrong question. Further, the wrong question recommendation module 140 determines the class corresponding to each student by the big data model and associates the class with the wrong question of each student. Further, the wrong question recommendation module 140 calculates the correctness of each wrong question (i.e., the first wrong question) of each student in a certain grade.

[0098] For example, the wrong question 1 of student A includes multiple sub-questions. Then, the wrong question recommendation module 140 calculates the correctness of the wrong question 1 of student A according to the correctness calculation formula. The correctness calculation formula is:

[0099] Correctness = sum of scores of multiple sub-questions / sum of full scores of multiple sub-questions.

[0100] Further, the wrong question recommendation module 140 calculates the correctness of the wrong question 1 of each student in the grade according to the above method. Each student in the grade is all the students in the grade, including the students whose answer results of the wrong question 1 are incorrect and the students whose answer results of the wrong question 1 are correct.

[0101] Further, the wrong question recommendation module 140 calculates the grade data according to the correctness of the wrong question 1 of each student and the number of students in the grade by the grade data calculation formula. The grade data is used to indicate the mean of the first wrong question in the grade. The grade data calculation formula is:

[0102] Grade data = sum of correct rate of each student / number of students in the grade.

[0103] Wherein the number of students in the grade is used to indicate the number of students in the grade who answer the wrong question 1.

[0104] Further, the wrong question recommendation module 140 calculates the grade data corresponding to other first wrong questions in the wrong question set according to the above-mentioned method of calculating the grade data corresponding to the wrong question 1. Herein will not be repeated.

[0105] In addition, in addition to the grade data, the wrong question recommendation module 140 will also statistically analyze the number of wrong students and the list of each wrong question based on the class and students of the teacher's selected question requirements through the big data model.

[0106] In addition, wherein the class stratification includes excellent, good and weak, the wrong question recommendation module 140 can determine the class stratification corresponding to the student according to the interval where the average score of the student in a certain subject in multiple examinations.

[0107] For example, if the average score of a student in a certain subject is below 60 points, the class stratification of the student is weak; if the average score of a student in a certain subject is between 60-80 points, the class stratification of the student is good; if the average score of a student in a certain subject is above 80 points, the class stratification of the student is excellent.

[0108] In addition, the wrong question recommendation module 140 also associates each preset element through the big data model. For example, the student and the corresponding class are associated, the class and the corresponding knowledge point are associated, and so on, so that the wrong question recommendation module 140 associates the knowledge point, the homework, the specific time range, the class, the class stratification, the student, the number of answers and the score of the grade, the type of question and the wrong reason in turn through the big data model.

[0109] Therefore, when the teacher selects a certain predetermined element as the teacher's selected question requirement in the application interface, other predetermined elements associated with the teacher's selected question requirement can be automatically displayed.

[0110] For example, when the teacher selects "Class 02, Grade 2" in the application interface, the homework tree automatically displays the homework associated with Class 02, Grade 2.

[0111] Therefore, the technical solution associates the student ID with the wrong question, so that the grade data can be quickly calculated, and the efficiency of calculating and analyzing the data is improved.

[0112] Optionally, the operation of determining the second wrong question corresponding to the teacher's selected question requirement comprises: in the case that the teacher's selected question requirement is multiple, determining the second wrong question according to the intersection of the first wrong questions corresponding to the teacher's selected question requirement; and in the case that the first wrong question in the intersection is zero, obtaining a variable question corresponding to the teacher's selected question requirement as the second wrong question.

[0113] Specifically, in the case that the teacher selects multiple teacher topic requirements in the application interface, the error question recommendation module 140 determines the corresponding error questions (i.e., first error questions) according to the respective teacher topic requirements. Then the error question recommendation module 140 determines the intersection between the first error questions corresponding to the respective teacher topic requirements, i.e., the same first error questions, and determines the error questions in the intersection as second error questions.

[0114] Further, as shown in FIG. 13, in the case that the number of error questions in the intersection between the first error questions corresponding to the respective teacher topic requirements is zero, the error question recommendation module 140 obtains the variable questions corresponding to the teacher topic requirements as second error questions from the error question collection module 130. Figure 7

[0115] Thus, the technical solution takes the variable questions as the second error questions (i.e., common error questions) recommended to the teacher, so that other test questions can be flexibly recommended to the teacher in the case that there is no error question meeting the teacher topic requirements, and the teacher requirements can be adapted. Moreover, the students can also master the knowledge of the corresponding knowledge points according to the variable questions.

[0116] Alternatively, the method further comprises: recommending the individual error questions corresponding to the students to the teacher from the error question set according to the teacher topic requirements; and sending the individual error questions to the corresponding students according to the expected arrangement object of the teacher.

[0117] Specifically, in the case that the teacher needs to select the error questions meeting the learning progress of the students for individual students, the corresponding teacher topic requirements can be selected in the application interface, so that the error question recommendation module 140 determines the individual error questions corresponding to the students according to the teacher topic requirements and recommends them to the teacher. Then the error question recommendation module 140 sends the individual error questions to the image fusion module 110. After receiving the individual error questions, the image fusion module 110 processes the individual error questions to generate corresponding images (i.e., text images). Then, the identification adding module 120 generates the identification images for identifying the error questions, and then the image fusion module 110 fuses the text images and the identification images to generate the individual error question images including both the error questions and the identifications. Then the image fusion module 110 sends the individual error question images to the error question distribution module 150.

[0118] Further, the teacher selects the expected arrangement object as the student in the application interface, and the error question distribution module 150 determines the expected arrangement object. Then the error question distribution module 150 sends the individual error question images received from the error question recommendation module 140 to the terminal device of the expected arrangement object, i.e., the student.

[0119] ​Therefore, in addition to common wrong questions, the technical solution also recommends individual wrong questions suitable for individual students to teachers, so that suitable wrong questions can be arranged according to the actual situation of individual students. Therefore, the technical solution can recommend wrong questions in many aspects to meet the needs of teachers.

[0120] In addition, according to a second aspect of the embodiment, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory, the processor executing the computer program to implement the steps of the above method.

[0121] In addition, according to a third aspect of the embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0122] In addition, according to a fourth aspect of the embodiment, a computer program product is provided, comprising a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0123] Therefore, according to the embodiment, first, by generating common wrong questions into a text image, the understanding obstacle that pure text information may bring is overcome, especially when facing low-grade students or non-native learners, the image presentation method is easier to understand and remember. Secondly, the common wrong questions screened out by the technical solution are converted into high-definition text images. Unlike traditional one-time static image generation, the scheme adopts hierarchical processing technology to separate the wrong question content and the annotation information, and generates basic text images and dynamic identification images respectively. The system also allows teachers to adjust the annotation content or add new annotations at any time without the need to rebuild the entire image, greatly improving the immediacy and flexibility of teaching interaction, avoiding resource waste and reducing the limitations of image generation.

[0124] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0125] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software on a general hardware platform as necessary, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product in essence or in the form of a part that contributes to the prior art, and the computer software product is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk), and includes a plurality of instructions for causing an end device (which can be a mobile phone, a computer, a server, or a network device) to execute the method described in each embodiment of the present application.

[0126] Embodiment 2

[0127] Figure 8 An education-based common error question image generation device 800 according to the present embodiment is shown, which corresponds to the method according to the first aspect of Embodiment 1. Referring to Figure 8 shown, the device 800 includes an error question recommendation module 810 for filtering common error questions for educating students from an error question set according to a teacher's question selection requirement, wherein the common error questions are used to indicate error questions selected by multiple students; a first image generation module 820 for generating a text image of the common error questions; a second image generation module 830 for fusing the text image with an identification image for identifying error questions to generate a common error question image; and an error question sending module 840 for displaying the common error question image to an expected arrangement object of the teacher, wherein the second image generation module 830 includes a background image generation submodule for taking the text image as a background image; a foreground image generation submodule for generating a corresponding identification image according to an identification type and taking the identification image as a foreground image; and an error question image generation submodule for fusing the foreground image with the background image to generate the common error question image, wherein the foreground image generation submodule includes a first identification generation unit for generating a first identification at a first identification node position according to an error question number level when the identification type is the error question number level; and a first image generation unit for generating the identification image as the foreground image according to the first identification, and a second identification generation unit for generating a second identification at a second identification node position according to a key knowledge level when the identification type is the key knowledge level; and a second image generation unit for generating the identification image as the foreground image according to the second identification.

[0128] Optionally, the second mark generating unit comprises: identifying text information of the common wrong questions, determining key knowledge information in the text information; determining position information of the key knowledge information in the text image; determining the second mark node position corresponding to the position information in the mark image according to the position information in the text image; and generating the second mark at the second mark node position according to the key knowledge level.

[0129] Optionally, the operation of generating the second mark at the second mark node position according to the key knowledge level comprises: generating the second mark of a corresponding color for the key knowledge information according to the key knowledge level.

[0130] Optionally, the apparatus 800 further comprises: a first generating module configured to receive an answer result generated by scanning a test paper by a scanning device and a correction result; a first determining module configured to determine a first wrong question in the test paper according to the correction result; and a second generating module configured to generate a wrong question set according to the first wrong question and the corresponding answer result.

[0131] Optionally, the wrong question recommending module 810 comprises: an element associating submodule configured to associate a first wrong question in the wrong question set and a preset element corresponding to a teacher selected question requirement through a preset big data model, wherein the teacher selected question requirement comprises at least any one of a knowledge point, an assignment, a specific time range, a class, a class stratification, a student, an answer person number and a score of a grade, a question type, and a wrong reason; a second determining submodule configured to obtain a teacher selected question requirement, and determine a second wrong question corresponding to the teacher selected question requirement according to the preset element corresponding to the teacher selected question requirement; and a recommending submodule configured to recommend the second wrong question as a common wrong question to a teacher.

[0132] Optionally, in a case where the preset element is a knowledge point, the element associating submodule comprises: a first generating unit configured to associate the first wrong question in the wrong question set and the knowledge point through the big data model, and generate a knowledge point tree, wherein each knowledge point node on the knowledge point tree is associated with the first wrong question.

[0133] Optionally, in a case where the preset element is an assignment, the element associating submodule comprises: a second generating unit configured to associate the first wrong question in the wrong question set and the assignment through the big data model, and generate an assignment tree, wherein each assignment node on the assignment tree is associated with the first wrong question.

[0134] Optionally, in the case that the preset element is a student, the element association submodule comprises: a third generation unit configured to associate a first mistake question in the mistake question set with the student by using the big data model to generate grade data, wherein the operation of generating the grade data comprises: calculating a correctness of the first mistake question according to scores of multiple sub-questions in the first mistake question associated with the student and full scores of the multiple sub-questions; and calculating the grade data according to the correctness of the first mistake question and a number of the students.

[0135] Optionally, the second determination submodule comprises: a first determination unit configured to, in the case that the teacher's question selection requirement is multiple, determine a second mistake question according to an intersection of the first mistake questions corresponding to the teacher's question selection requirement; and a second determination unit configured to, in the case that the first mistake questions in the intersection are zero, obtain a variable question corresponding to the teacher's question selection requirement as the second mistake question.

[0136] Optionally, the device 800 further comprises: a personalized mistake question recommendation module configured to recommend personalized mistake questions corresponding to the students to the teacher from the mistake question set according to the teacher's question selection requirement; and a personalized mistake question sending module configured to send the personalized mistake questions to the corresponding students according to the teacher's expectation of arrangement objects.

[0137] According to the present embodiment, first, by generating the common mistake questions into a text image, the understanding obstacle possibly caused by pure text information is overcome, especially when facing low-grade students or non-native learners, the image presentation method is easier to understand and remember. Second, the present technical solution converts the screened common mistake questions into high-definition text images. Unlike the traditional one-time static image generation, the present solution adopts a hierarchical processing technology to separate the mistake question content and the annotation information, and generates a basic text image and a dynamic identification image respectively. The system also allows the teacher to adjust the annotation content or add new annotations at any time without the need to rebuild the entire image, greatly improving the immediacy and flexibility of teaching interaction, avoiding resource waste, and reducing the limitations of image generation.

[0138] Embodiment 3

[0139] Figure 9 A common mistake question image generation device 900 based on education according to the present embodiment is shown, which corresponds to the method according to the first aspect of embodiment 1. Referring to Figure 9As shown, the apparatus 900 comprises: a processor 910; and a memory 920, connected with the processor 910, for providing the processor 910 with instructions to process the following processing steps: selecting common mistakes for educating students from the mistake set according to the teacher's topic selection requirement, wherein the common mistakes are used to indicate mistakes selected by multiple students; generating a text image of the common mistakes; fusing the text image with an identification image for identifying mistakes to generate a common mistake image; and displaying the common mistake image to the teacher's expected arrangement object, wherein the operation of fusing the text image with the identification image for identifying mistakes to generate a common mistake image comprises: taking the text image as a background image; generating a corresponding identification image according to an identification type, and taking the identification image as a foreground image; and fusing the foreground image with the background image to generate the common mistake image, wherein the operation of generating a corresponding identification image according to an identification type, and taking the identification image as a foreground image comprises: in the case that the identification type is a mistake number level, generating a first identification at a first identification node position according to the mistake number level; and generating the identification image as the foreground image according to the first identification, and in the case that the identification type is a key knowledge level, generating a second identification at a second identification node position according to the key knowledge level; and generating the identification image as the foreground image according to the second identification.

[0140] Optionally, in the case that the identification type is a key knowledge level, the operation of generating a second identification at a second identification node position according to the key knowledge level comprises: identifying text information of the common mistakes, determining key knowledge information in the text information; determining position information of the key knowledge information in the text image; determining the second identification node position corresponding to the position information in the identification image according to the position information in the text image; and generating the second identification at the second identification node position according to the key knowledge level.

[0141] Optionally, the operation of generating the second identification at the second identification node position according to the key knowledge level comprises: generating a second identification of a corresponding color for the key knowledge information according to the key knowledge level.

[0142] Optionally, the memory 920 is further used for providing the processor 910 with instructions to process the following processing steps: receiving an answer result generated by scanning a test paper by a scanning device and a correction result; determining a first mistake in the test paper according to the correction result; and generating a mistake set according to the first mistake and a corresponding answer result.

[0143] Optionally, the operation of selecting common mistakes from the mistake set for the teacher to select the topic requirement for the students, comprises: associating the first mistake in the mistake set with a preset element corresponding to the teacher's selected topic requirement through a preset big data model, wherein the teacher's selected topic requirement comprises at least any one of the following: knowledge points, homework, a specific time range, a class, a class stratification, a student, a number of answerers and scores of a grade, a type of question, and a mistake reason; obtaining the teacher's selected topic requirement, determining a second mistake corresponding to the teacher's selected topic requirement according to the preset element corresponding to the teacher's selected topic requirement; and recommending the second mistake to the teacher as a common mistake.

[0144] Optionally, in the case that the preset element is knowledge points, the operation of associating the first mistake in the mistake set with a preset element corresponding to the teacher's selected topic requirement through a preset big data model, comprises: associating the first mistake in the mistake set with the knowledge points through the big data model to generate a knowledge point tree, wherein each knowledge point node on the knowledge point tree is associated with the first mistake.

[0145] Optionally, in the case that the preset element is homework, the operation of associating the first mistake in the mistake set with a preset element corresponding to the teacher's selected topic requirement through a preset big data model, comprises: associating the first mistake in the mistake set with the homework through the big data model to generate a homework tree, wherein each homework node on the homework tree is associated with the first mistake.

[0146] Optionally, in the case that the preset element is a student, the operation of associating the first mistake in the mistake set with a preset element corresponding to the teacher's selected topic requirement through a preset big data model, comprises: associating the first mistake in the mistake set with the student through the big data model to generate grade data, wherein the operation of generating the grade data comprises: calculating the correctness of the first mistake according to the scores of multiple sub-questions in the first mistake associated with the student and the full scores of the multiple sub-questions; and calculating the grade data according to the correctness of the first mistake and the number of students.

[0147] Optionally, the operation of determining the second mistake corresponding to the teacher's selected topic requirement, comprises: in the case that the teacher's selected topic requirement is multiple, determining the second mistake according to the intersection of the first mistakes corresponding to the teacher's selected topic requirement; and in the case that the first mistake in the intersection is zero, obtaining a variant question corresponding to the teacher's selected topic requirement as the second mistake.

[0148] Optionally, the memory 920 is further configured to provide the processor 910 with instructions for processing the following processing steps: recommending individual mistakes corresponding to the students to the teacher from the mistake set according to the teacher's selected topic requirement; and sending the individual mistakes to the corresponding students according to the teacher's expected arrangement object.

[0149] Thus, according to the present embodiment, firstly, by generating the common error questions as a text image, the understanding obstacle that the pure text information may bring is overcome, especially when facing low-grade students or non-native learners, the image presentation method is easier to understand and remember. Secondly, the common error questions screened out are converted into high-definition text images. Unlike the generation of traditional one-time static images, the present solution adopts a layered processing technology to separate the error question content and the annotation information, and generates a basic text image and a dynamic identification image respectively. The system also allows teachers to adjust the annotation content or add new annotations at any time without the need to rebuild the entire image, greatly improving the immediacy and flexibility of teaching interaction, avoiding resource waste and reducing the limitations of image generation.

[0150] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0151] In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0152] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, which can be electrical or other forms.

[0153] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the present embodiment.

[0154] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0155] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0156] The above is only the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method for generating images of common incorrect questions in education, characterized in that, include: Based on the teacher's selection criteria, common incorrect questions are selected from the incorrect question collection for use in educating students. The common incorrect questions are used to indicate incorrect questions jointly selected by multiple students. Generate text images of the common incorrect questions; The text image is fused with the identification image used to identify incorrect questions to generate a common incorrect question image; as well as The teacher displays the images of the common incorrect questions to the students they intend to assign tasks to, wherein... The operation of fusing the text image with a marker image used to identify incorrect questions to generate the common incorrect question image includes: using the text image as a background image; generating a corresponding marker image according to the marker type, and using the marker image as a foreground image; and fusing the foreground image with the background image to generate the common incorrect question image, wherein... The operation of generating a corresponding identifier image based on the identifier type and using the identifier image as the foreground image includes: when the identifier type is the number of students who answered incorrect questions, generating a first identifier at a first identifier node position based on the number of students who answered incorrect questions; and generating the identifier image based on the first identifier as the foreground image. When the identifier type is a key knowledge level, a second identifier is generated at the second identifier node position according to the key knowledge level; and the identifier image is generated as the foreground image based on the second identifier, wherein... When the identifier type is a key knowledge level, the operation of generating a second identifier at the second identifier node position according to the key knowledge level includes: The process involves identifying the text information of the common incorrect questions, determining the key knowledge information in the text information, determining the location information of the key knowledge information in the text image, determining the position of the second identifier node in the identifier image corresponding to the location information based on the location information in the text image, and generating the second identifier at the position of the second identifier node based on the key knowledge level, wherein the second identifier is an identifier of the key knowledge level corresponding to the corresponding knowledge point.

2. The method according to claim 1, characterized in that, The operation of generating the second identifier at the second identifier node position based on the aforementioned key knowledge level includes: Based on the level of key knowledge, a second identifier of corresponding color is generated for the key knowledge information.

3. The method according to claim 1, characterized in that, Also includes: The device receives the answers and grading results generated from scanning the exam papers. Based on the grading results, determine the first incorrect question in the test paper; as well as The set of incorrect questions is generated based on the first incorrect question and the corresponding answer.

4. The method according to claim 1, characterized in that, The process of selecting common errors from the error collection for use in educating students, based on the teacher's requirements for selecting questions, includes: The first wrong question in the wrong question set is associated with the preset elements corresponding to the teacher's question selection requirements through a preset big data model. The teacher's question selection requirements include at least one of the following: knowledge point, homework, specific time range, class, class level, student, number of students and scores in the grade, question type, and reason for error. Obtain the teacher's selected topic requirements, and determine the second incorrect question corresponding to the teacher's selected topic requirements based on the preset elements corresponding to the teacher's topic requirements; and The second incorrect question will be recommended to the teacher as a common incorrect question.

5. The method according to claim 4, characterized in that, When the preset element is the knowledge point, the operation of associating the first wrong question in the wrong question set with the preset element corresponding to the teacher's question selection requirements through a preset big data model includes: The big data model is used to associate the first wrong question in the wrong question set with the knowledge point to generate a knowledge point tree, wherein each knowledge point node in the knowledge point tree is associated with the first wrong question.

6. The method according to claim 4, characterized in that, When the preset element is the assignment, the operation of associating the first incorrect question in the incorrect question set with the preset element corresponding to the teacher's question selection requirements through a preset big data model includes: The big data model is used to associate the first incorrect question in the incorrect question set with the assignment, generating an assignment tree, wherein each assignment node in the assignment tree is associated with the first incorrect question.

7. The method according to claim 4, characterized in that, When the preset element is the student, the operation of associating the first wrong question in the wrong question set with the preset element corresponding to the teacher's question selection requirements through a preset big data model includes: The big data model is used to associate the first incorrect question in the incorrect question set with the student, generating grade-level data. The operations for generating the grade data include: Calculate the accuracy rate of the first incorrect question based on the scores of multiple sub-questions in the first incorrect question associated with the student and the full score of the multiple sub-questions; and The grade data is calculated based on the accuracy rate of the first incorrect question and the number of students.

8. The method according to claim 5, characterized in that, The steps to identify the second incorrect question corresponding to the teacher's question selection requirements include: When there are multiple teacher-selected topic requirements, the second incorrect topic is determined based on the intersection of the first incorrect topics corresponding to the teacher-selected topic requirements; and If the first incorrect question in the intersection is zero, the variant question corresponding to the teacher's question selection requirements is taken as the second incorrect question.

9. The method according to claim 1, characterized in that, Also includes: Based on the teacher's selection requirements, personalized error questions corresponding to the student are recommended to the teacher from the collection of error questions. as well as Based on the teacher's expectations, the personalized incorrect questions are sent to the corresponding students.

Images