Homework correcting method, homework correcting device, electronic equipment and storage medium

Abstract

The invention discloses a homework correcting method, a homework correcting device, electronic equipment and a computer readable storage medium. The method comprises the steps that a writing image of a homework is acquired, the writing image comprises a book area, and the book area comprises at least one question area; position information of a target object in the writing image is determined, and the target object is used for a user to write an answer; determining a target question area in the written image according to the position information of the target object; and extracting a target question and a user answer based on the target question area, and correcting the user answer according to the target question. Through the scheme of the invention, the homework can be corrected without manual intervention of a user, so that the correction efficiency can be improved, and the risk that the homework is forgotten to be corrected by the user can be reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of intelligent learning products, and in particular, relates to a homework grading method, a homework grading device, an electronic device, and a computer-readable storage medium. Background Art

[0002] In the traditional teaching process, teachers usually assign homework to students to consolidate their learning outcomes. Due to the large number of students in a single class, in order to save teachers' grading time, applications for homework checking have been developed on the market. After completing the homework, students can manually take pictures of the homework images through the application, and then the application can extract the content of the questions and the answers completed by the users from the homework images, and automatically grade the user's homework with the preset standard answers. However, the above process relies on the manual operation of the students, which not only has a low grading efficiency, but also has the risk of students forgetting to grade the homework after completing it. Summary of the invention

[0003] The present application provides a homework grading method, a homework grading device, an electronic device and a computer-readable storage medium, which can complete the grading of homework without manual intervention of the user, which can not only help improve the grading efficiency, but also reduce the risk of the user forgetting to grading the homework.

[0004] In a first aspect, the present application provides a method for marking homework, comprising:

[0005] Acquire a written image of the homework, wherein the written image includes a book area, and the book area includes at least one title area;

[0006] Determining position information of a target object in the writing image, wherein the target object is used for the user to write an answer;

[0007] Determine a target title area in the writing image according to the position information of the target object;

[0008] Extract target questions and user answers based on the target question area, and correct user answers according to the target questions.

[0009] In a second aspect, the present application provides a homework correction device, comprising:

[0010] An acquisition module, used for acquiring a writing image of a homework, wherein the writing image includes a book area, and the book area includes at least one title area;

[0011] A first determination module is used to determine the position information of a target object in the writing image, wherein the target object is used for the user to write an answer;

[0012] A second determination module is used to determine a target title area in the writing image according to the position information of the target object;

[0013] The correction module is used to extract the target questions and user answers based on the target question area, and correct the user answers according to the target questions.

[0014] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect when executing the computer program.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of the first aspect are implemented.

[0016] In a fifth aspect, the present application provides a computer program product, which includes a computer program. When the computer program is executed by one or more processors, it implements the steps of the method of the first aspect.

[0017] Compared with the prior art, the present application has the following beneficial effects: in the process of a user writing an assignment, the present application scheme can be applied, first obtaining a written image of the assignment, wherein the written image includes a book area, and the book area includes at least one question area; then determining the position information of the target object in the written image, wherein the target object is used by the user to write the answer; then determining the target question area in the written image based on the position information of the target object; finally extracting the target question and the user's answer based on the target question area, and correcting the user's answer based on the target question. In the above process, the user does not need to manually shoot the assignment after completing the assignment, but shoots the assignment while the user is writing the assignment; and, considering that the user will definitely use writing tools when doing the assignment, the position information of the target object in the written image can be used to know which questions the user has completed, and the question area corresponding to these questions is the target question area, based on which the target question and the user's answer can be extracted and corrected. Thus, through the above process, the correction of the assignment can be completed without the user's manual intervention, which can not only help improve the correction efficiency, but also reduce the risk of the user forgetting to correct the assignment.

[0018] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 It is a schematic diagram of the implementation process of the homework correction method provided in the embodiment of the present application;

[0021] Figure 2 It is a front structural diagram of a user terminal to which the homework correction method provided in the embodiment of the present application is applicable;

[0022] Figure 3 is an example diagram of the target topic area provided in the embodiment of the present application;

[0023] Figure 4 is another example diagram of the target topic area provided in the embodiment of the present application;

[0024] Figure 5 is a structural block diagram of a homework correction device provided in an embodiment of the present application;

[0025] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0027] A homework grading method provided in an embodiment of the present application is described below, and the homework grading method can be applied to an electronic device. The electronic device can be a user terminal equipped with a front camera, such as a tablet computer or a learning machine, or the electronic device can also be other devices that establish a communication connection with the user terminal, such as a smart phone, etc., which is not limited in the embodiment of the present application.

[0028] For the user terminal, it can be installed in a specified location, such as on the user's desk, and the angle between its display screen and the user's desk can meet the preset angle condition. Just as an example, when the angle range is [0,90°], the angle condition can be: the angle exceeds the preset angle threshold. It can be understood that the angle condition is set based on: it is convenient for the user to view the display screen and it is convenient for the front camera to shoot the desktop of the user's desk.

[0029] For the convenience of description, the following takes the electronic device used in the homework correction method as a user terminal as an example to explain and illustrate the homework correction method. Figure 1 , the homework correction method in the embodiment of the present application includes:

[0030] Step 101, obtaining a written image of a job.

[0031] As described above, after the user terminal is installed at a designated location, its front camera can shoot the desktop of the user's desk. Since the user usually places exercise books and / or test papers on the desk when performing various learning tasks, such as doing homework, the user terminal can obtain the written image of the homework through the shooting of the front camera.

[0032] Generally speaking, the writing image includes a book area, which contains the text content of the current page of the exercise book and / or test paper; considering that there must be at least one question in these text contents, the book area includes at least one question area, and each question area contains the text content of the corresponding question; it should be noted that the part between two adjacent questions above and below (generally blank) is usually the answer area of ​​the upper question of the two questions, and thus the answer area also belongs to the question area corresponding to the upper question.

[0033] Step 102: Determine the position information of the target object in the writing image.

[0034] When a user does homework, he or she must use an object to write the answer on the homework. For example, the user writes the answer on the paper version of the exercise book and / or test paper with a pen, and writes the answer on the electronic version of the exercise book and / or test paper (such as a tablet computer displaying the exercise book and / or test paper) with a finger or an electronic pen. This type of object used by the user to write the answer can be defined as a target object. The user terminal can first perform target detection on the writing image to determine whether there is a target object in the writing image. When the target object is detected, the position information of the target object in the writing image, that is, the coordinates of the target object in the writing image, can be obtained.

[0035] Step 103, determining the target title area in the writing image according to the position information of the target object.

[0036] Through the analysis of people's behavior when doing homework, it can be known that when answering questions, users generally answer questions from top to bottom and from left to right in the answer area (that is, write answers); and it is rare for users to answer questions outside the answer area. Since the user uses the target object to write the answer, based on the position information of the target object in the writing image, it can be analyzed in which question areas the user has completed answering the questions, thereby determining the target question area in the writing image. It can be understood that the target question area refers to: the question area corresponding to the question that the user has completed answering.

[0037] Step 104, extracting the target question and the user's answer based on the target question area, and correcting the user's answer according to the target question.

[0038] In the target question area, the user terminal can extract the user's handwritten text content, which is the user's answer; alternatively, the user terminal can also extract text content from the answer area of ​​the target question area, which is the user's answer. The embodiments of the present application do not limit the specific means of extracting the user's answer.

[0039] Similarly, in the target question area, the user terminal can extract text content that is not handwritten by the user, and this text content is the target question; alternatively, the user terminal can also determine the target homework image based on the matching relationship between the writing image and each preset homework image in the exercise bank, and then determine the target question from the target homework image based on the position of the target question area in the writing image. The embodiments of the present application do not limit the specific means of extracting the target question.

[0040] After extracting the target question and the user's answer, the user terminal can correct the user's answer according to the target question. In some embodiments, the user terminal can first find the standard answer corresponding to the target question from the question bank, and then automatically correct the homework by comparing the standard answer with the user's answer.

[0041] In some embodiments, the front camera of the user terminal is specifically a lifting front dual camera, including: a first camera and a second camera. Among them, there is a difference in the shooting angles of the first camera and the second camera. The first camera is used to shoot faces, and the second camera is used to shoot desktops. It can be understood that when the user writes homework, the first camera can definitely shoot the user's face, and the second camera can definitely shoot the homework on the desktop. Based on this, the user terminal can determine whether the user's homework behavior occurs by combining the images collected in real time by the first camera and the second camera.

[0042] Furthermore, in order to save system resources of the user terminal, the user terminal may also be integrated with an obstacle sensor for performing dToF (direct Time-of-Flight) detection operations, and the detection direction of the obstacle sensor may be consistent or approximately consistent with the shooting direction of the first camera. Figure 2 , Figure 2 A schematic diagram of the front structure of the user terminal is given, including: a first camera 201, a second camera 202, an obstacle sensor 203 and a display screen 204.

[0043] For the user terminal, its obstacle sensor can always work in low power consumption mode, and the first camera and the second camera can be in sleep mode first. When the obstacle sensor detects an obstacle, it can be preliminarily considered that the obstacle may be the user's face, thereby triggering the first camera to start running. When the image captured in real time by the first camera determines that the obstacle is indeed the user's face, the second camera can be triggered to start running. When the image captured in real time by the second camera determines that there is book information (that is, text content is detected in the image), the user terminal can enter the learning mode.

[0044] It is understandable that in application scenarios such as users reviewing / previewing teaching materials, doing homework or reading, the image captured by the second camera in real time will contain book information. Since this application mainly focuses on automatic correction of homework, after entering the learning mode, the user terminal can match the book information in the image currently captured by the second camera with the preset exercise library and the preset teaching material library in a whole-image search manner.

[0045] Obviously, if the book information matches the question bank, it can be basically determined that the user is currently doing homework, and the user terminal can enter the homework sub-mode under the learning mode, and execute various steps related to homework correction proposed in the embodiments of the present application in this homework sub-mode; if the book information matches the teaching material library, it can be basically determined that the user is currently reviewing or previewing, and the user terminal can enter the teaching material sub-mode under the learning mode, and execute various steps related to review or preview in this teaching material sub-mode, such as displaying the knowledge point content of the course that the current user is reviewing or previewing; if the book information cannot be matched with the teaching material library or the question bank, it can be basically determined that the user is currently reading, and the user terminal can enter the reading sub-mode under the learning mode, and execute various steps related to reading in this reading sub-mode, such as analyzing the user's reading speed.

[0046] In some embodiments, after the user terminal enters the learning mode, no matter which sub-mode it finally enters, the learning guard function can be activated. Under the learning guard function, the user terminal can detect the user's sitting posture through the front dual camera, and output a sitting posture reminder message when the user's sitting posture matches the preset bad sitting posture, so that the user can always maintain a good posture during the learning process, which is beneficial to the user's eye health. In addition, the learning guard function can also have specific operations in certain specific sub-modes. For example, it can trigger the user terminal to turn off the screen in the job sub-mode so that the user can focus on the job. In the embodiments of the present application, there is no limitation on the operations that can be performed by the learning guard function.

[0047] In some embodiments, the user terminal may consider correcting the answer to each question immediately after the user completes the question, and step 103 may specifically include:

[0048] A1. Determine the topic area that matches the target object based on the location information of the target object and the location information of each topic area.

[0049] The front camera of the user terminal can keep working in real time in the homework sub-mode, so that a real-time image of the homework on the desktop can be collected, which is the writing image. Through target detection and target positioning, the user terminal can obtain the real-time position information of the target object in the writing image, as well as the real-time position information of each question area. Of course, when the user is doing homework, the homework position will not be moved frequently, so the frequency of target positioning of each question area can be lower than the frequency of target positioning of the target object.

[0050] According to the position information of the target object and the position information of each topic area, the user terminal can analyze the relative position of the target object and each topic area, thereby determining the topic area matching the target object in real time.

[0051] A2. When the topic region matching the target object changes, the topic region matching the target object before the change is determined as the target topic region.

[0052] It can be imagined that after the user completes a question, the target object he holds will usually turn to the next question; until all the questions on the current page of the homework are completed, the target object he holds will usually leave the homework to complete the action of turning the page or closing the homework. Obviously, the above two situations will cause the question area that matches the target object to change (it may be changed to a new question area, or it may be changed to nothing). Based on this, when the question area that matches the target object changes, it can be considered that the user has just completed answering a question, and the question area that matches the target object before the change can be determined as the target question area. The subsequent user terminal can extract the target question and the user's answer from the target question area of ​​the real-time writing image to complete the automatic correction of the target question.

[0053] In some embodiments, in order to accurately determine the topic area matching the target object, step A1 may include:

[0054] A11. Calculate the distance between the target object and each question area based on the position information of the target object and the position information of each question area.

[0055] As for the position information of the target object, it can be understood that when the target object is a pen or an electronic pen, the user mainly writes the answer by moving the pen tip; when the target object is a finger, the user mainly writes the answer by moving the fingertip. That is, the writing of the answer is actually completed by a specific part of the target object. Based on this, in the embodiments of the present application, it is not necessary to consider the position information of the target object as a whole, but only the position information of the specific part of the target object. For example, when the target object is a pen or an electronic pen, what is considered is the coordinates of the pen tip of the pen or the electronic pen in the writing image; when the target object is a finger, what is considered is the coordinates of the fingertip in the writing image.

[0056] For the position information of the title area, the position information may be the coordinates of the center point of the title area in the written image; in addition, considering that the title area is generally rectangular or approximately rectangular in shape, the position information may also be the coordinates of the sides of the title area in the written image, which is not limited in the embodiments of the present application.

[0057] Through the location information of the target object and the location information of each question area, the user terminal can quickly calculate the distance between the target object and each question area through mathematical knowledge.

[0058] A12. Detect whether the calculated minimum distance is less than a preset distance threshold.

[0059] Obviously, the question area corresponding to the calculated minimum distance is the question area that the user is most likely to answer at the moment. However, considering that the target object may not be in the valid answering area, the user terminal can also compare the calculated minimum distance with the preset distance threshold, and determine whether the question area corresponding to the minimum distance is the question area that matches the target object based on the comparison result.

[0060] A13. When the minimum distance is less than the distance threshold, the question area corresponding to the minimum distance is determined as the question area matching the target object.

[0061] When the minimum distance is less than the distance threshold, it can be considered that the target object is currently in a valid answer area in the question area corresponding to the minimum distance. At this time, the question area can be determined as the question area matching the target object; that is, at this time, it can be determined that the user is writing the answer in the question area corresponding to the minimum distance.

[0062] See also Figure 3 , Figure 3 Examples of target topic areas are given. Figure 3 As shown, at time T1, the question area in the writing image that matches the target object is question area 1, which means that the user is answering the questions in question area 1; at time T2, the question area in the writing image that matches the target object changes from question area 1 to question area 2, which means that the user has completed the questions in question area 1 and started to answer the questions in question area 2. Based on this, question area 1 can be determined as the target question area. Since the writing image is an image captured in real time by the front camera of the user terminal, as long as the user does not turn the page, after determining the target question area, the latest writing image must include the answer written by the user in the target question area.

[0063] In some embodiments, the user terminal may also consider synchronously correcting the answers to all questions on the current page of the assignment after the user completes all questions on the current page of the assignment. Then step 103 may specifically include:

[0064] B1. Determine whether the target object is located at a designated position in the book area according to the position information of the target object.

[0065] The position information of the target object has been described above and will not be repeated here; the designated position is specifically: the question area of ​​the last question in the book area (that is, the question area closest to the bottom boundary of the book area). It can be understood that when the target object is at the designated position in the book area, it can be considered that the user is writing the last question in the current page of the homework.

[0066] B2. When the target object leaves the designated position, all the question areas are determined as target question areas.

[0067] When the target object leaves the designated position, the user terminal can basically determine that the user has completed answering all questions on the current page of the assignment, and at this time all question areas in the writing image can be determined as target question areas. The user terminal can thus extract all questions on the current page of the assignment and the corresponding user answers. Compared with steps A1 and A2 described above, the real-time performance of this grading method is slightly reduced, but it can still ensure the automatic grading of the assignment by the user terminal.

[0068] Of course, when the target object is a pen or an electronic pen, considering that the user must hold the pen when writing the answer using the target object, in order to eliminate the special situation where the pen or electronic pen rolls away from the homework, the user terminal can also synchronously detect the position information of the human hand and determine whether the human hand is in the designated position of the book area; when both the target object and the human hand leave the designated position, the user terminal can assume that it is indeed the user who has left the designated position with the pen, and at this time all question areas can be determined as target question areas.

[0069] See also Figure 4 , Figure 4 Examples of target topic areas are given. Figure 4 As shown, at time T1, the target object in the writing image is already at the specified position; at time T2, the target object has left the specified position, which means that the user has completed answering all questions on the current page of the assignment. Based on this, all question areas in the writing image (i.e., question areas 1, 2, and 3) can be determined as target question areas. Since the writing image is an image captured in real time by the front camera of the user terminal, as long as the user does not turn the page, after determining the target question area, the latest writing image must include the answers written by the user in each target question area.

[0070] In some embodiments, in order to further improve the learning efficiency of the user and help the user to learn in a targeted manner, after step 103, the homework grading method further includes:

[0071] C1. Generate a user assignment analysis report based on the correction results.

[0072] The user terminal can continuously correct the homework through the steps described above while the user is doing the homework. After the user completes the homework, that is, stops doing the homework, the user terminal can generate a user homework analysis report for this homework based on the various correction results obtained this time. The user homework analysis report may include but is not limited to the following content: accuracy rate, number of wrong questions and analysis of the reasons for each wrong question, etc.

[0073] In some examples, users usually close the exercise book after completing the homework, which will cause the real-time writing image captured by the front camera of the user terminal to no longer contain the text content of the questions, but the cover of the exercise book. Obviously, the proportion of text content on the cover of the exercise book is significantly reduced compared to the homework. Based on this, the user terminal can determine whether the user has completed the homework based on the proportion of text content in the writing image. Specifically, when the proportion of text content in the writing image is less than the preset proportion threshold, it is determined that the user has completed the homework.

[0074] In other examples, the user usually stops writing after completing the assignment, which causes the target object to stop moving for a long period of time (e.g., 5 minutes). Based on this, the user terminal can determine whether the user has completed the assignment based on the state of the target object, specifically: when the position information of the target object in the writing image remains unchanged for a specified period of time, or when the target object does not exist in the writing image for a specified period of time, it is determined that the user has completed the assignment.

[0075] C2. Output user operation analysis report.

[0076] The user terminal can output the latest user job analysis report. In some examples, the user terminal may consider displaying the user job analysis report on its own display screen so that the user can know the completion status of his or her job as soon as possible after completing the job. In other examples, the user terminal can also transmit the user job analysis report to the target device, which is specifically: a device bound to the user terminal. It can be understood that the user's guardian can bind the device he or she uses (such as a smart phone) to the user terminal so that the user's guardian can know the user's job completion status as soon as the user completes the job, and supervise the user based on the job completion status.

[0077] In some embodiments, the user terminal can also determine the user's weak knowledge points for the day based on the latest user homework analysis report, and extract the learning content corresponding to the weak knowledge points for the day from the preset course library and exercise library, such as the first target course and first target exercises corresponding to the weak knowledge points for the day, and push the first target course and first target exercises to the user to help the user better consolidate the learning outcomes of the day.

[0078] In addition, the user terminal can also determine the user's weak knowledge points of the week based on the user's homework analysis report within a preset time period (such as the past week) at a specified time point (such as the weekend), and extract the learning content corresponding to the weak knowledge points of the week from the preset course library and exercise library, such as the second target courses and second target exercises corresponding to the weak knowledge points of the week, and push the second target courses and second target exercises to the user to help the user better consolidate the learning results of the week.

[0079] Compared with the first target course, the second target course has a higher level of detail; compared with the first target exercise, the second target exercise has a higher number of exercises. This can help users make full use of the weekend time to consolidate their learning foundation and improve their ability to master weak knowledge points of the week.

[0080] As can be seen from the above, in the embodiment of the present application, the user does not need to manually take a photo of the homework after completing it, but takes a photo of the homework while the user is doing it; and, considering that the user will definitely use writing tools when doing homework, the position information of the target object in the writing image can be used to know which questions the user has completed, and the question area corresponding to these questions is the target question area, based on which the target question and the user's answer can be extracted and corrected. Therefore, through the above process, the correction of homework can be completed without the manual intervention of the user, which can not only help improve the correction efficiency, but also reduce the risk of the user forgetting to correct the homework.

[0081] It should be understood that the size of the serial numbers of the steps in the embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0082] Corresponding to the homework grading method provided above, the embodiment of the present application also provides a homework grading device, which can be integrated into an electronic device. As an example only, the electronic device can be a user terminal; or, the electronic device can also be other devices that establish a communication connection with the user terminal, which is not limited in the embodiment of the present application. The user terminal and the other device have been introduced in the previous text and will not be repeated here. Please refer to Figure 5 The homework correction device 5 in the embodiment of the present application includes:

[0083] An acquisition module 501 is used to acquire a writing image of a homework, wherein the writing image includes a book area, and the book area includes at least one question area;

[0084] A first determination module 502 is used to determine the position information of a target object in the writing image, wherein the target object is used for the user to write an answer;

[0085] The second determination module 503 is used to determine the target topic area in the writing image according to the position information of the target object;

[0086] The correction module 504 is used to extract the target question and the user's answer based on the target question area, and correct the user's answer according to the target question.

[0087] In some embodiments, the written image is a real-time image; the second determination module 503 includes:

[0088] A first determining unit, configured to determine a topic area matching the target object according to the location information of the target object and the location information of each topic area;

[0089] The second determining unit is configured to determine the topic area matching the target object before the change as the target topic area when the topic area matching the target object changes.

[0090] In some embodiments, the first determining unit includes:

[0091] A calculation subunit, used for calculating the distance between the target object and each question area according to the position information of the target object and the position information of each question area;

[0092] A detection subunit, used to detect whether the calculated minimum distance is less than a preset distance threshold;

[0093] The determination subunit is used to determine the topic area corresponding to the minimum distance as the topic area matching the target object when the minimum distance is less than the distance threshold.

[0094] In some embodiments, the position information of the topic area includes: position information of the center point of the topic area and / or position information of each side length of the topic area.

[0095] In some embodiments, the written image is a real-time image; the second determination module 503 includes:

[0096] a third determining unit, configured to determine whether the target object is located at a designated position in the book area according to the position information of the target object;

[0097] The fourth determining unit is used to determine all the topic areas as target topic areas when the target object leaves the designated position.

[0098] In some embodiments, the homework correction device 5 further includes:

[0099] A generating module, which is used to extract the target topic and the user's answer based on the target topic area in the correcting module 504, correct the user's answer according to the target topic, and generate a user homework analysis report according to the correcting result;

[0100] Output module, used to output user job analysis report.

[0101] In some embodiments, the output module includes:

[0102] A display unit is used to display the user operation analysis report on a display screen; and / or,

[0103] The transmission unit is used for transmitting the user operation analysis report to the target device.

[0104] As can be seen from the above, in the embodiment of the present application, the user does not need to manually take a photo of the homework after completing it, but takes a photo of the homework while the user is doing it; and, considering that the user will definitely use writing tools when doing homework, the position information of the target object in the writing image can be used to know which questions the user has completed, and the question area corresponding to these questions is the target question area, based on which the target question and the user's answer can be extracted and corrected. Therefore, through the above process, the correction of homework can be completed without the manual intervention of the user, which can not only help improve the correction efficiency, but also reduce the risk of the user forgetting to correct the homework.

[0105] Corresponding to the homework grading method provided above, the embodiment of the present application also provides an electronic device. As an example only, the electronic device may be a user terminal; or, the electronic device may also be other devices that establish a communication connection with the user terminal, which is not limited in the embodiment of the present application. The user terminal and the other device have been introduced above and will not be described here. Please refer to Figure 6 The electronic device 6 in the embodiment of the present application includes: a memory 601, one or more processors 602 ( Figure 6 Only one is shown in the figure) and a computer program stored in the memory 601 and executable on the processor. Among them: the memory 601 is used to store software programs and modules, and the processor 602 executes various functional applications and data processing by running the software programs and units stored in the memory 601 to obtain resources corresponding to the preset events. Specifically, the processor 602 implements the following steps when running the computer program stored in the memory 601:

[0106] Acquire a written image of the homework, wherein the written image includes a book area, and the book area includes at least one title area;

[0107] Determining position information of a target object in the writing image, wherein the target object is used for the user to write an answer;

[0108] Determine a target title area in the writing image according to the position information of the target object;

[0109] Extract target questions and user answers based on the target question area, and correct user answers according to the target questions.

[0110] Assuming the first possible implementation, in a second possible implementation provided on the basis of the first possible implementation, the writing image is a real-time image; determining the target topic area in the writing image according to the position information of the target object includes:

[0111] Determine the topic area matching the target object according to the location information of the target object and the location information of each topic area;

[0112] When the topic region matching the target object changes, the topic region matching the target object before the change is determined as the target topic region.

[0113] In a third possible implementation manner provided on the basis of the second possible implementation manner, determining the topic area matching the target object according to the location information of the target object and the location information of each topic area includes:

[0114] Calculate the distance between the target object and each question area according to the position information of the target object and the position information of each question area;

[0115] Detect whether the calculated minimum distance is less than a preset distance threshold;

[0116] When the minimum distance is less than the distance threshold, the topic area corresponding to the minimum distance is determined as the topic area matching the target object.

[0117] In a fourth possible implementation provided on the basis of the third possible implementation, the position information of the topic area includes: position information of a center point of the topic area and / or position information of each side length of the topic area.

[0118] In a fifth possible implementation provided on the basis of the first possible implementation, the written image is a real-time image; and determining the target topic area in the written image according to the position information of the target object includes:

[0119] Determine whether the target object is located at a specified position in the book area according to the position information of the target object;

[0120] When the target object leaves the designated position, all the topic areas are determined as target topic areas.

[0121] In a sixth possible implementation provided on the basis of the first possible implementation, or on the basis of the second possible implementation, or on the basis of the third possible implementation, or on the basis of the fourth possible implementation, or on the basis of the fifth possible implementation, after extracting the target topic and the user answer based on the target topic area and correcting the user answer according to the target topic, the processor 602 further implements the following steps when running the computer program stored in the memory 601:

[0122] Generate user work analysis report based on the correction results;

[0123] Output user job analysis report.

[0124] In a seventh possible implementation provided on the basis of the sixth possible implementation, outputting a user operation analysis report includes:

[0125] Displaying the user operation analysis report on the display screen; and / or,

[0126] Transmits user job analysis reports to target devices.

[0127] It should be understood that in the embodiment of the present application, the processor 602 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0128] The memory 601 may include a read-only memory and a random access memory, and provide instructions and data to the processor 602. A part or all of the memory 601 may also include a non-volatile random access memory. For example, the memory 601 may also store information on the device type.

[0129] As can be seen from the above, in the embodiment of the present application, the user does not need to manually take a photo of the homework after completing it, but takes a photo of the homework while the user is doing it; and, considering that the user will definitely use writing tools when doing homework, the position information of the target object in the writing image can be used to know which questions the user has completed, and the question area corresponding to these questions is the target question area, based on which the target question and the user's answer can be extracted and corrected. Therefore, through the above process, the correction of homework can be completed without the manual intervention of the user, which can not only help improve the correction efficiency, but also reduce the risk of the user forgetting to correct the homework.

[0130] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of each functional unit and module is used as an example. In actual application, the function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit, and the integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0131] In the embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of external device software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0133] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the implementation method of the present application can also be completed by instructing the associated hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of each method embodiment when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer-readable memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electric carrier signals and telecommunication signals.

[0136] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A homework marking method, characterized in that: include: Acquire a written image of a homework, wherein the written image includes a book area, and the book area includes at least one title area; Determine position information of a target object in the writing image, wherein the target object is used for the user to write an answer; Determining a target topic area in the writing image according to the position information of the target object; A target question and a user answer are extracted based on the target question area, and the user answer is corrected according to the target question.

2. The homework marking method according to claim 1, characterized in that: The written image is a real-time image; determining the target topic area in the written image according to the position information of the target object includes: Determining a topic area matching the target object according to the location information of the target object and the location information of each topic area; In the case that the topic area matching the target object changes, the topic area matching the target object before the change is determined as the target topic area.

3. The homework marking method according to claim 2, characterized in that: The step of determining a topic area matching the target object according to the location information of the target object and the location information of each topic area includes: Calculating the distance between the target object and each of the question areas according to the position information of the target object and the position information of each of the question areas; Detect whether the calculated minimum distance is less than a preset distance threshold; When the minimum distance is less than the distance threshold, the topic area corresponding to the minimum distance is determined as the topic area matching the target object.

4. The homework marking method according to claim 3, characterized in that: The position information of the topic area includes: the position information of the center point of the topic area and / or the position information of each side length of the topic area.

5. The homework marking method according to claim 1, characterized in that: The written image is a real-time image; determining the target topic area in the written image according to the position information of the target object includes: Determining whether the target object is located at a designated position of the book area according to the position information of the target object; When the target object leaves the designated position, all the topic areas are determined as target topic areas.

6. The homework marking method according to any one of claims 1 to 5, characterized in that: After extracting the target topic and the user answer based on the target topic area, and correcting the user answer according to the target topic, the homework correction method further includes: Generate user work analysis report based on the correction results; Output the user operation analysis report.

7. The homework marking method according to claim 6, characterized in that: The outputting of the user operation analysis report includes: Displaying the user operation analysis report on a display screen; and / or, The user operation analysis report is transmitted to the target device.

8. A homework correction device, characterized in that: include: An acquisition module, used for acquiring a written image of a homework, wherein the written image includes a book area, and the book area includes at least one title area; A first determination module is used to determine the position information of a target object in the writing image, wherein the target object is used for the user to write an answer; A second determination module, configured to determine a target title area in the writing image according to the position information of the target object; The correction module is used to extract the target question and the user answer based on the target question area, and correct the user answer according to the target question.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images