Answer image acquisition and submission method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a test image acquisition and submission method, device, electronic equipment and storage medium. The test image acquisition method comprises: performing test paper editing according to given test parameters, layout parameters and volume size parameters to generate a target test paper; determining an image acquisition quantity and image recognition information according to the target test paper; and acquiring a test image of the target test paper according to the image acquisition quantity and the image recognition information. Therefore, the present disclosure can acquire an accurate test image and avoid the occurrence of abnormal situations such as incorrect transmission or missing transmission of the test image.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a question answering image acquisition and submission method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the continuous development of the Internet, online education is favored by more and more institutions, teachers and students due to its anytime, anywhere learning feature.

[0003] In the existing online education scheme, teachers can arrange homework through an online education platform to synchronize homework arrangement information to each client (student end) for printing, so that students can answer questions, and then upload the question answering images to the online education platform in the form of scanning or photographing, so that teachers can correct the question answering results.

[0004] However, in the prior art, the client cannot determine the specific number of uploaded question answering images when uploading the question answering images, which can easily lead to abnormal situations such as too many or too few question answering images. Furthermore, even if the number of uploaded question answering images is correct, it cannot avoid the occurrence of problems such as repeated uploading or incorrect uploading of question answering images.

[0005] Therefore, there is an urgent need for a processing method that can improve the accuracy of question answering image uploading. SUMMARY

[0006] Therefore, the embodiments of the present application provide a question answering image acquisition and submission method and device, electronic equipment and storage medium to at least partially solve the above problems.

[0007] According to a first aspect of the present application, a question answering image acquisition method is provided, comprising: performing paper setting editing according to given question parameters, layout parameters and paper size parameters to generate a target test paper; determining an image acquisition number and image recognition information according to the target test paper; and acquiring question answering images of the target test paper according to the image acquisition number and the image recognition information.

[0008] According to a second aspect of the present application, a question answering image submission method is provided, comprising: acquiring a target test paper of an online education platform; and submitting a plurality of question answering images of the target test paper to the online education platform according to an image acquisition number of the target test paper given by the online education platform, wherein the image acquisition number of the target test paper is determined by the question answering image acquisition method of the first aspect.

[0009] According to a third aspect of the present disclosure, a test image acquisition device is provided, comprising: a generation module configured to generate a target test paper according to given test parameters, layout parameters, and test paper size parameters; a determination module configured to determine an image acquisition quantity and image identification information according to the target test paper; and an acquisition module configured to acquire test images of the target test paper according to the image acquisition quantity and the image identification information.

[0010] According to a fourth aspect of the present disclosure, a test image submission device is provided, comprising: a test paper acquisition module configured to acquire a target test paper of an online education platform; and an image submission module configured to submit a plurality of test images of the target test paper to the online education platform according to an image acquisition quantity of the target test paper given by the online education platform, wherein the image acquisition quantity of the target test paper is determined by using the test image acquisition method according to the first aspect or the test image acquisition device according to the third aspect.

[0011] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory storing a program, wherein the program comprises instructions that, when executed by the processor, cause the processor to perform the test image acquisition method according to the first aspect or perform the test image submission method according to the second aspect.

[0012] According to a sixth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are configured to cause the computer to perform the test image acquisition method according to the first aspect or perform the test image submission method according to the second aspect.

[0013] The test image acquisition and submission scheme provided by the aspects of the present disclosure generates a target test paper according to various test paper generation parameters, and determines an image acquisition quantity and image identification of test images according to the generated target test paper, so as to accurately acquire test images of the target test paper, and effectively avoid abnormal situations such as incorrect transmission and missing transmission of test images, and improve the user experience of using the online education platform. BRIEF DESCRIPTION OF DRAWINGS

[0014] In the following description of exemplary embodiments in conjunction with the accompanying drawings, more details, features, and advantages of the present disclosure are disclosed, in which:

[0015] Figure 1 A flowchart of a test image acquisition method of an exemplary embodiment of the present disclosure.

[0016] Figure 2 A flowchart of a test image acquisition method of another exemplary embodiment of the present disclosure.

[0017] Figure 3 Flowchart of the answer image acquisition method according to another exemplary embodiment of the present disclosure.

[0018] Figure 4 Flowchart of the answer image acquisition method according to another exemplary embodiment of the present disclosure.

[0019] Figure 5 Flowchart of the answer image acquisition method according to another exemplary embodiment of the present disclosure.

[0020] Figure 6 Flowchart of the answer image submission method according to an exemplary embodiment of the present disclosure.

[0021] Figures 7A to 7F Application diagram of the answer image submission method according to an exemplary embodiment of the present disclosure.

[0022] Figure 8 Architecture diagram of the answer image acquisition apparatus according to an exemplary embodiment of the present disclosure.

[0023] Figure 9 Architecture diagram of the answer image submission apparatus according to an exemplary embodiment of the present disclosure.

[0024] Figure 10 Architecture diagram of the electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. While several embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein, but rather should be construed to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure. It is to be understood that the drawings and the embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure.

[0026] It is to be understood that the various steps of the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit performing the steps shown. The scope of the present disclosure is not limited in this respect.

[0027] The term "include" and variations thereof, as used in this document, means "to include, without limitation." The term "based on" means "based at least in part on." The term "one embodiment" means "at least one embodiment." The term "another embodiment" means "at least one additional embodiment." The term "some embodiments" means "at least some embodiments." Related terms shall be construed accordingly. It should be noted that "a" or "an" entity as used in this document refers to one or more than one entity. The terms "first," "second," and the like as used in this document do not have any specific meaning in terms of importance or priority, unless specifically indicated otherwise.

[0028] It should be noted that the terms "one" and "a" or "an" as used in this document refer to "one or more" or "at least one," unless specified otherwise. The terms "first," "second," and the like as used in this document do not have any specific meaning in terms of importance or priority, unless specifically indicated otherwise. The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of the messages or information.

[0029] In existing online education platforms, the client cannot predict the specific number of uploaded images when uploading the answer images of the target test paper, which may result in multiple uploads or missing uploads of images. In addition, the same answer image may be repeatedly uploaded, or the answer image of another test paper may be mistakenly uploaded. Based on this, the present disclosure proposes an answer image acquisition scheme to accurately acquire the answer images of the target test paper to improve the user experience of the online education platform.

[0030] Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0031] Figure 1 A flowchart of an answer image acquisition method according to an exemplary embodiment of the present disclosure is shown in FIG. 1. As shown in the figure, the present embodiment mainly includes the following steps:

[0032] In step S102, a test paper is generated by performing test paper editing according to the given question parameters, layout parameters, and paper size parameters.

[0033] In the present embodiment, the target test paper can include an examination test paper, a homework test paper, etc., for students to perform exercise training or examinations.

[0034] Optionally, the question parameters can include at least the question numbers of each question (also referred to as exercises or test questions) used to compose the target test paper. For example, a question bank can be pre-built to store the question content and type of each question, and a unique question number can be generated for each question.

[0035] In the embodiment, the content of the question can include at least one of text content, table content, and picture content; and the type of the question can include a selection question, a fill-in-the-blank question, a short answer question, and a discussion question.

[0036] Optionally, the layout parameters can include at least font size, line spacing, and character spacing.

[0037] Optionally, the sheet size parameters can include sheet effective length and sheet effective height. The sheet effective length is used to identify the horizontal effective editing size of each sheet in the target test paper, and the sheet effective height is used to identify the vertical effective editing size of each sheet in the target test paper.

[0038] In the embodiment, the sheet effective length and the sheet effective height can be determined by manual editing, or can be automatically determined by setting the sheet specification (for example, A3 or A4 specification).

[0039] In step S104, the image acquisition quantity and the image recognition information are determined according to the target test paper.

[0040] Optionally, according to the generated target test paper, the number of test paper pages contained in the target test paper and the questions contained in each target sheet of the target test paper can be determined, so that the image acquisition quantity of the to-be-acquired answer image can be determined according to the number of test paper pages of the target test paper, and the image recognition information of each to-be-acquired answer image can be determined according to the question numbers corresponding to the questions contained in each target sheet.

[0041] Optionally, the sheet identification code of each target sheet can be generated according to the question numbers corresponding to the questions contained in each target sheet, and the image recognition information of each answer image can be determined according to the sheet identification code of each target sheet.

[0042] Optionally, the sheet identification code can be a question number sequence (i.e., an array) generated by arranging the question numbers corresponding to the questions in the target sheet. For example, according to the question numbers 1, 2, 3, 4, 5, and 6 contained in the target sheet, the sheet identification code in the form of an array {1, 2, 3, 4, 5, 6} is generated.

[0043] Optionally, the sheet identification code of each target sheet can be generated in combination with the question numbers corresponding to the questions contained in each target sheet and the page numbers of each target sheet.

[0044] Optionally, the sheet identification code can also be an identification code (for example, a two-dimensional identification code) generated by converting the question numbers corresponding to the questions in the target sheet.

[0045] Optionally, the volume face identification code corresponding to each target volume face can be edited in a fixed area of each target volume face (for example, a top corner area or a footer area of the target volume face, etc.).

[0046] In step S106, the answer image of the target test paper is acquired according to the image acquisition quantity and the image recognition information.

[0047] Optionally, the answer image of the target test paper can be acquired, and when it is judged that the quantity of the acquired answer image is consistent with the image acquisition quantity, the volume face identification code of each target volume face and the image recognition information of each answer image are compared, so that each acquired answer image corresponds to each target volume face in the target test paper.

[0048] Specifically, the client (for example, the student end) can acquire the target test paper through the online education platform, and print the target test paper offline to answer the questions, wherein the volume face identification code of each target volume face of the target test paper is also printed on each answer sheet to form the image recognition information of each answer sheet (i.e. the subsequent answer image). After completing the answering, the client can acquire the answer image of each answer sheet by scanning or photographing, and upload each acquired answer image to the online education platform. The online education platform can judge whether the quantity of the acquired answer image is consistent with the image acquisition quantity (i.e. the number of test pages of the target test paper), and when it is judged that the two are consistent, the image recognition information of each answer image is further compared with the volume face identification code of each target volume face, and if the comparison result is consistent, the acquisition operation of the answer image is completed, and if the comparison result is not consistent, the client is outputted with a prompt information of answer image uploading error.

[0049] Preferably, if the comparison result is not consistent, the online education platform can further display the answer image in the acquired answer images which has the comparison result not consistent, to prompt the client which answer image uploaded by the client has error, and / or display the target volume face of the target test paper which has not acquired the answer image, so as to prompt the client which target volume face in the target test paper has not uploaded the corresponding answer image.

[0050] In an embodiment, in the case that the recognition accuracy requirement of the answer image is low, the volume face identification code in array form can be used in step S104, and by comparing the volume face identification code (array) of the target volume face and the image recognition information (array) on the answer image in this step, the recognition recall rate of the answer image is determined, and when the recognition recall rate of the answer image exceeds the given recall threshold, the answer image passes the recognition detection.

[0051] For example, if the roll surface identification code of the target roll surface is {1, 2, 3, 4, 5, 6} and the image identification information of the answer image is {1, 2, 8, 4, 6}, it can be determined that the identification recall rate of the answer image is 83.3%, which exceeds the given recall threshold of 80%, and the answer image passes the identification detection.

[0052] In another embodiment, in the case where the identification accuracy of the answer image is required to be higher, the roll surface identification code in the form of an identification code (such as a two-dimensional identification code) can be used in step S104, so that only when the roll surface identification code (two-dimensional code) of the target roll surface and the image identification information (two-dimensional code) on the answer image are exactly the same, the answer image can pass the identification detection (i.e., the recall rate is 100%), and this embodiment has the advantages of fast identification and high identification accuracy.

[0053] In summary, the present embodiment generates a target test paper according to various set paper parameters, and determines the number of image acquisitions of the answer image and the image identification information of each answer image according to the number of test paper pages of the target test paper and the roll surface identification code of each page of the target roll surface. Therefore, the answer image acquisition scheme of the present disclosure can be used to accurately acquire the answer image of the target test paper, so as to effectively avoid the occurrence of abnormal events such as wrong transmission and missing transmission of the answer image, and to improve the product use experience of the user.

[0054] Figure 2 A processing flowchart of an answer image acquisition method of another exemplary embodiment of the present application is shown, and the present embodiment shows a specific implementation of step S102, which mainly includes the following steps:

[0055] Step S202, determining the question content and the question type of each question corresponding to the question number according to the question number in the question parameter.

[0056] For example, the question content and the question type of each question corresponding to the question number can be acquired from the pre-built question bank according to the question number in the question parameter.

[0057] In the present embodiment, the question content can include at least one of text content, table content, and picture content.

[0058] For example, the question content of the question can be represented in the form of a triple structure, such as (char, pic, table).

[0059] Wherein, char is used to identify the number of characters contained in the text content of the question; pic is used to identify the length-width information (L pic , W pic ) of the picture content of the question, and if the current question does not contain picture content, pic is empty; table is used to identify the length-width information (L table , W table), if the current question does not contain table content, the table is empty.

[0060] In step S204, the question height corresponding to each question is determined according to the question content corresponding to each question, the layout parameter, and the effective length of the volume surface in the volume size parameter.

[0061] Optionally, for any one current question in each question, the question height of the current question is calculated according to the question content of the current question, the layout parameter (such as font size, line spacing, and character spacing), and the effective length of the volume.

[0062] In this embodiment, the unit height of the text content, the table content, and the picture content of the current question can be calculated according to the layout parameter and the effective length of the volume, and the question height of the current question is determined according to the sum of the unit heights of the text content, the table content, and the picture content, that is, W Q = W rows + W pic + W table , wherein W Q represents the question height of the current question Q, W rows represents the unit height of the text content of the current question; W pic represents the unit height of the picture content of the current question, and W table represents the unit height of the table content of the current question.

[0063] For example, for the text content part of the question, the editing row number corresponding to the text content can be calculated according to the number of characters contained in the text content, the layout parameter, and the effective length of the volume, which is represented as: rows = a*N / L.

[0064] Wherein, rows represents the editing row number corresponding to the text content, a represents the font size (which can include the character spacing parameter), N represents the number of characters contained in the text content, and L represents the effective length of the volume.

[0065] It should be noted that if the calculation result of the editing row number is a non-integer value, the final editing row number is determined by rounding up, for example, if the calculation result of the editing row number is 5.3, the final editing row number should be 6.

[0066] In this embodiment, the unit height W rows of the text content of the question can be determined according to the editing row number and the line spacing in the layout parameter.

[0067] In the embodiment, the cell height of the picture content and the table content of the question can be set as a fixed parameter or a variable parameter which is dynamically adjusted based on the actual layout parameter and the effective length of the volume surface. The related technical means are well known to those skilled in the art, and thus are not described in detail in the disclosure.

[0068] In step S206, the preferred layout order of each question is determined according to the corresponding question type of each question, the question height of each question, and the effective height of the volume surface in the volume size parameter.

[0069] In the embodiment, the preferred layout order of each question can be determined by performing multiple simulation paper setting corresponding to multiple traversal modes.

[0070] In the embodiment, the traversal mode used can at least include a double-pointer traversal mode and a sequential traversal mode.

[0071] In step S208, the paper setting editing is performed according to the preferred layout order of each question to generate the target test paper.

[0072] Specifically, according to the preferred layout order of each question, the question content corresponding to each question to be set is sequentially obtained and layout edited to generate the target test paper.

[0073] As described above, the paper setting editing can be performed based on the optimal layout order in the embodiment, which not only reduces the number of pages of the target test paper to reduce the number of printed answer sheets, but also correspondingly reduces the number of uploaded answer images to improve the uploading processing efficiency of the answer images and reduce the storage space of the image resources.

[0074] Figure 3 A processing flowchart of a method for obtaining answer images according to another exemplary embodiment of the present application is shown, which shows a specific implementation of step S206 described above, and mainly includes the following processing steps:

[0075] In step S302, the preferred height of the volume surface of the target test paper is determined according to the question height of each question and the effective height of the volume surface.

[0076] Optionally, the theoretical number of pages of the target test paper is calculated according to the question height of each question and the effective height of the volume surface, and the preferred height of the volume surface of the target test paper is determined according to the theoretical number of pages and the question height of each question.

[0077] In the embodiment, the theoretical number of pages of the target test paper can be calculated according to the question height of each question and the effective height of the volume surface by using the following formula 1:

[0078]

[0079] In the above formula 1, E represents the theoretical page number of the target test paper, W aQi represents the question height of the i-th question of type a, and n1 represents the number of questions of type a; W bQi represents the question height of the i-th question of type b, and n2 represents the number of questions of type b; W cQi represents the question height of the i-th question of type c, and n3 represents the number of questions of type c; and L represents the effective height of the paper surface.

[0080] In the present embodiment, if the calculation result of the theoretical page number E of the target test paper is a non-integer value, the theoretical page number is updated by rounding up, for example, if the calculation result of the theoretical page number E is 4.5, the finally determined theoretical page number should be 5.

[0081] In the present embodiment, the optimal height of the paper surface of the target test paper can be calculated according to the theoretical page number of the target test paper and the question height corresponding to each question by using the following formula 2.

[0082]

[0083] In the above formula 2, W E represents the optimal height of the paper surface of the target test paper, E represents the theoretical page number of the target test paper, W aQi represents the question height of the i-th question of type a, and n1 represents the number of questions of type a; W bQi represents the question height of the i-th question of type b, and n2 represents the number of questions of type b; W cQi represents the question height of the i-th question of type c, and n3 represents the number of questions of type c.

[0084] In step S304, according to the question type corresponding to each question, the question height corresponding to each question, and the optimal height of the paper surface, multiple simulation paper setting is performed corresponding to multiple traversal modes to determine the simulation layout order corresponding to each traversal mode and multiple simulation paper surface heights.

[0085] Optionally, the multiple traversal modes used in the present embodiment at least include a double-pointer traversal mode and a sequential traversal mode.

[0086] Optionally, according to different traversal modes, various simulation layout orders corresponding to each traversal mode can be determined, and simulation paper setting of each question is performed based on each simulation layout order, so as to determine multiple simulation paper surface heights of each traversal mode.

[0087] In the embodiment, each simulation paper height of any one traversal mode is used to identify the generated simulation paper editing height corresponding to each simulation paper after the simulation paper is generated according to the simulation layout sequence of the traversal mode, and therefore, the number of simulation paper heights should be the same as the number of pages of the simulation paper.

[0088] In step S306, according to each simulation paper height of each traversal mode and the paper preferred height, one of the simulation layout sequences is determined as the preferred layout sequence of each question.

[0089] Alternatively, according to each simulation paper height of each traversal mode and the paper preferred height, variance calculation is performed to determine the variance value of each traversal mode, and according to the variance value of each traversal mode, the simulation layout sequence of the traversal mode with the smallest variance value is determined as the preferred layout sequence of each question.

[0090] In the embodiment, for any one current traversal mode in each traversal mode, formula 3 is used to perform variance calculation according to each simulation paper height of the current traversal mode and the paper preferred height to determine the variance value of the current traversal mode.

[0091]

[0092] Wherein, N i represents the i th simulation paper height of the current traversal mode (or represents the paper editing height of the i th page simulation paper generated by the current traversal mode), m represents that the current traversal mode contains m simulation paper heights (or represents that the current traversal mode generates m pages of simulation paper), W E represents the paper preferred height.

[0093] In summary, the answer image acquisition method of the embodiment determines multiple simulation layout sequences by using multiple traversal modes, and performs multiple simulation paper generation based on each simulation layout sequence, so as to determine the preferred layout sequence according to the simulation paper generation result, which can be beneficial to subsequent generation of target test paper with fewer pages, and can reduce the number of uploaded answer images.

[0094] Further, the embodiment determines the paper preferred height of the target test paper by calculating the theoretical number of pages of the target test paper, so as to realize uniform distribution of each paper height in the target test paper and improve the overall layout of the test paper.

[0095] Figure 4 A processing flowchart of an answer image acquisition method of another example embodiment of the disclosure is shown, which is a specific implementation of step S304, and mainly includes the following steps:

[0096] In step S402, any one of the traversal modes is determined as the current traversal mode.

[0097] In the embodiment, the traversal mode at least includes a double-pointer traversal mode and a sequential traversal mode.

[0098] In step S404, according to the question types corresponding to the questions and the question heights, the questions are traversed by using the current traversal mode, and according to the traversal order of the questions, the simulation layout order of the questions in the current traversal mode is determined.

[0099] Optionally, the question type determination step can be executed to determine one of the question types as the current question type, and determine the questions corresponding to the current question type as the current questions, and according to the question heights corresponding to the current questions, the current questions are traversed by using the current traversal mode until each current question is traversed, and the question type determination step is repeatedly executed until each question type is determined as the current question type, and according to the traversal order of the questions, the simulation layout order of the questions in the current traversal mode is determined.

[0100] In an embodiment, in the case that the current traversal mode is the double-pointer traversal mode, according to the question heights corresponding to the current questions, one of the current questions with the maximum question height and one of the current questions with the minimum question height are alternately traversed from the current questions that have not been traversed until each current question is traversed.

[0101] For example, if the question heights corresponding to the current questions are represented as {5, 12, 4, 8, 6}, the traversal order of the current questions by using the double-pointer traversal mode is {12, 4, 8, 5, 6}, which is the simulation layout order of the current questions in the double-pointer traversal mode.

[0102] In another embodiment, in the case that the current traversal mode is the sequential traversal mode, according to the question heights corresponding to the current questions, each current question is sequentially traversed in descending order or ascending order until each current question is traversed.

[0103] For example, if the question heights corresponding to the current questions are represented as {5, 12, 4, 8, 6}, the traversal order of the current questions in descending order is {12, 8, 6, 5, 4}, and the traversal order of the current questions in ascending order is {4, 5, 6, 8, 12}, and any one of the above traversal orders is the simulation layout order of the current questions in the sequential traversal mode.

[0104] In step S406, according to the simulation layout order of the questions in the current traversal mode, the question heights corresponding to the questions, and the cover height, simulation paper setting is executed to obtain multiple simulation cover heights of the current traversal mode.

[0105] Specifically, based on the simulated layout order of each question, the height of each question, and the preferred height of the paper, a simulated paper assembly can be performed to obtain the simulated paper assembly result of the current traversal mode. Based on the simulated paper assembly result of the current traversal mode, the height of multiple simulated paper surfaces in the current traversal mode can be determined.

[0106] In this embodiment, the height of each simulated page in the current traversal mode can be identified as {N1, N2, ..., N...} n}, where N1 represents the height of the first simulated page of the current traversal mode (or can be regarded as the height of the simulated page of the first page generated based on the current traversal mode); N2 represents the height of the second simulated page of the current traversal mode (or can be regarded as the height of the simulated page of the second page generated based on the current traversal mode), and so on.

[0107] In summary, this embodiment utilizes multiple traversal methods to achieve various simulated layout orders, and performs simulated test paper assembly operations based on each different simulated layout order to obtain multiple simulated test paper heights under each simulated layout order. This facilitates the subsequent determination of an optimal layout order from among the simulated layout orders, thereby improving the test paper assembly layout effect.

[0108] Figure 5 This is a flowchart illustrating a method for obtaining answer images according to another exemplary embodiment of the present disclosure. This embodiment shows a specific implementation of step S406 above, which mainly includes the following processing steps:

[0109] Step S502: Determine the initial setting value of the current editing height.

[0110] In this embodiment, the initial setting value of the current editing height can be determined based on the preferred height of the paper or by manual setting.

[0111] Step S504: According to the simulated layout order of each question, obtain one question in the pending editing state as the question to be edited.

[0112] Specifically, according to the simulated layout order of each topic determined in step S404 above, a topic can be obtained in sequence as the topic to be edited.

[0113] Step S506: Determine whether the sum of the height of the question to be edited and the current editing height is greater than the preferred height of the paper. If yes, proceed to step S508; otherwise, proceed to step S510.

[0114] Specifically, the sum of the question height of the to-be-edited question and the current editing height is compared with the preferred height of the paper surface. If the sum is greater than the preferred height of the paper surface, step S508 is performed, and if the sum is not greater than the preferred height of the paper surface, step S510 is performed.

[0115] In step S508, the current editing height is determined as a simulated paper surface height of the current traversal mode, and the current editing height is initialized.

[0116] Specifically, if the sum of the question height of the to-be-edited question and the current editing height is greater than the preferred height of the paper surface, it means that the remaining editing height in the current editing paper surface is insufficient (the remaining editing height in the current editing paper surface is less than the question height of the to-be-edited question), and the paging operation of the simulated paper is performed to determine the current editing height as a simulated paper surface height of the current traversal mode, and the current editing height is restored to the initial set value.

[0117] In step S510, the to-be-edited question is updated to the edited state, and the current editing height is updated according to the sum.

[0118] Specifically, if the sum of the question height of the to-be-edited question and the current editing height is not greater than the preferred height of the paper surface, it means that there is sufficient remaining editing height in the current editing paper surface, and the editing of the to-be-edited question is performed in the current editing paper surface, the to-be-edited question is updated from the to-be-edited state to the edited state, and the current editing height of the current editing paper surface is updated according to the sum of the question height of the to-be-edited question and the current editing height.

[0119] In step S512, it is judged whether each question is updated to the edited state. If yes, the flow is ended, and if no, step S504 is continuously performed.

[0120] Specifically, if it is judged that each question is updated to the edited state, it means that the simulated paper operation of all questions has been completed, and the flow is ended, otherwise, step S504 is returned to sequentially obtain the next question in the to-be-edited state, and the simulated paper operation is continuously performed.

[0121] In summary, the answer image acquisition method provided in the embodiment is based on the determined preferred height of the paper surface, and the simulated paper operation in each traversal mode is performed to accurately acquire each simulated paper result corresponding to each traversal mode, which can be beneficial to accurately determining the preferred layout order of each question type in the subsequent process, thereby generating a target test paper with fewer paper surfaces.

[0122] Figure 6 A processing flowchart of an answer image submission method of an example embodiment of the disclosure is shown. As shown in the figure, the embodiment mainly includes the following steps:

[0123] Step S602, obtaining a target test paper of an online education platform.

[0124] Specifically, the client (such as a notebook computer, a desktop computer, a tablet, a mobile phone, or the like) can log in the online education platform to obtain the target test paper.

[0125] For example, the student can log in a test paper obtaining interface (not shown) of the online education platform via the client, obtain the target test paper, and print the target test paper offline to obtain multiple answer sheets of the target test paper, and perform the test paper answering work. Each answer sheet obtained by printing should be one-to-one corresponding to each target test paper page, that is, the number of answer sheets should be the same as the number of target test paper pages. For example, if the target test paper contains 4 target test paper pages, the answer sheets should also be 4.

[0126] Step S604, submitting multiple answer images of the target test paper satisfying the image acquisition quantity of the target test paper given by the online education platform to the online education platform.

[0127] In this embodiment, the image acquisition quantity of the target test paper is determined by using the answer image acquisition method shown in any one of the above embodiments. Figures 1 to 5

[0128] Specifically, after completing the test paper answering work, the client can log in an answer image submission interface of the online education platform, obtain and submit the answer images of each answer sheet by scanning or photographing, until the submission quantity of the answer images matches the image acquisition quantity of the target test paper given by the answer image submission interface. For example, if the target test paper contains 4 target test paper pages, the image acquisition quantity of the target test paper is 4, and correspondingly, the submission quantity of the answer images should also be 4.

[0129] For example, referring to Figures 7A to 7F After completing the test paper answering work, the client can log in the answer image submission interface 700 of the online education platform. The online education platform can prompt the image acquisition quantity of the target test paper in the answer image submission interface 700 according to the target test paper obtained by the client (for example, referring to the prompt window 701 of Figure 7A and Figure 7B The client can trigger the submission key 702 in the answer image submission interface 700, and submit the corresponding number of answer images to the online education platform according to the image acquisition quantity prompted in the answer image submission interface 700 (for example, referring to Figure 7B ).

[0130] ​Optionally, based on the number of images of the target test paper acquired, a corresponding number of prompt boxes can be displayed in the answer image submission interface 700 to indicate the progress of the answer image submission.

[0131] For example, in Figures 7C to 7F In the illustrated embodiment, if the target exam paper image acquisition quantity is 4 pages, then 4 corresponding prompt boxes 703a to 703d can be displayed on the answer image submission interface 700 to specifically indicate the number of answer images that have been submitted (or uploaded) and the number of answer images to be submitted (or uploaded). Figure 7C and Figure 7D The diagram shows the application of two submitted answer images (refer to prompt boxes 703a and 703b) and two pending answer images (refer to prompt boxes 703c and 703d). Figure 7E and Figure 7F This is an application illustration showing that all answer images have been submitted.

[0132] In summary, the answer image submission method provided in this embodiment can submit multiple answer images of the target test paper to the online education platform, matching the number of images to be acquired, thereby effectively avoiding the situation of over-transmission or under-transmission of answer images and improving the user experience.

[0133] Figure 8 A schematic diagram of the architecture of an answer image acquisition device according to an exemplary embodiment of the present disclosure is shown. As shown, the answer image acquisition device 800 of this embodiment includes a generation module 802, a determination module 804, and an acquisition module 806.

[0134] Optionally, the answer image acquisition device 800 of this embodiment can be applied to the server side of an online education platform. The answer image acquisition device 800 may include, but is not limited to, electronic devices such as network servers and cloud servers.

[0135] The generation module 802 is used to perform test paper editing and generate the target test paper based on the given question parameters, layout parameters, and paper size parameters.

[0136] The determining module 804 is used to determine the number of images to be acquired and the image recognition information based on the target test paper.

[0137] The acquisition module 806 is used to acquire the answer image of the target test paper based on the number of images acquired and the image recognition information.

[0138] Optionally, the generating module 802 is further configured to: determine, according to each question number in the question parameter, a question content and a question type of a question corresponding to each question number; determine, according to each question content corresponding to each question, the layout parameter, and a valid length of the roll surface in the roll size parameter, a question height corresponding to each question; determine, according to each question type corresponding to each question and each question height, and a valid height of the roll surface in the roll size parameter, an optimal layout order of each question; and perform paper setting editing according to the optimal layout order of each question, to generate the target test paper; wherein the question content comprises at least one of a text content, a table content, and a picture content.

[0139] Optionally, the generating module 802 is further configured to: determine, according to each question height corresponding to each question and the valid height of the roll surface, a roll surface optimal height of the target test paper; perform multiple times of simulated paper setting corresponding to multiple traversal modes according to each question type corresponding to each question and each question height and the roll surface optimal height, to determine a simulated layout order corresponding to each traversal mode and multiple simulated roll surface heights; and determine one of the simulated layout orders as the optimal layout order of each question according to each simulated roll surface height of each traversal mode and the roll surface optimal height.

[0140] Optionally, the generating module 802 is further configured to: determine any one of the traversal modes as a current traversal mode; traverse each question according to each question type corresponding to each question and each question height by using the current traversal mode, and determine a simulated layout order of each question in the current traversal mode according to a traversal order of each question; and perform simulated paper setting according to the simulated layout order of each question in the current traversal mode, each question height corresponding to each question, and the roll surface optimal height, to obtain multiple simulated roll surface heights of the current traversal mode.

[0141] Optionally, the generating module 802 is further configured to: perform a question type determination step, determine one of each question type as a current question type, and determine each question corresponding to the current question type as each current question; traverse each current question according to each question height corresponding to each current question by using the current traversal mode, until each current question is traversed; repeat the question type determination step until each question type is determined as the current question type; and determine a simulated layout order of each question in the current traversal mode according to a traversal order of each question.

[0142] Optionally, the generating module 802 is further configured to: in a case where the current traversal mode is the double-pointer traversal mode, traverse, according to each question height corresponding to each current question, a current question with a maximum question height and a current question with a minimum question height alternately from each current question that has not been traversed, until each current question is traversed.

[0143] Optionally, the generating module 802 is further configured to: in a case where the current traversal mode is the sequential traversal mode, sequentially traverse each current question according to the question heights of the respective current questions in descending order or ascending order until each current question is traversed.

[0144] Optionally, the generating module 802 is further configured to: determine an initial setting value of the current editing height; a question obtaining step, sequentially obtain a question in an unedited state as an edited question according to the simulated layout order of the respective questions; compare a sum of the question height of the edited question and the current editing height with the preferred height of the paper surface, if the sum is greater than the preferred height of the paper surface, determine the current editing height as a simulated paper surface height of the current traversal mode, and initialize the current editing height; if the sum is not greater than the preferred height of the paper surface, update the edited question to an edited state, and update the current editing height according to the sum; continue to execute the question obtaining step until each question is updated to the edited state.

[0145] Optionally, the generating module 802 is further configured to: perform variance calculation according to the simulated paper surface height of each traversal mode and the preferred height of the paper surface, to determine a variance value of each traversal mode; and determine the simulated layout order of the traversal mode with the minimum variance value as the preferred layout order of the respective questions according to the variance value of each traversal mode.

[0146] Optionally, the determining module 804 is further configured to: determine the number of image acquisition of the answer image according to the number of pages of the target test paper; and determine the image recognition information of each answer image according to the respective question numbers corresponding to the respective questions contained in each target paper surface.

[0147] Optionally, the determining module 804 is further configured to: generate a paper surface identification code of each target paper surface according to the respective question numbers corresponding to the respective questions contained in each target paper surface; and determine the image recognition information of each answer image according to the paper surface identification code of each target paper surface.

[0148] Figure 9 An architecture schematic diagram of a question image submission device of an exemplary embodiment of the present disclosure is shown. As shown in the figure, the question image submission device 900 of the present embodiment includes a test paper obtaining module 902 and an image submission module 904.

[0149] Optionally, the question image submission device 900 of the present embodiment can be applied to a client of an online education platform, and the question image submission device 900 can include, but is not limited to, an electronic device such as a tablet computer, a mobile phone, a notebook computer, etc.

[0150] The test paper obtaining module 902 is configured to obtain a target test paper of an online education platform.

[0151] The image submitting module 904 is configured to submit, to the online education platform, a plurality of answer images of the target test paper that satisfy an image acquisition quantity of the target test paper given by the online education platform.

[0152] In this embodiment, the image acquisition quantity of the target test paper is determined by using the answer image acquisition method shown in any one of the above Figures 1 to 5 embodiments, or by using the answer image acquisition device shown in the above Figure 8 embodiments.

[0153] The non-transitory computer-readable storage medium storing computer instructions is provided in the embodiments of the present disclosure, and the computer instructions are used to make the computer execute the answer image acquisition method described in the exemplary embodiments of the present disclosure.

[0154] The electronic device provided in the exemplary embodiments of the present disclosure includes at least one processor and a memory connected with the at least one processor in communication. The memory stores computer programs that can be executed by the at least one processor, and the computer programs, when executed by the at least one processor, are used to make the electronic device execute the answer image acquisition method according to the exemplary embodiments of the present disclosure.

[0155] For more details, please refer to Figure 10 The structural block diagram of the electronic device 1000 that can be a server or a client of the present disclosure will be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections, and relationships, and their functions, are merely examples and are not intended to limit implementations of the present disclosure described and / or claimed herein.

[0156] As shown in Figure 10As shown, the electronic device 1000 includes a computing unit 1001 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded into a random access memory (RAM) 1003 from a storage unit 1008. Various programs and data required for the operation of the device 1000 can also be stored in the RAM 1003. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0157] A plurality of components in the electronic device 1000 are connected to the I / O interface 1005, including an input unit 1006, an output unit 10010, a storage unit 1008, and a communication unit 1009. The input unit 1006 can be any type of device that can input information to the electronic device 1000, and can receive inputted digital or character information, and generate key signal inputs related to user settings and / or function controls of the electronic device. The output unit 10010 can be any type of device that can present information, and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 1008 can include, but is not limited to, a magnetic disk, an optical disk. The communication unit 1009 allows the electronic device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0158] The computing unit 1001 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1001 performs various methods and processes described above. For example, in some embodiments, the answer image acquisition method or the answer image submission method described above can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 1000 via the ROM 1002 and / or the communication unit 1009. In some embodiments, the computing unit 1001 can be configured to perform the answer image acquisition method or the answer image submission method described above by any other appropriate means, such as by means of firmware.

[0159] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can be embodied entirely on a machine, partially on a machine, fully on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0160] In the context of the present disclosure, a machine-readable medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine- readable storage medium can be any tangible medium that can be used to store or transfer data or instructions for use by or in connection with the instruction execution system, apparatus, or device. The machine-readable storage medium can be a machine-readable storage medium such as one or more wireline, portable, and / or fixed storage devices including, but not limited to, optical-, semiconductor-, and / or magnetic- based memory and / or storage devices, and / or any suitable combination thereof. A machine-readable signal medium can be any tangible medium that is capable of storing or transferring data or instructions for use by or in connection with the instruction execution system, apparatus, or device.

[0161] As used in the present disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus and / or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal that can be used to provide machine instructions and / or data to a programmable processor.

[0162] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0163] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0164] The computer system can include clients and servers. This description uses the terms "client" and "server" to describe the roles of these computers in the interactions

[0165] It should be noted that, according to the needs of implementation, each component / step described in the embodiments of the present disclosure can be split into more components / steps, or two or more components / steps or partial operations of the components / steps can be combined into a new component / step, to achieve the purpose of the embodiments of the present disclosure.

[0166] The above embodiments are only used to illustrate but not to limit the present disclosure. Those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure. Therefore, the patent protection scope of the present disclosure should be defined by the claims.

Claims

1. A method for obtaining an answer image, characterized by, The method comprises the following steps: According to the question number in the given question parameters, determine the question content and question type corresponding to each question number; According to the question content corresponding to each question, the layout parameters, and the effective length of the paper size parameters, determine the height of each question corresponding to each question; according to the height of each question corresponding to each question, the effective height of the paper size parameters, determine the optimal height of the paper surface of the target test paper; according to the question type corresponding to each question, the height of each question, and the optimal height of the paper surface, execute multiple times of simulated paper setting corresponding to multiple traversal modes to determine the simulated layout sequence and multiple simulated paper surface heights corresponding to each traversal mode; according to the simulated paper surface height of each traversal mode and the optimal height of the paper surface, execute variance calculation to determine the variance value of each traversal mode; according to the variance value of each traversal mode, determine the simulated layout sequence of the traversal mode with the smallest variance value as the optimal layout sequence of each question; execute paper setting editing according to the optimal layout sequence of each question to generate the target test paper; According to the target test paper, determine the image acquisition quantity and image recognition information; According to the image acquisition quantity and the image recognition information, acquire the answer image of the target test paper.

2. The answer image acquisition method according to claim 1, wherein The question content includes at least one of text content, table content, and picture content.

3. The answer image acquisition method according to claim 2, characterized in that, The step of executing multiple times of simulated paper setting corresponding to multiple traversal modes according to the question type corresponding to each question and the height of each question and the optimal height of the paper surface to determine the simulated layout sequence and multiple simulated paper surface heights corresponding to each traversal mode comprises: Determine any one of the traversal modes as the current traversal mode; According to the question type corresponding to each question and the height of each question, traverse each question using the current traversal mode, and according to the traversal order of each question, determine the simulated layout sequence of each question in the current traversal mode; According to the simulated layout sequence of each question in the current traversal mode, the height of each question corresponding to each question, and the optimal height of the paper surface, execute simulated paper setting to obtain multiple simulated paper surface heights of the current traversal mode.

4. The answer image acquisition method according to claim 3, characterized in that, The step of traversing each question using the current traversal mode according to the question type corresponding to each question and the height of each question, and determining the simulated layout sequence of each question in the current traversal mode according to the traversal order of each question comprises: The question type determination step determines one of the question types as the current question type, and determines the questions corresponding to the current question type as the current questions; According to the height of each current question, traverse each current question using the current traversal mode until each current question is traversed; Repeat the question type determination step until each question type is determined as the current question type; According to the traversal order of each question, determine the simulated layout sequence of each question in the current traversal mode.

5. The answer image acquisition method according to claim 4, characterized in that, The current traversal mode at least includes a double-pointer traversal mode and a sequential traversal mode; In a case where the current traversal mode is the double-pointer traversal mode, the traversing each current question according to the question height of each current question by using the current traversal mode comprises: alternately traversing a current question with the maximum question height and a current question with the minimum question height from the current questions that have not been traversed according to the question height of each current question until each current question is traversed; In a case where the current traversal mode is the sequential traversal mode, the traversing each current question according to the question height of each current question by using the current traversal mode comprises: sequentially traversing each current question according to the question height of each current question in descending order or ascending order until each current question is traversed.

6. The answer image acquisition method according to claim 3, characterized in that, The simulating paper setting according to the simulated layout order of each question, the question height of each question, and the preferred paper height in the current traversal mode comprises: determining an initial setting value of the current editing height; a question obtaining step of sequentially obtaining a question in the to-be-edited state as a to-be-edited question according to the simulated layout order of each question; comparing the sum of the question height of the to-be-edited question and the current editing height with the preferred paper height, determining the current editing height as a simulated paper height of the current traversal mode and initializing the current editing height if the sum is greater than the preferred paper height, and updating the to-be-edited question to the edited state and updating the current editing height according to the sum if the sum is not greater than the preferred paper height; continuously performing the question obtaining step until each question is updated to the edited state.

7. The answer image acquisition method according to any one of claims 1 to 2, characterized by, The determining the image acquisition quantity and the image recognition information according to the target test paper comprises: determining the image acquisition quantity of the answer image according to the number of pages of the target test paper; determining the image recognition information of each answer image according to the question number corresponding to each question included in each target paper surface in the target test paper.

8. The answer image acquisition method according to claim 7, characterized in that, The determining the image recognition information of each answer image according to the question number corresponding to each question included in each target paper surface in the target test paper comprises: generating a paper surface identification code of each target paper surface according to the question number corresponding to each question included in each target paper surface; determining the image recognition information of each answer image according to the paper surface identification code of each target paper surface.

9. A method of submitting an answer image, characterized by, comprises: obtaining a target test paper of an online education platform; submitting a plurality of answer images of the target test paper satisfying the image acquisition quantity of the target test paper to the online education platform according to the image acquisition quantity of the target test paper given by the online education platform; wherein the image acquisition quantity of the target test paper is determined by using the answer image acquisition method in any one of claims 1 to 8.

10. A test image acquisition apparatus for implementing the test image acquisition method according to claim 1, characterized by, comprises: a generation module configured to determine the question content and the question type of each question corresponding to each question number according to each question number in the given question parameter; According to the corresponding question content, layout parameters, and the effective length of the volume size parameters, determine the height of each question; according to the height of each question, the effective height of the volume size parameters, determine the optimal height of the target test paper; according to the corresponding question type and the height of each question, the optimal height, execute multiple times of simulated paper setting corresponding to multiple traversal modes to determine the simulated layout order and multiple simulated volume heights corresponding to each traversal mode; according to the simulated volume height of each traversal mode, the optimal height, determine one of the simulated layout order as the optimal layout order of each question, and execute paper setting editing according to the optimal layout order of each question to generate the target test paper; The determining module is configured to determine the image acquisition quantity and image recognition information according to the target test paper; The obtaining module is configured to obtain the answer image of the target test paper according to the image acquisition quantity and the image recognition information.

11. A solution image submitting apparatus characterized by comprising: Comprise: Test paper obtaining module, for obtaining the target test paper of online education platform; Image submission module, for submitting multiple answer images of the target test paper to the online education platform according to the image acquisition quantity of the target test paper given by the online education platform; Wherein, the image acquisition quantity of the target test paper is determined by using the answer image acquisition method of any one of claims 1 to 8 or using the answer image acquisition device of claim 10.

12. An electronic device comprising: a processor; and a memory storing a program, wherein the program includes instructions that, when executed by the processor, cause the processor to perform the answer image acquisition method according to any one of claims 1-8, or perform the answer image submission method according to claim 9.

13. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to make the computer execute the answer image acquisition method according to any one of claims 1-8, or execute the answer image submission method according to claim 9.

Images