Examination paper question automatic positioning method and device based on scanned image region mapping, electronic equipment and computer readable storage medium

Abstract

The application discloses a kind of based on scanning image area mapping's reading paper subject automatic positioning method, device, electronic equipment and computer readable storage medium, comprising: obtaining the scanning image of target answer sheet or target paper, and the reading positioning metadata corresponding to each question in scanning image;Get the display parameter of scanning image in reading interface, and according to display parameter, determine the page code corresponding to each question in the page corresponding to the page code currently displayed in reading interface, the question hit area corresponding to reading interface under;Get the current position information of cursor in reading interface, judge whether current position information falls in certain question hit area;If yes, then drive the target scoring component corresponding to question hit area in the correction panel to produce response.Therefore, by establishing the space mapping relationship between scanning image and correction panel, automatic driving scoring component linkage response is realized when cursor operates on paper image.

Description

Technical Field

[0001] This application relates to the technical field of educational informatization and intelligent marking, and more specifically, to a method, device, electronic device and computer-readable storage medium for automatic positioning of marking questions based on scanned image region mapping. Background Technology

[0002] In paper-based exam scanning and grading scenarios, the answer sheets or exam papers completed by candidates are typically scanned into images. Graders then view these images in the grading system and enter scores or add annotations in the grading panel based on the question numbers. In related technologies, the grading system usually separates the scanned image display area from the grading panel. Graders need to simultaneously view the exam image and manually locate the corresponding question number in the grading panel before grading.

[0003] Due to insufficient linkage between the test paper image display area and the scoring panel, the reliance on manual searching of the target question in the test paper image to find the corresponding question number in the scoring panel is inefficient and prone to incorrect scoring. Summary of the Invention

[0004] In view of the above problems, this application proposes a method, device, electronic device and computer-readable storage medium for automatic location of marking questions based on scanned image region mapping, which can solve the above problems.

[0005] In a first aspect, embodiments of this application provide an automatic question location method for marking based on scanned image region mapping. The method includes: acquiring a scanned image of a target answer sheet or test paper, and marking location metadata corresponding to each question in the scanned image; the marking location metadata includes at least the page number, question number, and region coordinate information of the answer area; acquiring display parameters of the scanned image in the marking interface, and determining, based on the display parameters, the region coordinate information corresponding to each question on the page currently displayed in the marking interface, and the corresponding question hit area in the marking interface; acquiring the current position information of the cursor in the marking interface, and determining whether the current position information falls within the target question hit area; if so, driving the target scoring component corresponding to the target question hit area in the marking panel to generate a response, the response including at least one of scrolling the marking panel to the position of the target scoring component, highlighting the question number identifier corresponding to the target scoring component, or setting the scoring input box corresponding to the target scoring component to a focused state.

[0006] Secondly, embodiments of this application also provide an automatic marking question positioning device based on scanned image region mapping. The device includes: an acquisition module, used to acquire a scanned image of a target answer sheet or target exam paper, and marking positioning metadata corresponding to each question in the scanned image; the marking positioning metadata includes the answer sheet code, page number, question number, question type, question score, and region coordinate information to which the answer area belongs; a determination module, used to acquire display parameters of the scanned image in the marking interface, and determine, based on the display parameters, the question hit area corresponding to the region coordinate information of each question in the scanned image under the marking interface; a judgment module, used to acquire the current position information of the cursor in the marking interface, and determine whether the current position information falls within the target question hit area; and a driving module, used to, if so, drive the target scoring component corresponding to the target question hit area in the marking panel to generate a response, the response including at least one of scrolling the marking panel to the position of the target scoring component, highlighting the question number identifier corresponding to the target scoring component, or setting the scoring input box corresponding to the target scoring component to a focused state.

[0007] Thirdly, embodiments of this application also provide an electronic device, including a processor, a memory, and one or more application programs; the one or more application programs are stored in the memory and configured to be executed by the processor to implement the above-described method for automatically locating marking questions based on scanned image region mapping.

[0008] Fourthly, embodiments of this application also provide a computer-readable storage medium storing program code, wherein the above-mentioned automatic positioning method for marking questions based on scanned image region mapping is executed when the program code is run by a processor.

[0009] The technical solution provided in this application includes the following method: acquiring a scanned image of a target answer sheet or target test paper, and marking positioning metadata corresponding to each question in the scanned image; the marking positioning metadata includes at least the page number, question number, and area coordinate information of the answer area; acquiring the display parameters of the scanned image in the marking interface, and determining the area coordinate information corresponding to each question in the page currently displayed in the marking interface, and the corresponding question hit area in the marking interface based on the display parameters; acquiring the current position information of the cursor in the marking interface, and determining whether the current position information falls within the target question hit area; if so, driving the target scoring component corresponding to the target question hit area in the marking panel to generate a response, the response including scrolling the marking panel to the position of the target scoring component, highlighting the question number identifier corresponding to the target scoring component, or setting the scoring input box corresponding to the target scoring component to a focused state, at least one of these. Therefore, by acquiring the marking location metadata of each question in the scanned image and converting the area coordinate information into the question hitting area according to the display parameters of the marking interface, a spatial mapping relationship between the scanned image and the marking panel is established. When the cursor is detected to fall into the hitting area of ​​a target question, the system automatically drives the corresponding scoring component in the marking panel to generate responses such as scrolling, highlighting, or focusing. This eliminates the need for marking teachers to manually search for the corresponding question number in the scoring panel, thus solving the problems of insufficient linkage between the scanned image display area and the scoring panel, low efficiency due to reliance on manual question number search, and the scoring of easily mistaken questions. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments and drawings obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0011] Figure 1 The illustration shows a flowchart of an automatic question location method for marking examination papers based on scanned image region mapping, provided in an embodiment of this application.

[0012] Figure 2 This illustration shows a schematic diagram of an automatic question location device for marking papers based on scanned image region mapping, provided in an embodiment of this application.

[0013] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0014] Figure 4 This illustration shows a schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of this application. Detailed Implementation

[0015] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0016] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0017] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0018] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0019] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0020] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0021] In paper-based exam scanning and grading scenarios, the answer sheets or exam papers completed by candidates are typically scanned into images. Graders then view these images in the grading system and enter scores or add annotations in the grading panel based on the question numbers. In related technologies, grading systems usually separate the exam paper image display area from the grading panel. Graders need to simultaneously view the exam paper image and manually locate the corresponding question number in the grading panel before performing the grading operation.

[0022] When the number of questions on the exam paper is small and the page structure is simple, manually searching for question numbers is acceptable. However, in scenarios involving multi-page answer sheets, combined questions, subjective questions spanning multiple pages, column-based answer areas, or grading the entire exam paper, the answer areas on the exam paper image and the question numbers on the scoring panel are not always intuitively correlated. Graders need to frequently switch their attention between the image area and the scoring panel, which can easily lead to problems such as slow question finding, inaccurate location, incorrect question numbers, missed grading, or duplicate scoring.

[0023] Furthermore, exam paper images are typically processed through scaling, panning, page stitching, or rotation correction in the grading interface. Relying solely on the original page coordinates or manual visual judgment makes it difficult to accurately determine the specific question area corresponding to the current mouse position. This is especially true for combined sub-questions and questions spanning multiple pages, where the answer areas may be distributed across different pages or different image fragments, further increasing the complexity of question location and grading operations.

[0024] Therefore, the marking system has problems such as reliance on manual question location, insufficient linkage between image areas and scoring panels, low location efficiency in complex question types and multi-page scenarios, and easy to award marks for incorrect questions.

[0025] To address the aforementioned issues, this application provides a method, apparatus, electronic device, and computer-readable storage medium for automatic question location in exam marking based on scanned image region mapping. The method includes: acquiring a scanned image of a target answer sheet or exam paper, and marking location metadata corresponding to each question in the scanned image; the marking location metadata includes at least the page number, question number, and region coordinate information of the answer area; acquiring display parameters of the scanned image in the marking interface, and determining, based on the display parameters, the region coordinate information corresponding to each question on the page currently displayed in the marking interface, and the corresponding question hit area in the marking interface; acquiring the current position information of the cursor in the marking interface, and determining whether the current position information falls within the target question hit area; if so, driving a target scoring component in the marking panel corresponding to the target question hit area to respond, the response including at least one of scrolling the marking panel to the position of the target scoring component, highlighting the question number identifier corresponding to the target scoring component, or setting the scoring input box corresponding to the target scoring component to a focused state.

[0026] Therefore, by acquiring the marking location metadata of each question in the scanned image and converting the area coordinate information into the question hitting area according to the display parameters of the marking interface, a spatial mapping relationship between the scanned image and the marking panel is established. When the cursor is detected to fall into the hitting area of ​​a target question, the system automatically drives the corresponding scoring component in the marking panel to generate responses such as scrolling, highlighting, or focusing. This eliminates the need for marking teachers to manually search for the corresponding question number in the scoring panel, thus solving the problems of insufficient linkage between the scanned image display area and the scoring panel, low efficiency due to reliance on manual question number search, and the scoring of easily mistaken questions.

[0027] This invention provides an automatic question location method for marking examination papers based on scanned image region mapping. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, this automatic question location method based on scanned image region mapping can be executed by software or hardware installed on a terminal device or a server device. The software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cluster of cloud servers. The server can be an independent server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0028] Please see Figure 1 , Figure 1 This illustration shows a flowchart of an automatic question location method for marking exam papers based on scanned image region mapping, provided in an embodiment of this application. Figure 1 As shown, the method may include steps 110 to 140.

[0029] In step 110, a scanned image of the target answer sheet or the target test paper is obtained, along with the marking location metadata corresponding to each question in the scanned image. The marking location metadata includes at least the page number, question number, and area coordinate information of the answer area.

[0030] Scanned images can be image files generated by scanning paper answer sheets or exam papers using a scanning device, or image files generated by photographing paper answer sheets or exam papers using a photographing device. The scanning device can be a high-speed scanner or flatbed scanner, and the photographing device can be a mobile phone camera or a document camera.

[0031] The system can receive scanned images uploaded by scanning or photographing devices via a network interface, or retrieve scanned images corresponding to the target answer sheet or test paper from a database, file server, or cloud storage that pre-stores scanned images. A scanned image may include at least one image. When the target answer sheet or test paper contains multiple pages, the scanned images may include multiple images corresponding to each page. The system can determine which page of the target answer sheet or test paper each scanned image corresponds to based on the answer sheet code, page number, or image upload order.

[0032] Marking location metadata can be data records describing the position and related attributes of each question in the scanned image of the target answer sheet or test paper. Specifically, marking location metadata can include the answer sheet code, page number, question number, parent question number, question type, question score, and area coordinate information of the answer area corresponding to each question. Among them, the answer sheet code is used to uniquely identify the version of the answer sheet or test paper to which the scanned image belongs; the page number is used to determine the page of the scanned image to which the answer area belongs, avoiding confusion of the same coordinate range on different pages of multi-page answer sheets; the question number and parent question number are used to determine the scoring item corresponding to the answer area. For combined questions, the parent question number is used to identify the major question to which the sub-question belongs; the question type is used to determine the display method and marking method of the question, such as objective question, subjective question, combined question, etc.; the question score is used for subsequent validation of scoring; the area coordinate information is used to determine the rectangular boundary of the answer area in the coordinate system of the scanned image. The system can calculate the width, height, and center point position of the answer area based on the area coordinate information.

[0033] The coordinate information for each question includes the coordinates of the first and second vertices on the boundary of its answer area, which are diagonally opposite. In one specific implementation, the coordinate information may include the coordinates of the top-left corner (i.e., the first vertex coordinates) and the bottom-right corner (i.e., the second vertex coordinates) of the answer area corresponding to each question. In another specific implementation, the coordinate information may include the coordinates of the top-right corner (i.e., the first vertex coordinates) and the bottom-left corner (i.e., the second vertex coordinates) of the answer area corresponding to each question. For ease of explanation, the following description uses the top-left corner coordinates as the first vertex coordinates and the bottom-right corner coordinates as the second vertex coordinates as the example. The same principle applies to implementations that use the top-right and bottom-left corner coordinates for the coordinate information.

[0034] By locating metadata in the marking process, the system can establish a correspondence between the specific answer areas in the scanned image and the question numbers and scoring components in the marking panel.

[0035] In some implementations, the grading location metadata for each question can be generated by the system during the answer sheet template generation stage, based on the answer sheet format, page size, column layout, question number area, and answer area. In some implementations, for regular questions, the system directly binds an answer area to the corresponding question number; for combined questions, the system records the parent question information and sub-question information separately, and binds each sub-question's answer area to its corresponding sub-question number; for questions with multiple answer areas, the system saves multiple coordinate segments for that question and distinguishes different segments using page numbers and area sequence numbers.

[0036] In some implementations, the system formats the marking location metadata, expanding the coordinate relationships between major questions, general questions, combined questions, and their sub-questions into a set of question coordinates per readable question. The system first groups the marking location metadata according to the answer sheet code and page number, obtaining a set of question area records corresponding to each page of scanned images. Then, the system establishes a question hierarchy based on the question number, parent question number, and question type of each record in this question area record set.

[0037] For regular questions that do not contain sub-questions, the system directly generates a viewable question coordinate record based on the corresponding record in the question area record set. This viewable question coordinate record includes the question number, question type, question score, page number, top-left corner coordinate, and bottom-right corner coordinate.

[0038] For combined questions, the system first identifies the records in the question area record set that are marked as combined questions as parent question records. Then, it recursively searches for the child question records corresponding to the parent question record in the question area record set. If the found child question record has an independent answer area, the system expands each child question record into an independent readable question coordinate record and retains the parent question number, parent question type, and parent question identifier in the readable question coordinate record. If the parent question record is only used to carry materials or question stems and is not scored separately, the system saves the parent question record as a material area and does not treat it as an independently scored question.

[0039] For cases where the same question spans multiple pages or is distributed across multiple regions, the system saves multiple records with the same question number but different page numbers or region numbers from the question region record set as multiple coordinate segments for that question. Each coordinate segment contains an independent page number, top-left corner coordinate, bottom-right corner coordinate, and region number.

[0040] The formatted question coordinate set contains at least the following elements: unique question identifier, question number, parent question number, question type, question score, answer sheet code, page number, original top-left corner coordinates, original bottom-right corner coordinates, and area sequence number. Through this formatting process, the system converts the original answer sheet's major questions, general questions, combined questions, sub-questions, and multi-page questions into a data structure based on readable questions. Subsequent coordinate conversions, area detection, question location, and scoring are all based on this question coordinate set. This avoids the problem of unclear question number correspondences during the marking process for combined questions, sub-questions, multi-page questions, and multi-area questions, ensuring that the system can identify the specific question or sub-question corresponding to any question area when the marker operates on it in the scanned image.

[0041] In step 120, the display parameters of the scanned image in the marking interface are obtained, and based on the display parameters, the coordinate information of the area corresponding to each question on the page currently displayed in the marking interface is determined, and the corresponding question hit area is determined in the marking interface.

[0042] The display status of scanned images in the marking interface is maintained in real time by the front-end marking component. The system records the current display parameters when the scanned image is loaded, zoomed, scrolled, panned, page-trimmed, multi-page stitched, or the marking mode is switched.

[0043] Display parameters may include the original width and height of the scanned image, the current display width and height, the scaling ratio, the horizontal offset and vertical offset of the scanned image relative to the canvas or scrolling container, the current page number, the order of multiple pages of images, and the current reading mode.

[0044] The system, based on display parameters, converts the coordinate information of the area corresponding to each question on the page currently displayed on the marking interface into the corresponding question hit area on the marking interface. Specifically, in some implementations, determining the coordinate information of the area corresponding to each question on the page currently displayed on the marking interface, and the corresponding question hit area on the marking interface, based on display parameters, may include the following steps: (1) Based on the coordinates of the first vertex, the position information of the first vertex in the first direction, and the horizontal offset, determine the first horizontal coordinate of the first vertex in the marking interface; (2) Based on the coordinates of the first vertex, the position information of the first vertex coordinates in the second direction, and the vertical offset, determine the first vertical coordinate corresponding to the first vertex coordinates in the marking interface; the first direction and the second direction are set to intersect. (3) Based on the coordinates of the second vertex, the position information of the second vertex in the first direction, and the horizontal offset, determine the second horizontal coordinate of the second vertex in the marking interface; (4) Based on the coordinates of the second vertex, the position information of the second vertex coordinates in the second direction, and the vertical offset, determine the second vertical coordinates of the second vertex coordinates in the marking interface; (5) Based on the first horizontal coordinate, the first vertical coordinate, the second horizontal coordinate, and the second vertical coordinate, determine the corresponding question hit area of ​​each question on the marking interface.

[0045] The first direction can be the X-axis direction of the marking interface, and the second direction can be the Y-axis direction of the marking interface.

[0046] For example, assuming the coordinates of the first vertex of a certain answer area are (x1, y1) and the coordinates of the second vertex are (x2, y2), the current scaling factor is scale, the horizontal offset is offsetX, and the vertical offset is offsetY, then the coordinates of the first vertex (displayX1, displayY1) and the second vertex (displayX2, displayY2) of the corresponding question hit area in the marking interface are: displayX1=x1×scale+offsetX; displayY1=y1×scale+offsetY; displayX2=x2×scale+offsetX; displayY2=y2×scale+offsetY.

[0047] Where displayX1 is the first horizontal coordinate, displayY1 is the first vertical coordinate, displayX2 is the second horizontal coordinate, and displayY2 is the second vertical coordinate.

[0048] In some implementations, the automatic question location method based on scanned image region mapping may include the following steps: (1) In the marking interface, when multiple scanned images are displayed in a vertical stitching manner, obtain the display height and page spacing of each scanned image before the scanned image displayed on the current page; (2) Calculate the cumulative page offset based on the display height and page spacing; (3) The first vertical coordinate of the first vertex is determined in the marking interface according to the first vertex coordinate, the position information of the first vertex coordinate in the second direction and the vertical offset, including: determining the first vertical coordinate according to the first vertex coordinate, the position information of the first vertex coordinate in the second direction, the vertical offset and the cumulative page offset; (4) The steps are as follows: Based on the second vertex coordinates, the position information of the second vertex coordinates in the second direction and the vertical offset, determine the second vertical coordinates corresponding to the second vertex coordinates in the marking interface, including: based on the second vertex coordinates, the position information of the second vertex coordinates in the second direction, the vertical offset and the cumulative page offset, determine the second vertical coordinates.

[0049] For example, assuming the calculated cumulative page offset is pageOffsetY, the first and second ordinates can be represented as: displayY1=y1×scale+offsetY+pageOffsetY; displayY2=y2×scale+offsetY+pageOffsetY.

[0050] In some implementations, when multi-page scanned images are displayed using a pagination switching method, the system only calculates the coordinate information of the area corresponding to the current page number and regenerates the question hit area corresponding to the current page when switching pages.

[0051] Therefore, the system can map the original area coordinate information recorded in the marking positioning metadata or question coordinate set to the corresponding question hit area in the marking interface in real time, based on the current display status of the scanned image in the marking interface. This ensures that the position of the question area seen by the examiner in the marking interface is always consistent with the actual answer area of ​​the question in the coordinate system of the scanned image, and is not affected by changes in display status such as image scaling, scrolling, or page switching.

[0052] Furthermore, in some embodiments, before obtaining the display parameters of the scanned image in the marking interface, the automatic marking question location method based on scanned image region mapping further includes the following steps: (1) Retrieve the corresponding answer sheet template from the preset template library according to the answer sheet code; (2) Compare the regional coordinate information with the standard coordinate information in the answer sheet template to obtain the comparison results; (3) If the comparison result shows that there is offset, tilt or recognition error, then obtain the image recognition result or the manual correction result; (4) Update the region coordinate information based on the image recognition results or manual correction results.

[0053] The preset template library contains multiple answer sheet templates, each associated with a corresponding answer sheet code. Each template also records the standard coordinates of each question on the answer sheet or exam paper corresponding to that code. After recognizing the answer sheet code in the scanned image, the system searches the preset template library for the correct code and retrieves the answer sheet template corresponding to the scanned image.

[0054] The coordinate information of the region corresponding to each question in the obtained scanned image is compared one by one with the standard coordinate information corresponding to the same question number in the retrieved answer sheet template. The degree of difference between the two in coordinate values, boundary range or angle is determined, and the comparison result is generated based on the degree of difference.

[0055] If the comparison results show that the difference between the regional coordinate information and the standard coordinate information exceeds the preset range, it is determined that the scanned image has an offset, tilt, or recognition error. At this time, the system can identify the positioning points, border features, or marker points in the scanned image through image recognition, and calculate the image recognition results such as the offset and tilt angle of the scanned image relative to the answer sheet template; the system can also receive the manual correction results input by the examiners or system administrators after manually correcting the scanned image.

[0056] The obtained image recognition results or manual correction results are used to update the coordinates of the first and second vertices in the coordinate information of the region corresponding to the answering region that has offset, tilt or recognition error, so that the updated region coordinate information can accurately correspond to the actual position of the answering region in the scanned image.

[0057] This ensures that before obtaining the display parameters of the scanned image in the marking interface, the offset, tilt, or recognition error correction of the area coordinate information is completed first. The area coordinate information used to calculate the question hit area is the accurate coordinate after correction, thereby avoiding the problem that the calculated question hit area is inconsistent with the actual answer area in the scanned image due to the offset, tilt, or recognition error of the scanned image.

[0058] In step 130, the current position information of the cursor in the marking interface is obtained, and it is determined whether the current position information falls within the target question's hit area.

[0059] The system continuously monitors the hovering, clicking, or annotation operations of examiners on the scanned images. When an examiner hovers, clicks, annotates, or assigns a score using the mouse, the system reads the coordinates from the corresponding mouse or touch event and, combined with the display parameters at that moment, converts the operation position into coordinates in the display coordinate system of the examiner's interface, thus obtaining the current position information of the cursor in the examiner's interface.

[0060] The current position information of the cursor in the marking interface can include the horizontal coordinate (px) and vertical coordinate (py) of the cursor in the marking interface.

[0061] After obtaining the current location information, the system compares it with the hit area of ​​each question to determine whether the current location information falls within the hit area of ​​a target question. Specifically, let the coordinates of the first vertex of a question's hit area be (displayX1, displayY1), and the coordinates of the second vertex be (displayX2, displayY2). Then, the condition for determining whether the current location information (px, py) falls within the hit area of ​​that question is: displayX1≤px≤displayX2, and displayY1≤py≤displayY2. If this condition is met, the current location information is determined to fall within the hit area of ​​that question, and that question's hit area is identified as the target question's hit area.

[0062] In some implementations, if the current location information falls into multiple question hit areas at the same time, the system will prioritize selecting the question hit area with the smaller area as the target question hit area, or prioritize selecting the question hit area corresponding to the sub-question at a deeper level as the target question hit area, in order to avoid misjudgment when the question hit area corresponding to the parent question in a combined question covers the question hit area corresponding to the sub-question.

[0063] In some implementations, if the current location information does not fall within any question hit area, the system is unsure of the target question hit area and will not trigger question switching, annotation binding, or score binding operations, in order to avoid question location or score errors caused by misoperation.

[0064] Therefore, the system can accurately determine the target question hitting area corresponding to the real-time operation position of the examiner on the scanned image, providing a basis for subsequently determining the current marking question based on the target question hitting area and driving the marking panel to generate a linkage response.

[0065] In step 140, if so, the target scoring component in the grading panel corresponding to the target question hit area will respond. The response includes at least one of the following: scrolling the grading panel to the position of the target scoring component, highlighting the question number corresponding to the target scoring component, or setting the scoring input box corresponding to the target scoring component to a focused state.

[0066] In some implementations, the step-driven target scoring component in the grading panel that corresponds to the target question hit area may generate a response, which may include the steps of: generating a location identifier based on the question number bound to the target question hit area, and searching for a target scoring component with the same location identifier in the grading panel.

[0067] Specifically, the system generates a location identifier for the current marking question based on the question number or parent question number bound to the target question's hit area, and searches for a scoring component with the same location identifier in the marking panel, identifying the found scoring component as the target scoring component.

[0068] In some implementations, if the target scoring component is located outside the current visible area of ​​the grading panel, the system controls the grading panel to scroll to the location of the target scoring component, so that the grader can see the target scoring component in the grading panel without having to manually search for or scroll to locate it.

[0069] In some implementations, the system highlights the question number corresponding to the target scoring component, enabling examiners to visually identify the question number of the currently assigned question in the grading panel, which is then corroborated by the currently operated answer area in the scanned image.

[0070] In some implementations, if the question corresponding to the target scoring component is the current question to be scored, the system sets the scoring input box corresponding to the target scoring component to a focused state, so that the examiner can directly enter the score without having to click the scoring input box again.

[0071] In some implementations, for sub-questions within a combined question, the system determines the target scoring component corresponding to the sub-question based on the parent question number and sub-question number bound to the target question's hit area. This ensures that when examiners operate the answer area of ​​a sub-question in the scanned image, the scoring panel responds with the scoring component corresponding to that sub-question, rather than the scoring component corresponding to its parent question.

[0072] In some implementations, when there are multiple answer areas or pages for the same question, the system locates the target scoring component corresponding to the question number based on the page number and area number of the target question's answer area. This ensures that when the examiner operates in any answer area corresponding to the question's coordinate segment, the same target scoring component corresponding to the same question number will be displayed in the grading panel.

[0073] Therefore, the system establishes a real-time linkage between the position of the examiner in the scanned image and the scoring components in the grading panel. This allows examiners to switch their gaze or focus between the scanned image and the grading panel without having to manually search, scroll, or click on the corresponding scoring components, thereby improving grading efficiency and reducing the risk of incorrect or missed scores due to mismatches between scoring components and questions.

[0074] After completing the above-mentioned question location and grading panel linkage, examiners typically enter the actual score for the current question in the grading panel. However, when entering scores, examiners may enter scores outside the reasonable range due to misoperation, incorrect input, or system recognition errors, thus affecting the accuracy of the score summary. To solve this problem, in some implementations, this automatic question location method based on scanned image region mapping may further include the following steps: (1) Obtain the actual score for each question; (2) If the actual score of a question is less than zero or greater than the preset score of a question, the actual score of the question is determined to be an illegal score, and score verification exception handling is performed. Score verification exception handling includes at least one of intercepting the score submission operation, clearing the score data entered this time, or generating a score exception prompt message. (3) If the actual score of a question is greater than zero and less than the preset score of a question, the actual score of the question is determined to be a valid score, and the actual score of the question is entered into its marking positioning metadata, driving the scoring component corresponding to the question in the marking panel to be updated synchronously.

[0075] The system obtains the actual scores entered by the examiners for each question through the scoring input box, scoring component, or mouse scoring method in the grading panel.

[0076] The system determines the preset score for the question based on the score recorded in the marking location metadata, and compares the actual score with zero and the preset score respectively.

[0077] If the actual score is less than zero, or greater than the preset question score, the actual score is determined to be invalid. In this case, the system performs score verification exception handling, which includes at least one of the following: intercepting the score submission operation, clearing the input score data, or generating a score exception prompt message, to prevent invalid scores from being included in the marking record.

[0078] If the actual score is greater than or equal to zero and less than or equal to the preset question score, the system determines the actual score to be a valid score. The system then associates the valid score with the question number, parent question number, question unique identifier, and other information of the question and saves it in the marking positioning metadata. At the same time, the system drives the scoring component corresponding to the question in the marking panel to update synchronously, so that the score displayed by the scoring component is consistent with the actual score entered this time.

[0079] In some implementations, for combined questions, the system checks whether the actual score of each sub-question exceeds the preset question score of the corresponding sub-question. When the parent question has a total score limit, the system can also check whether the sum of the actual scores of each sub-question under the parent question exceeds the preset question score of the parent question. If it exceeds, it is also determined to be an illegal score and the corresponding score verification exception handling is performed, thereby avoiding the situation where the sum of the scores of each sub-question of the combined question exceeds the total score of the combined question.

[0080] Specifically, in some implementations, the marking location metadata also includes a first preset total score of the parent question to which the answer area belongs, and a second preset score of each sub-question included in the parent question. This automatic marking question location method based on scanned image area mapping may also include the following steps: (1) Obtain the actual score for each sub-question; (2) Determine the actual score of the parent question based on the sum of the actual scores of each sub-question; (3) If the actual score of a sub-question is greater than the second preset score corresponding to the sub-question, or the actual score of the parent question is greater than the first preset total score, then the actual score of the sub-question or the parent question is determined to be an illegal score; (4) Perform score verification exception handling, which includes at least one of intercepting the score submission operation, clearing the score data entered this time, or generating a score exception prompt message.

[0081] The second preset score can be the score of the sub-question recorded in the marking positioning metadata, used to limit the highest score that the sub-question can obtain on its own; the first preset total score can be the score of the parent question recorded in the marking positioning metadata, used to limit the highest score allowed for the sum of the actual scores of each sub-question in the combined question.

[0082] The system compares the actual score of each sub-question with zero and its corresponding second preset score. If the actual score of a sub-question is less than zero or greater than the second preset score, the actual score of that sub-question is determined to be an invalid score. The system also compares the actual score of the parent question with the first preset total score. If the actual score of the parent question is greater than the first preset total score, the actual score of the parent question is determined to be an invalid score.

[0083] If the actual score of a sub-question or parent question is determined to be an invalid score, the system will perform score verification exception handling to prevent invalid scores from being included in the marking record and thus affecting the accuracy of the score summary.

[0084] In some implementations, if the actual score of a sub-question and the actual score of its parent question are not illegal scores, the system determines that the actual scores of the sub-question and its parent question are legal scores, and records the actual scores of each sub-question and its parent question into the marking positioning metadata, thereby driving the scoring components in the marking panel corresponding to the combined question and its sub-questions to be updated synchronously.

[0085] Please see Figure 2 , Figure 2 This illustration shows a schematic diagram of an automatic marking question location device based on scanned image region mapping provided in an embodiment of this application. The automatic marking question location device 200 based on scanned image region mapping includes: an acquisition module 210, a determination module 220, a judgment module 230, and a driving module 240. Specifically: The acquisition module 210 is used to acquire scanned images of the target answer sheet or target test paper, and the marking location metadata corresponding to each question in the scanned image; the marking location metadata includes the answer sheet code, page number, question number, question type, question score and area coordinate information to which the answer area belongs; The determination module 220 is used to obtain the display parameters of the scanned image in the marking interface, and determine the area coordinate information of each question in the scanned image and the corresponding question hit area in the marking interface according to the display parameters. The judgment module 230 is used to obtain the current position information of the cursor in the marking interface and to determine whether the current position information falls within the target question's hit area. The driving module 240 is configured to, if so, drive the target scoring component in the grading panel corresponding to the target question's hit area to generate a response, the response including at least one of scrolling the grading panel to the position of the target scoring component, highlighting the question number identifier corresponding to the target scoring component, or setting the scoring input box corresponding to the target scoring component to a focused state.

[0086] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0087] In the several embodiments provided in this application, the coupling or direct coupling or communication connection between the modules shown or discussed may be an indirect coupling or communication connection through some interface, device or module, and may be electrical, mechanical or other forms.

[0088] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0089] Please see Figure 3 , Figure 3 The diagram shows a structural schematic of an electronic device provided in an embodiment of this application. The electronic device 300 in this application may include one or more of the following components: a processor 310, a memory 320, and one or more application programs. The one or more application programs may be stored in the memory 320 and configured to be executed by one or more processors 310. The one or more programs are configured to execute the automatic location method for marking questions based on scanned image region mapping as described in the foregoing method embodiments.

[0090] Processor 310 may include one or more processing cores. Processor 310 connects to various parts within the electronic device 300 using various interfaces and lines, and performs various functions and processes data of the electronic device 300 by running or executing instructions, programs, code sets, or instruction sets stored in memory 320, and by calling data stored in memory 320. Optionally, processor 310 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 310 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 310 and may be implemented separately using a communication chip.

[0091] The memory 320 may include random access memory (RAM) or read-only memory (ROM). The memory 320 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 320 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described below, etc. The data storage area may also store data created by the electronic device 300 during use.

[0092] Please see Figure 4 , Figure 4 The diagram illustrates the structure of a computer-readable storage medium 400 provided in an embodiment of this application. The computer-readable storage medium 400 stores program code, which can be called by a processor to execute the automatic locating method for marking questions based on scanned image region mapping described in the above method embodiment.

[0093] The computer-readable storage medium 400 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 400 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 400 has storage space for program code 410 that performs any of the method steps described above. This program code can be read from or written to one or more computer program devices. The program code 410 may be compressed, for example, in a suitable form.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for automatically locating marking questions based on scanned image region mapping, characterized in that, The method includes: Obtain a scanned image of the target answer sheet or target test paper, and the marking location metadata corresponding to each question in the scanned image; the marking location metadata includes at least the page number, question number, and area coordinate information of the answer area; Obtain the display parameters of the scanned image in the marking interface, and determine the area coordinate information of each question in the page corresponding to the currently displayed page number of the marking interface based on the display parameters, and the corresponding question hit area in the marking interface. Obtain the current position information of the cursor in the marking interface, and determine whether the current position information falls within the target question's hit area; If so, the target scoring component in the grading panel corresponding to the target question hit area will respond. The response includes at least one of the following: scrolling the grading panel to the position of the target scoring component, highlighting the question number corresponding to the target scoring component, or setting the scoring input box corresponding to the target scoring component to a focused state.

2. The automatic question location method for marking papers based on scanned image region mapping according to claim 1, characterized in that, The marking location metadata also includes the answer sheet code to which its answer area belongs. Before obtaining the display parameters of the scanned image in the marking interface, the method further includes: The corresponding answer sheet template is retrieved from the preset template library based on the answer sheet code; The coordinate information of the region is compared with the standard coordinate information in the answer sheet template to obtain the comparison result; If the comparison result indicates a shift, tilt, or recognition error, then obtain the image recognition result or the manual correction result. The region coordinate information is updated based on the image recognition results or manual correction results.

3. The automatic question location method for marking papers based on scanned image region mapping according to claim 1, characterized in that, The display parameters include the image scaling ratio of the marking interface, and the horizontal and vertical offset of the scanned image relative to the display container; The area coordinate information for each question includes the coordinates of the first vertex and the second vertex on the boundary of its answer area, and the coordinates of the first vertex and the second vertex are diagonally related. The step involves determining the coordinate information of the area corresponding to each question on the page currently displayed on the marking interface, based on the display parameters. The corresponding question hit area on the marking interface includes: Based on the first vertex coordinates, the position information of the first vertex coordinates in the first direction, and the horizontal offset, determine the first horizontal coordinate corresponding to the first vertex coordinates in the marking interface; Based on the first vertex coordinates, the position information of the first vertex coordinates in the second direction, and the vertical offset, the first vertical coordinate corresponding to the first vertex coordinates in the marking interface is determined; the first direction and the second direction are intersected. Based on the second vertex coordinates, the position information of the second vertex coordinates in the first direction, and the horizontal offset, determine the second horizontal coordinate corresponding to the second vertex coordinates in the marking interface; Based on the second vertex coordinates, the position information of the second vertex coordinates in the second direction, and the vertical offset, determine the second vertical coordinate corresponding to the second vertex coordinates in the marking interface; Based on the first horizontal coordinate, the first vertical coordinate, the second horizontal coordinate, and the second vertical coordinate, determine the question hit area corresponding to each question on the marking interface.

4. The automatic question location method for marking papers based on scanned image region mapping according to claim 3, characterized in that, The method further includes: In the examination interface, when multiple scanned images are displayed in a vertical stitching manner, the display height and page spacing of each scanned image preceding the scanned image displayed on the current page are obtained; Calculate the cumulative page offset based on the display height and page spacing; The step of determining the first ordinate of the first vertex on the marking interface based on the first vertex coordinates, the position information of the first vertex coordinates in the second direction, and the vertical offset includes: The first vertical coordinate is determined based on the first vertex coordinates, the position information of the first vertex coordinates in the second direction, the vertical offset, and the cumulative page offset; The step of determining the second ordinate of the second vertex on the marking interface based on the second vertex coordinates, the position information of the second vertex coordinates in the second direction, and the vertical offset includes: The second vertical coordinate is determined based on the second vertex coordinates, the position information of the second vertex coordinates in the second direction, the vertical offset, and the cumulative page offset.

5. The automatic question location method for marking papers based on scanned image region mapping according to claim 1, characterized in that, The marking location metadata also includes the preset question score for the question to which the answer area belongs, and the method further includes: Obtain the actual score for each question; If the actual score of a question is less than zero or greater than the preset score of the question, the actual score of the question is determined to be an illegal score, and score verification exception handling is performed. The score verification exception handling includes at least one of intercepting the score submission operation, clearing the score data entered this time, or generating a score exception prompt message. If the actual score of a question is greater than zero and less than the preset score of the question, the actual score of the question is determined to be a valid score, and the actual score of the question is entered into its marking positioning metadata, which drives the scoring component corresponding to the question in the marking panel to be updated synchronously.

6. The automatic question location method for marking papers based on scanned image region mapping according to claim 1, characterized in that, The marking location metadata also includes a first preset total score for the parent question to which the answer area belongs, and a second preset score for each sub-question included in the parent question. The method further includes: Obtain the actual score for each sub-question; The actual score of the parent question is determined based on the sum of the actual scores of each of the sub-questions; If the actual score of a sub-question is greater than the second preset score corresponding to that sub-question, or if the actual score of the parent question is greater than the first preset total score, then the actual score of the sub-question or the parent question is determined to be an illegal score. Perform score verification exception handling, which includes at least one of intercepting the score submission operation, clearing the currently input score data, or generating a score exception prompt message.

7. The automatic question location method for marking papers based on scanned image region mapping according to claim 1, characterized in that, The target scoring component in the step-driven grading panel, corresponding to the area where the target question is hit, generates a response, including: A location identifier is generated based on the question number bound to the target question hit area, and a target scoring component with the same location identifier is searched in the grading panel.

8. An automatic question location device for marking examination papers based on scanned image region mapping, characterized in that, The device includes: The acquisition module is used to acquire a scanned image of the target answer sheet or the target test paper, and the marking location metadata corresponding to each question in the scanned image; the marking location metadata includes the answer sheet code, page number, question number, question type, question score, and area coordinate information to which the answer area belongs; The determination module is used to obtain the display parameters of the scanned image in the marking interface, and determine the area coordinate information of each question in the scanned image and the corresponding question hit area in the marking interface according to the display parameters. The judgment module is used to obtain the current position information of the cursor in the marking interface and determine whether the current position information falls within the target question's hit area. The driving module is configured to, if so, drive the target scoring component in the grading panel corresponding to the target question hit area to generate a response, the response including at least one of scrolling the grading panel to the position of the target scoring component, highlighting the question number identifier corresponding to the target scoring component, or setting the scoring input box corresponding to the target scoring component to a focused state.

9. An electronic device, characterized in that, include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the automatic question location method for marking based on scanned image region mapping as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code, which can be called by a processor to execute the automatic locating method for marking questions based on scanned image region mapping as described in any one of claims 1-7.

Images