Roll surface single / double surface batch correction determination method, device, equipment and readable medium

Abstract

The application discloses a method, device and equipment for determining single or double-sided correction of a test paper, and a readable medium. The method comprises scanning and uploading a test paper to be corrected; performing sample extraction on the uploaded test paper to be corrected to obtain a first sample test paper set; performing test paper determination on the first sample test paper set; and executing first determination logic after the determination. Through the combination of sample extraction, test paper determination and two-stage determination logic, it can be determined automatically and accurately whether the test paper scanned in the current class needs single-sided correction or double-sided correction, thereby solving the problem that the existing intelligent correction machine cannot accurately determine the correction object when facing single or double-sided mixed placement, effectively meeting the actual needs of schools for printing different test papers on the front and back of a piece of paper to save materials, supporting two separate corrections of the front and back, and realizing the function of single-page test paper correction and leaving marks, and improving the adaptive ability of the intelligent correction machine to diversified teaching scenarios.

Description

Technical Field

[0001] This invention belongs to the field of educational technology, specifically relating to a method, apparatus, equipment, and readable medium for judging single-sided and double-sided marking of test papers. Background Technology

[0002] Against the backdrop of the rapid development of smart education, intelligent homework grading machines have received widespread attention and application in the education field as an important tool for improving teaching efficiency. These devices can achieve fully intelligent grading of student homework and test papers. Their core workflow mainly consists of three key steps: scanning test papers, intelligent grading of test papers, and printing of test papers. Through automated processing, the workload of teachers in manual grading has been greatly reduced.

[0003] However, existing smart grading machines have significant technical limitations in practical applications. Current devices are generally designed for double-sided scanning of exam papers, meaning they can only simultaneously recognize and grade both sides of the same sheet of paper. But in actual teaching scenarios, two prominent problems exist:

[0004] The way students submit their exam papers or assignments is random; they may be face up or face down. When these two types of papers are mixed together, the existing grading machine cannot accurately determine the specific page that needs to be graded, resulting in an unclear grading target.

[0005] To save on material costs, schools often print different content on both sides of the same sheet of paper. In this case, it is necessary to grade each side separately and leave grading marks. However, existing equipment cannot meet the requirement of grading and leaving marks on a single page, making it difficult to adapt to this material-saving application scenario.

[0006] Therefore, how to solve the problem of determining whether an exam paper is single-sided or double-sided, especially when students' exam papers are mixed together, and how to intelligently and accurately determine the corresponding page that needs to be graded, has become a key challenge that needs to be overcome in the development of intelligent homework grading technology in the current field of smart education. This is of great significance for improving the practicality and adaptability of intelligent grading machines. Therefore, we need to provide methods, devices, equipment and readable media for determining whether an exam paper is single-sided or double-sided. Summary of the Invention

[0007] The purpose of this invention is to provide a method, apparatus, device, and readable medium for determining whether a student's exam paper needs single-sided or double-sided marking. By combining sample extraction, paper surface determination, and a two-level judgment logic, it can automatically and accurately determine whether the scanned exam paper for the current class requires single-sided or double-sided marking. This solves the problem of existing smart marking machines being unable to accurately determine the marking target when single-sided and double-sided papers are mixed. It effectively meets the practical needs of schools to save on consumables by printing different exam papers on both sides of a single sheet of paper. It supports two separate marking and recording operations on both sides, realizing the function of marking and recording on a single page, and improving the adaptability of smart marking machines to diverse teaching scenarios. This addresses the problem mentioned in the background art of how to determine whether the scanned exam paper for the current class requires single-sided or double-sided marking, and, if determined to be single-sided, how to intelligently and accurately determine the corresponding page requiring marking when the front and back of students' exam papers are mixed.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: a method for judging single-sided and double-sided corrections on a roll, comprising the following steps:

[0009] Scan the papers to be graded and upload them;

[0010] The uploaded papers to be graded are sampled to obtain the first sample paper set.

[0011] Perform a paper determination judgment on the first sample paper set, and then execute the first judgment logic;

[0012] If the first judgment logic determines the correction mode, the judgment ends.

[0013] If the first judgment logic fails to identify the grading mode, then a second sample set of papers will be obtained by sampling the papers to be graded.

[0014] The second set of papers will be used to determine the paper type. After the determination, the second determination logic will be executed to confirm the grading mode.

[0015] Preferably, the first sample set and the second sample set can be the same sample set.

[0016] Preferably, the execution of the paper surface determination further refers to performing paper surface determination on the paper surface information scanned by each student, that is, defining the first image of the test paper scanned by each student as the front and the second image as the back, which is essentially performing a front and back recognition on the student's paper surface in all samples.

[0017] Preferably, the determination of the paper surface can be further made through image similarity recognition and / or text OCR recognition;

[0018] Image similarity refers to acquiring front and back images of student A, randomly defining the first image as the front and the second as the back, and comparing the similarity of other students' images in the sample with the front and / or back images of student A to confirm the front and back of other students in the sample. Text OCR recognition refers to acquiring front and back images of student A, randomly defining the first image as the front and the second as the back, acquiring the OCR text in the front and the OCR text in the back, and then performing OCR recognition on each image of other students in the sample. By matching the similarity with the OCR text of student A's front and / or back images, the front and back of other students can be confirmed.

[0019] Preferably, the first determination logic is a trace-keeping determination logic, and the corresponding second determination logic is a question-and-answer determination logic. The trace-keeping determination logic refers to determining whether there is a mark indicating that the front and back images have been marked: obtain the front and back of the first sample; if both the front and back have been marked, then the recognition and marking logic will not be executed on either the front or back; if only one page of the front and back has been marked, then it is determined to be a single-page marking, and the page to be marked is the front or back without a mark; if neither the front nor back has been marked, then the second determination logic will be executed. The question-and-answer determination logic further refers to determining whether there are traces of handwritten answers on the front and back of the student's exam paper; if neither the front nor back has been marked, then it is determined that the exam paper will not be marked; if only one page of the front and back has been marked, then it is determined to be a single-page marking, and the page marked at the top is the page with the answer; if both the front and back have been marked, then it is determined to be a double-sided marking logic, and both the front and back will be marked.

[0020] Preferably, the first determination logic is the "whether an answer has been given" determination logic, and the corresponding second determination logic is the "traceability determination logic." The "whether an answer has been given" determination logic further refers to determining whether there are traces of handwritten answers on both sides of the student's exam paper. If neither side has been answered, the exam paper is determined not to be graded. If only one page on both sides has been answered, it is determined to be a single-page grade, and the page marked at the top is the page with the answer. If both sides have been answered, the second determination logic continues to be executed. The "traceability determination logic" refers to determining whether there are any marking marks on the images of both sides: obtaining the front and back sides from the first sample, if both sides have been marked, the recognition and grading logic is not executed on either side. If only one page on both sides has been marked, it is determined to be a single-page grade, and the page to be graded is the front or back side without a mark. If neither side has been marked, it is determined to be a double-sided grading logic, and recognition and grading are performed on both sides.

[0021] Preferably, in the first determination logic, if the ratio of images with marks on the front or back of the sample is greater than a first preset threshold, it is determined that marks have been left on the front or back; in the second determination logic, if the ratio of images of the front or back of the student's answer in the sample is greater than a second preset threshold, it is determined that the student has answered on the front or back.

[0022] A device for determining whether a paper is single-sided or double-sided, including:

[0023] Scanning unit: Used to scan the paper to be graded;

[0024] Recognition Unit: Used to extract samples from the scanned papers to be graded, determine the papers, and execute judgment logic to determine the grading mode. This includes front and back recognition of the sample papers, paper determination through image similarity recognition and / or text OCR recognition, execution of trace determination logic, and whether an answer has been given.

[0025] Sample extraction unit: used to extract the first sample set and the second sample set from the scanned test papers to be graded;

[0026] Judgment Logic Execution Unit: Used to execute the first judgment logic and the second judgment logic, wherein the first judgment logic can be the record-keeping judgment logic or the whether to answer judgment logic, and the second judgment logic is another judgment logic corresponding to the first judgment logic, and the grading mode is determined according to the judgment result;

[0027] Threshold setting unit: used to preset various judgment thresholds, including the first preset threshold, the second preset threshold, the third preset threshold, the fourth preset threshold, the fifth preset threshold, the sixth preset threshold, etc., to provide quantitative standards for the execution of judgment logic.

[0028] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for determining whether a paper is single-sided or double-sided.

[0029] A computer-readable storage medium stores non-transitory computer-readable instructions, which, when executed by a computer, enable the method for determining whether a paper is single-sided or double-sided.

[0030] The technical effects and advantages of this invention: Compared with the prior art, the method, apparatus, equipment, and readable medium for determining single-sided and double-sided corrections proposed in this invention have the following advantages:

[0031] This invention, through a combination of sample extraction, paper layout determination, and two-level judgment logic, can automatically and accurately determine whether the scanned test papers for the current class require single-sided or double-sided marking. This solves the problem of existing smart marking machines being unable to accurately determine the marking target when faced with a mix of single-sided and double-sided papers. It effectively meets the practical needs of schools to save on consumables by printing different test papers on both sides of a single sheet of paper. It supports two separate marking and recording operations on both sides, realizing the function of marking and recording on a single page. This enhances the adaptability of the smart marking machine to diverse teaching scenarios, eliminating the need for manual selection of marking pages, reducing teachers' operational steps and workload, avoiding potential errors from manual operation, and improving user efficiency. Simultaneously, by supporting flexible single-sided and double-sided marking, it further complements schools' consumable-saving needs, reducing consumable costs and equipment usage difficulty during the teaching process.

[0032] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description and the drawings. Attached Figure Description

[0033] Figure 1 This is a flowchart of the steps of the present invention. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] This invention provides, for example Figure 1 The method for judging whether a paper is single-sided or double-sided includes the following steps:

[0036] Scan the papers to be graded and upload them;

[0037] The uploaded papers to be graded are sampled to obtain the first sample paper set.

[0038] Perform a paper determination judgment on the first sample paper set, and then execute the first judgment logic;

[0039] If the first judgment logic determines the correction mode, the judgment ends.

[0040] If the first judgment logic fails to identify the grading mode, then a second sample set of papers will be obtained by sampling the papers to be graded.

[0041] The second set of papers will be used to determine the paper type. After the determination, the second determination logic will be executed to confirm the grading mode.

[0042] The first sample set and the second sample set can be the same sample set;

[0043] Specifically, when the first judgment logic does not identify the grading mode, there is no need to re-extract samples from the papers to be graded. The first sample paper set can be directly used as the second sample paper set to reduce redundant sample extraction operations and improve judgment efficiency.

[0044] When the same set of test papers is used for the first and second decision logics, the test paper determination results that have been completed (i.e., the front and back recognition results of each student's test paper in the sample) can be shared. There is no need to repeat the test paper determination steps for the second decision logic, thus avoiding the waste of data processing resources.

[0045] If the first sample set of test papers and the second sample set of test papers are the same sample set of test papers, the sample coverage, the number of student test papers, and the image information of a single sample remain consistent during the two judgment logic execution processes, ensuring that the judgment logic based on the same sample data is executed continuously, and guaranteeing the consistency and accuracy of the grading mode judgment results.

[0046] The execution of the paper surface determination further refers to performing paper surface determination on the paper surface information scanned by each student, that is, defining the first image of the test paper scanned by each student as the front and the second image as the back. In essence, it is to perform a front and back recognition on the student's paper surface in all samples.

[0047] Specifically, for a single student's scanned data, the first scanned and uploaded test paper image is defined as the front side, and the second scanned test paper image is defined as the back side; if a single student only scans a single test paper (i.e., there is only one side image), then the image is defaulted to the front side, and the back side is marked as "none".

[0048] A unified front and back recognition process is implemented for the paper information of all students in the first sample paper set or the second sample paper set: based on the front and back definition of a single student, a reference label for "front" and "back" in the sample is established to clearly distinguish the first (front) and second (back) sides of each student's paper image.

[0049] After the paper examination step, the first and second judgment logics executed subsequently both use "front" and "back" as standard terms to describe the first and second images of the student's paper, ensuring consistency in the reference of the paper pages in different judgment logics and avoiding judgment errors caused by confusion of terminology.

[0050] The front and back recognition results will serve as the basis for the first and second judgment logics. When the first sample set and the second sample set are the same sample set, the recognition results can be directly reused without repeated calculation.

[0051] The determination of the paper surface can be further made through image similarity recognition and / or text OCR recognition;

[0052] Image similarity refers to acquiring front and back images of student A, randomly defining the first image as the front and the second as the back, and comparing the similarity of other students' images in the sample with the front and / or back images of student A to confirm the front and back of other students in the sample; text OCR recognition refers to acquiring front and back images of student A, randomly defining the first image as the front and the second as the back, acquiring the OCR text in the front and the OCR text in the back, and then performing OCR recognition on each image of other students in the sample, and matching the similarity with the OCR text in the front and / or back images of student A to confirm the front and back of other students.

[0053] Specifically, the image similarity recognition and determination is as follows: select any student in the sample (such as student A) as the reference object, obtain all the scanned images of the student's papers, and randomly define the first image as the front image of student A and the second image as the back image of student A; if student A only scans a single image, then only that image is defined as the front image, and the back image is marked as "none".

[0054] Extract image features (such as layout, question type distribution, border style, fixed pattern, etc.) from the front and back images of Student A to establish a front feature library and a back feature library.

[0055] For each scanned image of other students in the first sample set or the second sample set, extract their image features and calculate the similarity with student A's front and back feature databases (e.g., using histogram matching, feature point matching, etc.).

[0056] If the similarity between a student's image and a frontal image of student A is higher than a preset similarity threshold (e.g., 80%), then the image is determined to be the frontal image of that student; if the similarity between a student's image and a backal image of student A is higher than a preset similarity threshold, then the image is determined to be the backal image of that student; if the similarity thresholds for both the frontal and backal images are met, then the scanning order is used to assist in the determination (e.g., images that are scanned earlier in the scanning order are prioritized as the frontal image).

[0057] Text OCR recognition judgment: Student A is selected as the reference object. OCR text recognition is performed on the defined front and back images of the student. The front text information (such as the test paper title, question number range, specific explanatory text, etc.) and the back text information are extracted to establish the front text library and the back text library.

[0058] For each scanned image of other students in the sample, perform OCR text recognition to obtain their text content, and perform text preprocessing (such as removing redundant symbols, standardizing format, etc.).

[0059] The preprocessed text content is compared with the positive and negative text databases of Student A (for example, the text matching degree is calculated by algorithms such as cosine similarity and edit distance).

[0060] If the similarity between a student's image text and the positive text database of student A is higher than a preset text threshold (e.g., 70%), then it is determined to be the positive text of that student; if the similarity with the negative text database is higher than the preset text threshold, then it is determined to be the negative text; if there is a cross-match, it can be further distinguished by combining unique identification information in the text (e.g., specific page numbers, chapter numbers).

[0061] Fusion Judgment Logic: Image similarity recognition or text OCR recognition can be used alone to determine the front and back of the paper; or the two methods can be combined. When the two recognition results are consistent, the front and back can be directly confirmed; when the results are inconsistent, the final judgment result can be determined by weighted calculation (such as 60% for image similarity and 40% for text similarity) or preset priority (such as text OCR recognition result having higher priority than image similarity recognition), thereby improving the accuracy of front and back recognition.

[0062] The first determination logic is the traceability determination logic, and the corresponding second determination logic is the whether an answer has been given determination logic. The traceability determination logic refers to determining whether there are any marking marks in the front and back images: obtain the front and back of the first sample. If both the front and back have marking marks, then the recognition and marking logic will not be executed on either the front or back. If only one page has marking marks, then it is determined to be a single-page marking, and the page to be marked is the front or back without marking marks. If neither the front nor back has marking marks, then the second determination logic will be executed. The whether an answer has been given determination logic further refers to determining whether there are any handwritten marks of the student's answers on the front and back of the student's paper. If neither the front nor back has answers, then it is determined not to mark this paper. If only one page has answers, then it is determined to be a single-page marking, and the page marked at the top is the page with answers. If both the front and back have answers, then it is determined to be a double-sided marking logic, and both the front and back will be recognized and marked.

[0063] Specifically, the traceability determination logic includes:

[0064] Define "markers with marked corrections" as visual markers with clear correction attributes, including but not limited to red checkmarks, QR codes with correction records, top-displayed correction images (such as screenshots of teachers' handwritten annotations), and correction text markers in specific formats (such as preset fields like "read" and "corrected").

[0065] Trace mark detection is performed on the front and back images of each student in the first sample set of test papers. The mark features are located and extracted using image recognition technology (such as object detection algorithm).

[0066] Based on the detection results, the following judgment is made: If the front and back images of a student both detect the mark that meets the definition, and the integrity of the mark (such as the complete display of the checkmark and cross, and the recognizability of the QR code) meets the preset standard, then it is determined that the front and back of the student have been marked, and the recognition and correction logic will not be executed on these two pages of the student in the future.

[0067] If a trace marker is detected only on the front or back, and no trace marker is detected on the other page, it is determined to be a single-page correction mode, and the page without trace markers is designated as the target page for this correction.

[0068] If no trace mark is detected on either side, or if the trace mark does not meet the integrity standard (e.g., only some checkmark or cross mark remains), it is determined that the trace mark judgment logic has not confirmed the correction mode, triggering the second judgment logic.

[0069] The logic for determining whether an answer has been given includes: defining "student handwriting traces" as handwritten text, symbols, drawings, etc., written by students within the answer area of ​​the test paper (such as the answer box, horizontal line area, etc., within a preset range), excluding non-answer traces such as printed text and random doodles in blank areas.

[0070] Handwriting detection is performed on the sample test papers (including the first sample test paper set or the second sample test paper set) that enter the second judgment logic. Handwriting features in the answer area are extracted by handwriting recognition algorithm (such as a deep learning-based handwriting segmentation model).

[0071] Judgment based on detection results: If no valid handwriting is detected in the answer area of ​​both the front and back images, or if the area of ​​handwriting is less than the preset answer threshold (e.g., 5%), the paper is judged as blank and will not be graded this time.

[0072] If valid handwriting is detected only in the answer area on the front or back, and the proportion of handwriting in the answer area of ​​another page is lower than the preset threshold, it is determined to be a single-page grading mode, and the answer page is marked as the grading target.

[0073] If valid handwritten characters are detected in both the front and back answer areas and both meet the preset answer threshold, it is determined to be a double-sided correction mode, and the recognition and correction logic is executed on both the front and back pages.

[0074] The first determination logic is the "whether an answer has been given" logic, and the corresponding second determination logic is the "traceability" logic. The "whether an answer has been given" logic further refers to determining whether there are handwritten marks on both sides of the student's exam paper. If neither side has an answer, the exam paper is not graded. If only one page has an answer, it is graded as a single page, with the graded page at the top being the page with the answer. If both sides have an answer, the second determination logic continues. The "traceability" logic determines whether there are any marking marks on the front and back images: If both sides have marks in the first sample, neither side continues the marking logic. If only one page has a mark, it is graded as a single page, and the graded page is either the unmarked front or back. If neither side has a mark, it is graded as a double-sided page, requiring marking on both sides.

[0075] Specifically, the scope of "students' handwritten answers" should be clearly defined, limited to the pre-designated answer areas on the test paper (such as the answer box below the question, the designated horizontal line area, the area where the chart is drawn, etc.), excluding handwritten marks in non-answer areas such as the edges of the test paper, headers and footers (such as student names, class and other identifying text).

[0076] Handwriting recognition technology (such as a deep learning-based handwriting detection model) is used to scan the front and back images of each student in the first sample test paper set, extract handwriting features (including stroke trajectory, ink depth, writing continuity, etc.) in the answer area, and distinguish them from the original printed text features of the test paper.

[0077] The judgment is based on quantitative standards: if no handwriting matching the characteristics is detected in the answer area of ​​both the front and back images, or if the cumulative length and area ratio of the handwriting are lower than the preset answer threshold (e.g., the handwriting coverage area of ​​a single page is less than 5%), then it is judged as a blank paper and no grading logic is executed this time.

[0078] If handwritten marks matching the characteristics are detected only in the answer area on the front or back, and the handwritten marks in the answer area of ​​another page do not reach the answer threshold, it is determined to be a single-page grading mode. The answer page is then set as the target page for this grading, and the front and back attributes of the page are recorded (based on the previous paper layout to determine the judgment result).

[0079] If handwritten characters matching the characteristics are detected in both the front and back answer areas and both reach the answer threshold, it is determined that the answer judgment logic has not confirmed the correction mode, triggering the second judgment logic (traceability judgment logic).

[0080] The logic for determining the traceability includes: defining "markers that have been marked" as markers with clear marking attributes, including but not limited to red (or other preset colors) checkmarks, crosses, wavy lines and other marking symbols used by teachers when marking, QR codes with marking records (including marking time, marking person and other information), and top-level marking marks automatically generated by the system (such as text boxes with the words "marked" or border marks of a specific style).

[0081] Image recognition technology (such as target detection algorithm) is used to scan the sample paper that enters the second judgment logic (which may be the same set as the first sample paper set) to locate and identify the above-mentioned trace mark, and at the same time verify the validity of the mark (such as the QR code can be parsed and the check mark symbol can be completely identified).

[0082] Based on the recognition results, the following judgment is made: If valid trace marks are detected on both the front and back images of a student, and the number and coverage of the marks meet the preset standards (such as at least one complete mark on each side), then it is determined that the front and back images of the student have been corrected, and the recognition and correction logic will not be executed on these two pages again.

[0083] If a valid trace marker is detected only on the front or back, and no trace marker is detected on the other page, it is determined to be a single-page correction mode, and the page without trace markers is designated as the target page for this correction.

[0084] In the first determination logic, if the ratio of images with marks on the front or back of the sample is greater than the first preset threshold, it is determined that marks have been left on the front or back. In the second determination logic, if the ratio of images of the front or back of the student's answer in the sample is greater than the second preset threshold, it is determined that the student has answered on the front or back.

[0085] Specifically, the ratio of images with traces on the front or back of the sample refers to the proportion of student images with valid trace markings detected on the front of the first sample set to the total number of student images with valid trace markings detected on the back of the sample set to the total number of student images with valid trace markings detected on the back of the sample set.

[0086] The first preset threshold is a proportion threshold set based on the representativeness of the sample (e.g., 60%). When the proportion of front-side traced images exceeds this threshold, it is determined that the front of the current scanned test paper of the class has been traced; when the proportion of back-side traced images exceeds this threshold, it is determined that the back of the current scanned test paper of the class has been traced.

[0087] If the ratio of trace images on both the front and back exceeds the first preset threshold, then based on the trace detection results of a single student, a supplementary judgment is performed on the individual student's page that has not left a trace (e.g., the judgment result of the class as a whole is given priority, and it is assumed that the student's page has left a trace).

[0088] Application of the second preset threshold: The ratio of front or back images of student answers in the sample refers to the proportion of the number of student images with valid answer traces detected on the front to the total number of all student front images in the second sample set (which may be the same set as the first sample set), and the proportion of the number of student images with valid answer traces detected on the back to the total number of all student back images in the sample set.

[0089] The second preset threshold is a proportion threshold set based on the prevalence of answers (e.g., 50%). When the proportion of front-side answer images exceeds this threshold, it is determined that the front of the currently scanned test paper for that class contains answers; when the proportion of back-side answer images exceeds this threshold, it is determined that the back of the currently scanned test paper for that class contains answers.

[0090] If the ratio of the answer images on both the front and back exceeds the second preset threshold, the double-sided grading logic is triggered directly; if only the ratio on one side exceeds the threshold, the individual student's answer detection results are combined to perform a secondary verification on the individual student's page that does not meet the standard (such as confirming whether it is a misjudgment caused by blurry scanning), and finally determine that the page is in single-page grading mode.

[0091] A device for determining whether a paper is single-sided or double-sided, including:

[0092] Scanning unit: Used to scan the paper to be graded;

[0093] Recognition Unit: Used to extract samples from the scanned papers to be graded, determine the papers, and execute judgment logic to determine the grading mode. This includes front and back recognition of the sample papers, paper determination through image similarity recognition and / or text OCR recognition, execution of trace determination logic, and whether an answer has been given.

[0094] Sample extraction unit: used to extract the first sample set and the second sample set from the scanned test papers to be graded;

[0095] Judgment Logic Execution Unit: Used to execute the first judgment logic and the second judgment logic, wherein the first judgment logic can be the record-keeping judgment logic or the whether to answer judgment logic, and the second judgment logic is another judgment logic corresponding to the first judgment logic, and the grading mode is determined according to the judgment result;

[0096] Threshold setting unit: used to preset various judgment thresholds, including the first preset threshold, the second preset threshold, the third preset threshold, the fourth preset threshold, the fifth preset threshold, the sixth preset threshold, etc., to provide quantitative standards for the execution of judgment logic.

[0097] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement a method for determining whether a paper is single-sided or double-sided.

[0098] A computer-readable storage medium stores non-transitory computer-readable instructions, which, when executed by a computer, enable the aforementioned method for determining single-sided or double-sided marking of exam papers.

[0099] Working principle: Scan and upload the papers to be graded; extract samples from the uploaded papers to obtain a first sample set of papers; perform a paper determination judgment on the first sample set of papers, and then execute the first judgment logic; if the first judgment logic determines the grading mode, the judgment ends; if the first judgment logic does not determine the grading mode, extract samples from the papers to be graded to obtain a second sample set of papers; perform a paper determination judgment on the second set of papers, and then execute the second judgment logic to confirm the grading mode.

[0100] In addition, the aforementioned scanning unit, recognition unit, sample extraction unit, threshold setting unit, and judgment logic execution unit are also used to implement other functions of the above-mentioned single-sided and double-sided marking judgment method, which will not be elaborated here.

[0101] In addition, the present invention also provides a terminal device. The method for judging single-sided and double-sided corrections in this embodiment is mainly applied in the terminal device, which can be a PC, a portable computer, a mobile terminal or other device with display and processing functions.

[0102] Specifically, the terminal device may include a processor (e.g., CPU), a communication bus, a user interface, a network interface, and memory. The communication bus is used to enable communication between these components; the user interface may include a display screen or an input unit such as a keyboard; the network interface may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface); the memory may be high-speed RAM or stable non-volatile memory, such as disk storage, and may also optionally be a storage device independent of the aforementioned processor.

[0103] The memory stores a readable storage medium, which stores a single-sided / double-sided correction determination program. The processor can call the single-sided / double-sided correction determination program stored in the memory and execute the single-sided / double-sided correction determination method provided in this embodiment of the invention.

[0104] Understandably, a readable storage medium can be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer-readable storage medium can be, for example—but not limited to—an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage medium as used herein is not to be construed as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0105] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0106] Computer program instructions used to perform operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions to implement various aspects of this disclosure.

[0107] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for judging whether a paper is single-sided or double-sided, characterized in that: Includes the following steps: Scan the papers to be graded and upload them; The uploaded papers to be graded are sampled to obtain the first sample paper set. Perform front and back recognition on the first sample set of test papers. After the recognition, execute the first judgment logic, which is either the trace retention judgment logic or the question-and-answer judgment logic. If the first judgment logic determines the correction mode, the judgment ends. If the first judgment logic fails to identify the grading mode, then a second sample set of papers will be obtained by sampling the papers to be graded. The obtained second sample set of test papers is used to perform front and back recognition and determination. After the determination, the second determination logic is executed to confirm the grading mode. The second decision logic is another decision logic corresponding to the first decision logic; When the first determination logic is the trace-keeping determination logic, the corresponding second determination logic is the answer-whether-answered determination logic. The trace-keeping determination logic refers to determining whether there is a mark indicating that the front and back images have been marked: obtain the front and back of the first sample. If both the front and back have been marked, then the recognition and marking logic will not be executed on either the front or back. If only one page of the front and back has been marked, then it is determined to be a single-page marking, and the page to be marked is the front or back without a mark. If neither the front nor back has been marked, then the second determination logic will be executed. The answer-whether-answered determination logic further refers to determining whether there are traces of handwritten answers on the front and back of the student's paper. If neither the front nor back has been marked, then it is determined that the paper will not be marked. If only one page of the front and back has been marked, then it is determined to be a single-page marking, and the page marked at the top is the page that has been marked. If both the front and back have been marked, then it is determined to be a double-sided marking logic, and both the front and back will be marked.

2. The method for determining single-sided or double-sided marking of a test paper according to claim 1, characterized in that: The first sample set and the second sample set are the same sample set.

3. The method for judging single-sided and double-sided marking of a test paper according to claim 1, characterized in that: The aforementioned front and back recognition determination refers to determining the front and back of the exam paper information scanned by each student. That is, the first image of the exam paper scanned by each student is defined as the front and the second image as the back. In essence, the front and back of the student's exam paper in all samples is recognized once.

4. The method for determining single-sided or double-sided marking according to claim 3, characterized in that: The determination of the paper surface can be further made through image similarity recognition and / or text OCR recognition; Image similarity refers to acquiring front and back images of student A, randomly defining the first image as the front and the second as the back, and comparing the similarity of other students' images in the sample with the front and / or back images of student A to confirm the front and back of other students in the sample. Text OCR recognition refers to acquiring front and back images of student A, randomly defining the first image as the front and the second as the back, acquiring the OCR text in the front and the OCR text in the back, and then performing OCR recognition on each image of other students in the sample. By matching the similarity with the OCR text of student A's front and / or back images, the front and back of other students can be confirmed.

5. The method for judging single-sided and double-sided marking of a test paper according to claim 1, characterized in that: When the first determination logic is the "whether to answer" determination logic, the corresponding second determination logic is the "traceability" determination logic. The "whether to answer" determination logic further refers to determining whether there are traces of handwritten answers on both sides of the student's exam paper. If neither side is answered, the exam paper will not be graded. If only one page on both sides is answered, it will be graded as a single page, and the page marked at the top will be the page with the answer. If both sides are answered, the second determination logic will continue to be executed. The "traceability" determination logic refers to determining whether there are any marking marks on the front and back images: if both sides of the first sample are marked, the recognition and grading logic will not continue to be executed on either side. If only one page on both sides is marked, it will be graded as a single page, and the page to be graded will be the front or back without a mark. If neither side is marked, it will be graded as a double-sided grading logic, and both sides will be recognized and graded.

6. The method for determining single-sided or double-sided marking of a test paper according to claim 1, characterized in that: In the first determination logic, if the ratio of images with marks on the front or back of the sample is greater than the first preset threshold, it is determined that marks have been left on the front or back. In the second determination logic, if the ratio of images of the front or back of the student's answer in the sample is greater than the second preset threshold, it is determined that the student has answered on the front or back.

7. A device for determining whether a paper is single-sided or double-sided, used to implement the method for determining whether a paper is single-sided or double-sided as described in any one of claims 1-6, comprising: Scanning unit: Used to scan the paper to be graded; Recognition Unit: Used to extract samples from the scanned papers to be graded, determine the papers, and execute judgment logic to determine the grading mode. This includes front and back recognition of the sample papers, paper determination through image similarity recognition and / or text OCR recognition, execution of trace determination logic, and whether an answer has been given. Sample extraction unit: used to extract the first sample set and the second sample set from the scanned test papers to be graded; Judgment Logic Execution Unit: Used to execute the first judgment logic and the second judgment logic, wherein the first judgment logic can be the record-keeping judgment logic or the whether to answer judgment logic, and the second judgment logic is another judgment logic corresponding to the first judgment logic, and the grading mode is determined according to the judgment result; Threshold setting unit: used to preset various judgment thresholds, including the first preset threshold and the second preset threshold, to provide quantitative standards for the execution of judgment logic.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for determining single-sided or double-sided marking of papers as described in any one of claims 1-6.

9. A computer-readable storage medium storing non-transitory computer-readable instructions, which, when executed by a computer, implement the single-sided / double-sided marking determination method according to any one of claims 1-6.

Images