CN-122023385-A - Test paper and packaging bag examinee information synchronous printing method and device

CN122023385ACN 122023385 ACN122023385 ACN 122023385ACN-122023385-A

Abstract

A test paper and packaging bag examinee information synchronous printing method and device relate to the technical field of production printing. The method comprises the steps of obtaining identity information of a test paper to be tested to determine examination question information, generating a first printing task and a second printing task according to the identity information and the examination question information, controlling first printing equipment and second printing equipment to execute the first printing task and the second printing task to obtain a target test paper and a target packaging bag, conveying the target test paper and the target packaging bag to a preset rechecking position to extract actual measurement full images of the target test paper to obtain an actual measurement feature vector group, calculating the actual measurement feature vector group and a standard image feature set to obtain comprehensive image matching degree, generating a packaging instruction if the comprehensive image matching degree is larger than or equal to a preset matching threshold, loading the target test paper into the target packaging bag for sealing, and generating an abnormal processing signal if the comprehensive image matching degree is smaller than the preset matching threshold. By implementing the method, the accuracy of matching the test paper with the packaging bag is improved.

Inventors

ZHANG YINHAO
FU FENGYUN
XIA XIANFENG
DUAN CHENG
CHEN WEIJIU
LIU NU

Assignees

重庆市远大印务有限公司

Dates

Publication Date: 20260512
Application Date: 20260319

Claims (10)

1. The test paper and packaging bag examinee information synchronous printing method is characterized by comprising the following steps: Responding to a production instruction, acquiring examination report information corresponding to test-taker identity information, determining examination question information based on the examination report information, and generating a first printing task and a second printing task according to the test-taker identity information and the examination question information, wherein the first printing task is used for printing test paper of the examination question information, and the second printing task is used for printing the test-taker identity information on a packaging bag; generating a corresponding standard image feature set based on the digital layout information of the first printing task, and associating the standard image feature set with the test-subject identity information; controlling a first printing device to execute the first printing task to obtain a target test paper, controlling a second printing device to execute the second printing task to obtain a target packaging bag, and conveying the target test paper and the target packaging bag to a preset rechecking position; After confirming that the target test paper and the target packaging bag are at the preset rechecking position, acquiring an actual measurement full-image of the target test paper, and identifying identity information on the target packaging bag; Extracting the characteristics of the measured full-image according to the corresponding standard image characteristic set called by the identity information to obtain a measured characteristic vector group; Comparing and calculating the actually measured characteristic vector group with the standard image characteristic set to obtain comprehensive image matching degree; if the comprehensive image matching degree is greater than or equal to a preset matching threshold value, generating a packaging instruction, and controlling packaging equipment to load the target test paper into the target packaging bag and seal the target test paper; And if the comprehensive image matching degree is smaller than the preset matching threshold value, generating an abnormal processing signal.
2. The method according to claim 1, wherein the feature extraction is performed on the measured full image to obtain a set of measured feature vectors, and specifically includes: Identifying all independent pixel communication areas in the actually measured full image, and calculating the circumscribed rectangular bounding box of each independent pixel communication area; Acquiring centroid coordinates, area occupation ratios and length-width ratios of the circumscribed rectangular bounding boxes, arranging the centroid coordinates, the area occupation ratios and the length-width ratios of all the independent pixel communication areas according to a preset sequence to obtain topological geometric features, and taking the topological geometric features as macroscopic layout data; Dividing the actually measured full image based on a preset sampling rule to obtain a plurality of local verification areas, extracting image texture features from each local verification area, and taking the image texture features as local texture fingerprint data; Analyzing a digital layout file corresponding to the first printing task, and acquiring a preset coordinate range of identity information of an examinee in the digital layout file; Mapping the preset coordinate range to the actual measurement full-image to obtain an interested region; performing optical character recognition on the region of interest to obtain key region semantic data; and carrying out normalization processing and splicing on the macroscopic layout data, the local texture fingerprint data and the key region semantic data to obtain the actual measurement feature vector group.
3. The method according to claim 2, wherein the dividing the measured full image based on a preset sampling rule to obtain a plurality of local verification areas specifically includes: Analyzing the digital layout information of the first printing task, extracting high-frequency vector graphic elements in the digital layout information, constructing a virtual grid layer based on the distribution density of the high-frequency vector graphic elements, and calculating the information entropy weight of each grid unit; generating a dynamic pseudo-random sequence according to the information entropy weight, and screening the virtual grid layer by using the dynamic pseudo-random sequence to obtain a discrete coordinate point set; mapping the discrete coordinate point set onto the actually measured full-image, and taking the mapped point as a center, and intercepting an image fragment by using a preset irregular polygonal window; and performing discrete cosine transform on the intercepted image fragment, filtering direct current components, extracting an intermediate frequency coefficient matrix, and performing inverse transformation and restoration on the intermediate frequency coefficient matrix to obtain a spatial domain image so as to obtain the local verification region after frequency domain filtering.
4. The method according to claim 2, wherein the comparing the measured feature vector set with the standard image feature set to obtain a comprehensive image matching degree specifically includes: acquiring the dimension length of the actually measured feature vector group, and dividing the actually measured feature vector group according to the dimension length and the splicing sequence to obtain a first sub-vector, a second sub-vector and a third sub-vector; restoring the first sub-vector into actual measurement macroscopic layout data, restoring the second sub-vector into actual measurement local texture fingerprint data, and restoring the third sub-vector into actual measurement key region semantic data; Retrieving standard macro layout data corresponding to the actual measurement macro layout data, standard local texture fingerprint data corresponding to the actual measurement local texture fingerprint data, and standard key region semantic data corresponding to the actual measurement key region semantic data from the standard image feature set; Extracting an actual measurement centroid coordinate set from the actual measurement macroscopic layout data, extracting a standard centroid coordinate set from the standard macroscopic layout data, and calculating the actual measurement centroid coordinate set and the standard centroid coordinate set to obtain the maximum geometric deviation; Converting the actually measured local texture fingerprint data into an actually measured binary code sequence, converting the standard local texture fingerprint data into a standard binary code sequence, and performing bitwise exclusive OR logic operation on the binary code sequence and the standard binary code sequence to obtain an operation result; counting the target number of binary digits of 1 in the operation result, and dividing the target number by the total digits of the sequence to obtain a logic error rate; converting the actual measurement key region semantic data into an actual measurement character sequence, and converting the standard key region semantic data into a standard character sequence; Calculating the minimum single character editing operation times required for converting the actually measured character sequence into the standard character sequence based on a Lychnostan distance algorithm, and taking the editing operation times as character conversion cost; Constructing a three-dimensional rectangular coordinate system according to the maximum geometric deviation, the logic error rate and the character transformation cost, and respectively serving as components of an X axis, a Y axis and a Z axis to obtain a difference feature vector; Calculating Euclidean modular length of the difference feature vector to obtain comprehensive difference modular length; and mapping calculation is carried out on the comprehensive difference module length based on a preset inverse proportion normalization function, and the comprehensive image matching degree is obtained.
5. The method of claim 4, wherein the calculating the measured centroid coordinate set and the standard centroid coordinate set results in a maximum geometric deviation, specifically comprising: Acquiring a target actual measurement point from the actual measurement centroid coordinate set, wherein the target actual measurement point is any one of a plurality of actual measurement coordinate points in the actual measurement centroid coordinate set; Calculating Euclidean distances between the target actual measurement point and each standard coordinate point in the standard centroid coordinate set to obtain a current distance set; Screening a minimum value from the current distance set, and taking the minimum value as the nearest neighbor matching distance of the target actual measurement point; acquiring the nearest neighbor matching distances corresponding to all real measurement points in the actual measurement centroid coordinate set, and forming a distance sequence from the nearest neighbor matching distances corresponding to all the real measurement points; and screening a maximum value from the distance sequence, and taking the maximum value as the maximum geometric deviation degree.
6. The method of claim 1, wherein prior to said capturing the measured full image of the target test paper and identifying the identification information on the target envelope, the method further comprises: acquiring a theoretical weight range of the target test paper, and acquiring an actual measurement weight value of the target test paper; judging whether the measured weight value is in the theoretical weight range; If the measured weight value is in the theoretical weight range, judging that the physical state of the target test paper is normal, and acquiring the measured full-image of the target test paper; And if the measured weight value is not in the theoretical weight range, judging that the physical state of the target test paper is abnormal, and generating a weight abnormality processing signal.
7. The method according to claim 1, wherein generating an exception handling signal if the integrated image matching degree is smaller than the preset matching threshold value, specifically comprises: When the comprehensive image matching degree is smaller than the preset matching threshold, acquiring an identity code corresponding to the target test paper, and storing the identity code and the comprehensive image matching degree into a production log database; judging whether the comprehensive image matching degree is smaller than a preset serious error threshold value or not, wherein the preset serious error threshold value is smaller than the preset matching threshold value; If the comprehensive image matching degree is smaller than the preset serious error threshold, judging that the identity of the target test paper is not matched with the identity of the target packaging bag, generating a reprinting instruction aiming at the identity code based on the identity mismatching, and printing according to the reprinting instruction; And if the comprehensive image matching degree is greater than or equal to the preset serious error threshold, generating a manual review prompt signal to prompt an operator to perform appearance inspection on the target test paper.
8. The test paper and packaging bag examinee information synchronous printing device is characterized by comprising an acquisition unit, a processing unit and an evaluation unit, The acquisition unit is used for responding to a production instruction, acquiring examination report information corresponding to test-taker identity information, determining examination question information based on the examination report information, and generating a first printing task and a second printing task according to the test-taker identity information and the examination question information, wherein the first printing task is used for printing a test paper of the examination question information, and the second printing task is used for printing the test-taker identity information on a packaging bag; The processing unit is used for generating a corresponding standard image feature set based on the digital layout information of the first printing task, associating the standard image feature set with the test-subject identity information, controlling a first printing device to execute the first printing task to obtain a target test paper, controlling a second printing device to execute the second printing task to obtain a target packaging bag, conveying the target test paper and the target packaging bag to a preset checking position, acquiring an actual measurement full image of the target test paper after confirming that the target test paper and the target packaging bag are positioned at the preset checking position, identifying the identity identification information on the target packaging bag, extracting features of the actual measurement full image according to the identity identification information, obtaining an actual measurement feature vector group, and comparing and calculating the actual measurement feature vector group and the standard image feature set to obtain comprehensive image matching degree; The evaluation unit is used for generating a packaging instruction if the comprehensive image matching degree is larger than or equal to a preset matching threshold value, controlling packaging equipment to load the target test paper into the target packaging bag and seal the target test paper, and generating an exception processing signal if the comprehensive image matching degree is smaller than the preset matching threshold value.
9. An electronic device comprising a processor, a memory, a user interface, and a network interface, the memory for storing instructions, the user interface and the network interface for communicating with other devices, the processor for executing the instructions stored in the memory to cause the electronic device to perform the method of any of claims 1-7.
10. A computer readable storage medium storing instructions which, when executed, perform the method of any one of claims 1-7.

Description

Test paper and packaging bag examinee information synchronous printing method and device Technical Field The application relates to the technical field of production printing, in particular to a test paper and packaging bag examinee information synchronous printing method and device. Background The study and the recruitment examination have the characteristics of large scale, multiple subjects, high confidentiality requirement and the like. Unlike general exams, examers in the same examination room in research exams often refer to different examination-reporting institutions and professions, so that the types of required test papers are various, and the examination papers have high individuation characteristics. Therefore, in the test paper production process, the accurate matching of the test paper content and the identity information of the examinees is realized, and each examinee is ensured to accurately acquire the flaw-free test paper of the corresponding department purpose, so that the method is a key link for ensuring fair and smooth examination. The existing test paper and test paper bag production usually adopts an automatic assembly line to carry out operation. Generally, a step-by-step production mode is adopted, namely, test paper is firstly printed in batches according to the classification of subjects, and meanwhile, test paper bags printed with examinee information are independently printed. In the subsequent packaging link, the production line device reads the bar code on the test paper and the identification code on the test paper bag through an industrial camera or a code scanning gun, the read bar code information is logically compared by utilizing a background system, and when the bar code information is judged to be consistent, the mechanical device is controlled to load the test paper into the corresponding test paper bag, so that automatic matching and packaging are completed. However, the above-mentioned prior art has a major disadvantage in that only the matching of the "code" can be confirmed, but the "actual printed content" of the test paper cannot be substantially verified. If the data transmission errors occur in the printing process, the bar code is inconsistent with the content of the roll surface, and the content-level errors cannot be recognized completely by simple code scanning verification. Once such errors occur, the examinee may not normally test, the fairness and fairness of the test are seriously affected, and the public trust of the test organization is greatly damaged. Disclosure of Invention The application provides a test paper and packaging bag examinee information synchronous printing method and device, which solve the problem that the actual printing content cannot be found by only depending on bar code matching in the prior art, and improve the accuracy of the test paper and packaging bag matching. In a first aspect, the application provides a test paper and test taker information synchronous printing method of a packaging bag, the method comprises the steps of responding to a production instruction, obtaining test taker information corresponding to test taker identity information, determining test taker information based on the test taker information, generating a first printing task and a second printing task according to the test taker identity information and the test taker information, wherein the first printing task is used for printing the test paper of the test taker information, and the second printing task is used for printing the test taker identity information on the packaging bag; the method comprises the steps of generating a corresponding standard image feature set based on digital layout information of a first printing task, associating the standard image feature set with identity information of a test person, controlling first printing equipment to execute the first printing task to obtain a target test paper, controlling second printing equipment to execute the second printing task to obtain a target packaging bag, conveying the target test paper and the target packaging bag to a preset rechecking position, obtaining an actual measurement full-size image of the target test paper after confirming that the target test paper and the target packaging bag are at the preset rechecking position, identifying identity information on the target packaging bag, calling the corresponding standard image feature set according to the identity information, carrying out feature extraction on the actual measurement full-size image to obtain an actual measurement feature vector set, comparing and calculating the actual measurement feature vector set with the standard image feature set to obtain comprehensive image matching degree, generating a packaging instruction if the comprehensive image matching degree is larger than or equal to a preset matching threshold, controlling the packaging equipment to load the target test paper into the target packaging bag and