CN115690815A

CN115690815A - Paper job processing method, device, equipment and storage medium

Info

Publication number: CN115690815A
Application number: CN202211386989.5A
Authority: CN
Inventors: 苏臻
Original assignee: Dongguan Bubugao Education Software Co ltd
Current assignee: Dongguan Bubugao Education Software Co ltd
Priority date: 2022-11-07
Filing date: 2022-11-07
Publication date: 2023-02-03

Abstract

The application discloses a paper job processing method, a paper job processing device, paper job processing equipment and a storage medium, and relates to the technical field of intelligent learning. The technical scheme provided by the application comprises the following steps: determining writing handwriting in paper operation according to dot matrix units in the plurality of first images, and generating a second image of the paper operation according to the writing handwriting, wherein the first image is obtained by shooting by a dot matrix pen when the dot matrix pen writes in the paper operation printed with the dot matrix units; extracting the operation content of the paper operation from the second image through a character recognition algorithm, analyzing the operation content and determining a target knowledge point to be learned; and acquiring a target exercise from a preset exercise library according to the target knowledge point, and generating a target operation file according to the target exercise. By the technical means, the accuracy of the paper operation image and the identification accuracy of the operation content are improved, the reliability of the analysis result is ensured, and the problem of low reliability of the operation analysis result in the prior art is solved.

Description

Paper job processing method, device, equipment and storage medium

Technical Field

The present application relates to the field of intelligent learning technologies, and in particular, to a paper job processing method, apparatus, device, and storage medium.

Background

In recent years, with popularization and application of intelligent learning devices in the field of education, intelligent education devices are widely favored by students. The intelligent learning equipment can identify and analyze the character content input by the student by means of a character identification technology and an artificial intelligence technology, so that the learning condition of the student is evaluated, and the learning experience of the student is greatly optimized. However, the intelligent learning device generally depends on the electronic display screen for interaction, if a student writes homework through the touch display device, the student can have eyesight damage if using the electronic display screen for a long time, the time of using an electronic product by the student is strictly controlled, and the student writes paper homework as much as possible.

In the prior art, a camera is generally used to shoot an image of a paper job, the job content is identified through the image, and the job content is analyzed through an artificial intelligence technology. However, the paper operation image is affected by the size of the picture, image distortion and the like, the identification accuracy of the operation content is low, and the reliability of the analysis result cannot be guaranteed.

Disclosure of Invention

The application provides a paper job processing method, a device, equipment and a storage medium, so that when a user writes on a paper job printed with a dot matrix unit by using a dot matrix pen, an image containing the dot matrix unit and writing handwriting is obtained, and a highly restored paper job image is generated according to the dot matrix unit and the writing handwriting in the image, the precision of the paper job image and the recognition accuracy of job content are improved, the reliability of an analysis result is ensured, and the problem that the reliability of a job analysis result is low in the prior art is solved.

In a first aspect, the present application provides a paper job processing method, including:

determining writing handwriting in paper operation according to dot matrix units in a plurality of first images, and generating a second image of the paper operation according to the writing handwriting, wherein the first image is obtained by shooting by a dot matrix pen when the dot matrix pen writes in the paper operation printed with the dot matrix units;

extracting the operation content of the paper operation from the second image through a character recognition algorithm, analyzing the operation content and determining a target knowledge point to be learned;

and acquiring a target exercise from a preset exercise library according to the target knowledge point, and generating a target operation file according to the target exercise.

Further, before the determining the handwriting in the paper job according to the dot matrix units in the plurality of first images, the method further includes:

acquiring a preset dot matrix image, wherein the dot matrix image comprises a plurality of different dot matrix units, each dot matrix unit comprises a preset number of code points, and each code point is one pixel point in a preset pixel matrix;

overlapping the test question image and the dot matrix image to obtain a test question file to be printed;

and sending the test question file to be printed to a printing device connected in advance so as to enable the printing device to print the paper operation printed with the dot matrix unit.

Further, after the overlaying process is performed on the test question image and the dot matrix image, the method further includes:

determining the position information of the test question contents in the dot matrix image according to the dot matrix unit covered by each test question content in the test question image, and storing the test question contents and the corresponding position information in a correlation manner;

and deleting the dot matrix unit covered by the test question content in the test question image, and reserving the dot matrix unit of the answer area in the test question image.

Further, the determining writing handwriting in paper work according to the dot matrix units in the plurality of first images and generating a second image of the paper work according to the writing handwriting includes:

identifying a dot matrix unit in the first image, and determining the position information of the dot matrix unit in the dot matrix image;

generating corresponding writing handwriting according to the pixel points in the dot matrix unit, and determining the position information corresponding to the writing handwriting according to the position information of the dot matrix unit;

acquiring test question contents corresponding to the paper operation according to the position information of the dot matrix unit;

and respectively drawing the writing handwriting and the test question content according to the position information of the writing handwriting and the position information of the test question content to obtain the second image.

Further, the drawing the writing script and the test question content according to the position information of the writing script and the position information of the test question content respectively includes:

determining writing time of the handwriting corresponding to the dot matrix unit according to the acquisition time of the first image;

and drawing the corresponding position information positions of the writing handwriting in sequence according to the writing time sequence of the writing handwriting.

Further, the extracting the job content of the paper job from the second image through a character recognition algorithm includes:

determining the stroke writing sequence of each character in the second image according to the drawing sequence of each writing handwriting in the second image;

and recognizing the answer content in the second image according to the stroke writing sequence of each character.

Further, the recognizing the job content in the second image according to the stroke writing order of each character includes:

screening matched target characters from a preset character database according to the stroke writing sequence of each character;

and under the condition that the target characters do not exist in the preset character database, identifying the target characters corresponding to the stroke writing sequence through an image character identification algorithm, and marking the target characters as stroke writing sequence errors.

Further, after the test question content corresponding to the paper job is obtained, the method further includes:

determining the answer writing handwriting of the test question content according to the position information of the writing handwriting and the position information of the test question content;

and determining the answer duration of the test question content according to the writing time of the answer writing.

Further, the analyzing the job content to determine a target knowledge point to be learned includes:

acquiring answer content corresponding to each test question content from the operation content, and modifying the answer content according to the answer content and the standard answers of the test question content to obtain a modifying result;

analyzing the correction result and the answer duration through a pre-trained answer analysis model to obtain a learning score output by the answer analysis model;

and taking the knowledge points corresponding to the test question content as the target knowledge points under the condition that the learning score is smaller than a preset score threshold value.

Further, the printing device is a thermal sensitive printing device, and the dot matrix pen is provided with an infrared camera and a light supplementing light source; or the printing device is a thermal-sensitive carbon ribbon printing device, and the dot matrix pen is provided with an infrared camera.

In a second aspect, the present application provides a paper job processing apparatus comprising:

the operation acquisition module is configured to determine writing handwriting in paper operation according to dot matrix units in a plurality of first images and generate a second image of the paper operation according to the writing handwriting, wherein the first image is obtained by shooting by a dot matrix pen when the dot matrix pen writes in the paper operation printed with the dot matrix units;

the job analysis module is configured to extract job contents of the paper job from the second image through a character recognition algorithm, analyze the job contents and determine a target knowledge point to be learned;

and the operation customizing module is configured to acquire a target exercise from a preset exercise library according to the target knowledge point and generate a target operation file according to the target exercise.

In a third aspect, the present application provides an unmanned device comprising:

one or more processors; a storage device storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the paper job processing method according to the first aspect.

In a fourth aspect, the present application provides a storage medium containing computer-executable instructions for performing the paper job processing method of the first aspect when executed by a computer processor.

Determining writing handwriting in paper operation according to dot matrix units in a plurality of first images, and generating a second image of the paper operation according to the writing handwriting, wherein the first image is obtained by shooting by a dot matrix pen when the dot matrix pen writes in the paper operation printed with the dot matrix units; extracting the operation content of the paper operation from the second image through a character recognition algorithm, analyzing the operation content and determining a target knowledge point to be learned; and acquiring a target exercise from a preset exercise library according to the target knowledge point, and generating a target operation file according to the target exercise. By the technical means, when a user writes on the paper operation printed with the dot matrix unit by using the dot matrix pen, the image containing the dot matrix unit and the writing handwriting is obtained, and the highly restored paper operation image is generated according to the dot matrix unit and the writing handwriting in the image, so that the accuracy of the paper operation image and the identification accuracy of operation contents are improved, and the reliability of an analysis result is ensured. Analyzing the mastery degree of the knowledge points corresponding to the test question contents by the user according to the answer duration and the correction result of each test question content in the operation contents, thereby determining the target knowledge points which the user needs to strengthen learning. And summarizing the target exercises corresponding to the target knowledge points in the preset exercise library into a target operation file, so that the user can strengthen the learning of the target knowledge points by finishing the target operation file, and the learning efficiency of the user is improved.

Drawings

Fig. 1 is a flowchart of a paper job processing method according to an embodiment of the present application;

FIG. 2 is a flow chart of a print paper job provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of a lattice unit provided in an embodiment of the present application;

FIG. 4 is a flowchart of generating a test question file to be printed according to an embodiment of the present application;

FIG. 5 is a flow chart for generating a paper job image according to an embodiment of the present application;

FIG. 6 is a flow chart of drawing writing script provided by the embodiment of the present application;

fig. 7 is a flowchart of identifying answer content according to an embodiment of the present application;

FIG. 8 is a flow chart for recognizing text based on stroke writing order provided by an embodiment of the present application;

fig. 9 is a flowchart for determining answer duration according to an embodiment of the present application;

FIG. 10 is a flow chart of determining target knowledge points in an embodiment of the present application;

fig. 11 is a schematic structural diagram of a paper job processing apparatus according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of a paper job processing apparatus according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, specific embodiments of the present application will be described in detail with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some but not all of the relevant portions of the present application are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. A process may be terminated when its operations are completed, but could have additional steps not included in the figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.

The paper job processing method provided in this embodiment may be executed by a paper job processing device, where the paper job processing device may be implemented in a software and/or hardware manner, and the paper job processing device may be formed by two or more physical entities or may be formed by one physical entity. For example, the paper job processing device may be a mobile terminal device such as a mobile phone, a computer, a learning tablet, or the like, and may also be a main control module of a printing device.

The paper job processing equipment is provided with at least one type of operating system, and the paper job processing equipment can be provided with at least one application program based on the operating system, wherein the application program can be an application program carried by the operating system or an application program downloaded from a third-party device or a server. In this embodiment, the paper job processing apparatus has at least an application program that can execute the paper job processing method, and therefore, the paper job processing apparatus may also be the application program itself. For example, the paper job processing apparatus may also be a mobile terminal apparatus on which learning software is installed.

For convenience of understanding, the present embodiment is described taking a main control module of a printing apparatus as an example of a main body that executes a paper job processing method.

In one embodiment, after a user writes a paper homework, a camera of the intelligent learning device is used for shooting an image of the paper homework, the intelligent learning device conducts character recognition on the image to obtain homework content of the paper homework, and the homework content is analyzed to evaluate learning conditions of students on various knowledge points. However, images captured by the camera are affected by screen size, image distortion and the like, and the accuracy of identifying the job content is low, which leads to low reliability of the analysis result.

In order to solve the above problems in the prior art, this embodiment provides a paper job processing method to obtain a high-precision paper job image and improve the reliability of an analysis result.

Fig. 1 is a flowchart of a paper job processing method according to an embodiment of the present application. Referring to fig. 1, the paper job processing method specifically includes:

s110, determining writing handwriting in paper operation according to the dot matrix units in the plurality of first images, and generating a second image of the paper operation according to the writing handwriting, wherein the first image is obtained by shooting by a dot matrix pen when the dot matrix pen writes in the paper operation printed with the dot matrix units.

In this embodiment, the printing device establishes a communication connection with the dot-matrix pen in advance, for example, the printing device performs a bluetooth connection with the dot-matrix pen. When a user writes on paper operation printed with the dot matrix unit by using the dot matrix pen, the neighborhood range of the pen point is located in the shooting area of the camera of the dot matrix pen, and the dot matrix pen can shoot writing left by the pen point on the paper operation by the camera to obtain a first image containing the dot matrix unit and the writing. The dot matrix pen sends the first image shot in real time to the printing equipment through Bluetooth, so that a main control module of the printing equipment restores a second image of the paper job through the first image.

In one embodiment, the printing device may print out a paper job printed with dot matrix elements. Fig. 2 is a flowchart of a printing paper job provided in an embodiment of the present application. As shown in fig. 2, the step of printing the paper job specifically includes S1101-S1103:

s1101, acquiring a preset dot matrix image, wherein the dot matrix image comprises a plurality of different dot matrix units, each dot matrix unit comprises a preset number of code points, and each code point is a pixel point in a preset pixel matrix.

Fig. 3 is a schematic diagram of a lattice unit provided in an embodiment of the present application. As shown in fig. 3, the dot matrix unit is a 15 × 15 pixel matrix 11, the 15 × 15 pixel matrix 11 includes white pixels and black pixels, and the black pixels are code points in the dot matrix unit. The lattice unit comprises 25 code points. The code point is a pixel point in the 2 × 2 pixel matrix 12, and a pixel is spaced between the 2 × 2 pixel matrix 12 corresponding to each code point and the 2 × 2 pixel matrix 12 corresponding to the adjacent code point. In the 2 × 2 pixel matrix 12, the probability of a code point position is 4, so there may be 4^20=1099511627776 different lattice units. In the present embodiment, in order to ensure that the dot matrix unit is printed, the accuracy of the printing apparatus is at least higher than 300dpi, that is, the size of one pixel is 84um × 84um or less. If the printing device prints a paper job of 4A size with an accuracy of 300dpi, 2866 ten thousand paper jobs can be printed without repetition of dot matrix units. Therefore, each dot matrix unit can represent unique position information in paper operation, correspondingly, the position information of the dot matrix unit in the paper operation can be determined by identifying the dot matrix unit in the first image, and then writing handwriting in the dot matrix unit is drawn at the position corresponding to the position information, so that the high restoration of the writing handwriting in the paper operation is realized.

In this embodiment, a plurality of preset dot matrix images are generated by combining the dot matrix units in advance, and the position information of the dot matrix units in the preset dot matrix images is recorded. For example, assuming that the dot matrix unit in fig. 3 is located in the first row and the first column of the first sheet in the preset dot matrix image, the position information of the dot matrix unit is recorded as (1,1,1). When the dot matrix unit in the first image is identified as the dot matrix unit shown in fig. 3 subsequently, it is determined that the handwriting of the dot matrix unit in the first image is located in a first row and a first column in a preset dot matrix image.

In the present embodiment, an unused dot matrix image is acquired from dot matrix images generated in advance. For example, if the previous 3 dot matrix images have been used to print another paper job, the 4 th dot matrix image is acquired to print the current paper job. It should be noted that how many dot-matrix images are acquired is determined by the number of sheets of the paper job, but the acquisition principle is not changed.

And S1102, overlapping the test question image and the dot matrix image to obtain a test question file to be printed.

Illustratively, the test question image is scaled to A4 size and then covered above the dot matrix image, so as to obtain the test question file to be printed. The test question file to be printed is an electronic version of the paper operation printed with the dot matrix unit.

In an embodiment, fig. 4 is a flowchart of generating a test question file to be printed according to an embodiment of the present application. As shown in fig. 4, the step of generating the test question file to be printed specifically includes S11021 to S11022:

s11021, determining the position information of the test question contents in the dot matrix image according to the dot matrix unit covered by each test question content in the test question image, and storing the test question contents and the corresponding position information in a related mode.

Illustratively, the test question image includes a text area where the test question content is located and a blank answer area. Generally, a blank area below the test question content is a corresponding answer area, and a user writes a corresponding answer in the answer area by using a dot-matrix pen, that is, a first image captured by the dot-matrix pen is directed to a dot-matrix unit of the answer area. Based on the dot matrix unit in the first image, the handwriting in the paper work can be obtained, but the test question content in the paper work can not be obtained. Therefore, after the test question image is covered above the dot matrix image, the position information of the test question content in the dot matrix image can be recorded based on the position information of the dot matrix unit covered by the test question content, so that the test question content in the paper work can be restored based on the position information of the test question content subsequently, and the highly restored paper work image is obtained.

S11022, deleting the dot matrix units covered by the test question contents in the test question image, and reserving the dot matrix units of the answer areas in the test question image.

Illustratively, if the lattice units are laid on the test question content part, the lattice units can influence the user to read the test question content, so the lattice units covered by the test question content are deleted, and only the lattice units in the answer area are reserved.

And S1103, sending the test question file to be printed to a printing device connected in advance so that the printing device prints the paper job printed with the dot matrix unit.

In this embodiment, the printing apparatus includes a printing device, a main control module, a display module, an input module, and a communication module, and the printing device, the display module, the input module, and the communication module are all connected to the main control module. The main control module is used for executing the paper job processing method and coordinating and controlling the information of other modules, the main control module usually uses a CPU or an MCU as a control processor, and the main control module also comprises a power supply module which supplies power to the printing equipment through a battery or an external power supply; the display module is used for man-machine interaction, and a user can input a control instruction according to the instruction of the display module so that the printing equipment can complete corresponding operation according to the control instruction, and can also check test question contents, test question files to be printed, operation analysis results and the like through the display module. The input module comprises an operation input module and an image input module, the operation input module can use keys to input or touch a screen to input a control command, the image input module is a module for inputting characters and image contents to be printed by the printing device, the printing contents can be selected and obtained from the stored contents of the machine body, or obtained from intelligent terminal equipment such as a mobile phone connected with the communication module, or obtained by downloading from the network, or obtained by inputting through a camera or a CIS scanning sensor; the communication module is a module for connecting the printing equipment with a network, the printing equipment can be networked through a cellular network such as 5G/4G/3G/2G or WiFi, and can also be connected with the intelligent terminal equipment and the dot matrix pen through Bluetooth; the printing device is used for printing test question files to be printed or other printing contents transmitted by the main control module.

After the master control module generates the test question file to be printed, the test question file to be printed is sent to the printing device, and the printing device prints the test question file to be printed on paper to obtain paper operation printed with the dot matrix units. In this embodiment, in order to ensure that the code points in the first image shot by the dot matrix pen are clear, the printing device may adopt a thermal printing device or a thermal carbon ribbon printing device, the edges of the pixel points printed by these two printing devices are clear, the pixel points are complete, and each code point can be clearly presented. In addition, the two printing devices are small in size and suitable for desktop application, so that the two printing devices are suitable for being used as special printing devices for user learning. If the printing device adopts a thermal printing device, thermal paper is adopted as printing paper, and a printing head of the printing device realizes printing of images and characters by heating the thermal paper. If the printing device adopts a thermal carbon tape printing device, the printing paper can adopt common paper. And laser printer and ink jet printer's precision can only print the code point at 1200dpi at least, and the code point edge is unclear difficult to discernment moreover, compares in adopting laser printer or ink jet printer to print the code point, and temperature sensing printing device and temperature sensing carbon ribbon printing device's printing cost is lower and the code point of printing out is more clear, is favorable to improving the accuracy of dot matrix unit discernment.

And after the user takes the paper operation printed with the dot matrix unit, answering the paper operation in an answering area by using a dot matrix pen. The camera of dot matrix pen can shoot the handwriting that the nib was write when the user answered the question, and generate first image, sends first image to printing equipment's communication module through the bluetooth, and communication module sends first image to host system. In this embodiment, the printing device is a thermal ribbon printing device and the dot matrix pen is provided with an infrared camera. Exemplarily, in order to improve the contrast of the first image and reduce the interference of visible light to the identification process of the dot matrix unit, the dot matrix pen adopts an infrared camera, that is, an infrared light source with 850nm waveband is used inside the dot matrix pen, and an optical filter is arranged in front of a photosensitive chip of the camera to filter out light rays with other wavebands, so as to keep different color rendering areas on paper to reflect and image the 850nm infrared waveband. In another embodiment, the printing device is a thermal printing device, and the dot matrix pen is provided with an infrared camera and a light supplementing light source. For example, in a printing apparatus using a thermal printing device, since the thermal paper surface is coated, and the emissivity of light in the infrared band is similar in the areas where black parts are displayed by heating and the areas where white parts are displayed without heating, the dot matrix pen provided with only an infrared camera is not capable of recognizing code dots. Under the condition, the supplementary lighting and supplementary lighting in any wave band between 400 nm and 750nm is additionally arranged inside the dot matrix pen provided with the infrared camera, so that the dot matrix pen can shoot a first image capable of identifying the code points. In addition, when the printing device is a thermal printing device, the dot-matrix pen may be provided with a camera using ambient light as a light source.

Further, after the main control module acquires the first image transmitted by the communication module, the writing handwriting in the paper operation and the position of the writing handwriting in the paper operation are determined according to the first image, the writing handwriting at each position is collected to generate an image of an answer area in the paper operation, and the image of the answer area and the content of the test questions are collected to obtain an image of the paper operation. Fig. 5 is a flowchart for generating a paper job image according to an embodiment of the present application. As shown in fig. 5, the step of generating a paper job image specifically includes S1104-S1107:

s1104, identifying the dot matrix unit in the first image, and determining the position information of the dot matrix unit in the dot matrix image.

Illustratively, approximately three lattice units are displayed in a first image, and the code of the corresponding lattice unit can be determined according to the position of the code point in each lattice unit. The codes of the lattice units and the position information corresponding to the lattice images are stored in a correlated mode, and the position information of the lattice units in the corresponding lattice images can be determined according to the codes of the lattice units. Referring to fig. 3, if a code point is at the top left corner of the 2 × 2 pixel matrix, the corresponding conversion is to a 1000 binary code, if the code point is at the top right corner of the 2 × 2 pixel matrix, the corresponding conversion is to a 0100 binary code, if the code point is at the bottom left corner of the 2 × 2 pixel matrix, the corresponding conversion is to a 0010 binary code, and if the code point is at the bottom right corner of the 2 × 2 pixel matrix, the corresponding conversion is to a 0001 binary code. The 2 x 2 pixel matrix corresponding to all code points in the lattice unit can be converted into 100-bit binary code according to the sequence from top to bottom and from left to right.

S1105, generating corresponding writing handwriting according to the pixel points in the dot matrix unit, and determining the position information of the corresponding writing handwriting according to the position information of the dot matrix unit.

Illustratively, when a user answers on an answer area of a paper job, each pixel point corresponding to the dot matrix unit is covered by ink of the dot matrix pen to generate handwriting, and therefore, the handwriting in the corresponding dot matrix unit can be generated according to the pixel point covered by the ink in the dot matrix unit. Because the dot matrix image and the paper operation are overlapped, the position information of the dot matrix unit in the preset dot matrix image is equivalent to the position information of the writing in the dot matrix unit in the paper operation, and the position information of the dot matrix unit in the dot matrix image can be determined as the position information of the writing in the paper operation. For example, if the dot matrix unit is located in the first row and the first column of the fourth page in the preset dot matrix image, it is determined that the writing script of the dot matrix unit is in the first row and the first column of the fourth page in the paper job. It should be noted that, the paper job of the fourth page mentioned in this embodiment does not indicate that there are at least four pages in the paper job, but indicates the page turning sequence of the page where each writing trace is located in the paper job. For example, if the writing handwriting A and the writing handwriting B are respectively on the fourth page and the fifth page, the page where the writing handwriting B is located can be determined to be located on the next page of the page where the writing handwriting A is located, so that the writing handwriting of each page can be subsequently generated into a paper operation image according to the page turning sequence, and the writing handwriting of the paper operation can be highly restored.

And S1106, acquiring test question contents corresponding to the paper operation according to the position information of the dot matrix unit.

For example, assuming that the position information of the dot matrix unit is the first row and the first column of the first dot matrix image, the test question content with the position information of the first dot matrix image is selected as the test question content of the paper job in which the dot matrix unit is located according to the currently stored position information of all the test question contents.

S1107, respectively drawing the writing and the test question content according to the position information of the writing and the position information of the test question content to obtain a second image.

Illustratively, according to the position information of the handwriting and the position information of the test question content, the handwriting and the test question content are respectively drawn at corresponding positions of the blank image, and a highly restored paper operation image is obtained. In the process of restoring the paper operation image, all the pixel points in the paper operation are restored one to one, so that the accuracy of the paper operation image is ensured.

And if the paper operation comprises a plurality of pages, splicing the page images according to the page turning sequence to obtain the paper operation image. It can be understood that if the answer of a certain test question is written at the bottom of a certain page and the top of the next page, the page images are spliced according to the page turning sequence, so that disorder of written answers can be avoided, the written handwriting of paper operation is highly restored, and the accuracy of subsequent analysis results is ensured.

In this embodiment, fig. 6 is a flowchart for drawing handwriting provided by an embodiment of the present application. As shown in fig. 6, the step of drawing the handwriting specifically includes S11071-S11072:

and S11071, determining the writing time of the writing handwriting of the corresponding dot matrix unit according to the acquisition time of the first image.

Illustratively, when a user writes an answer on a paper job printed with a dot matrix unit by using a dot matrix pen, a first image shot by the dot matrix pen records the writing process of the user, so that the acquisition time of the first image is the writing time of the writing of the dot matrix unit in the first image.

And S11072, drawing the writing handwriting at the corresponding position information in sequence according to the writing time sequence of the writing handwriting.

Illustratively, when the writing handwriting is drawn according to the sequence of writing time, the stroke sequence of the user writing characters on paper operation can be restored, so that the subsequent character recognition can be conveniently carried out according to the stroke sequence of the characters and whether the writing sequence of the characters is correct or not can be judged. And the first image is generated in real time, and the handwriting corresponding to the first image can be drawn whenever the first image is generated, so that the acquisition efficiency of the paper operation image is effectively improved.

And S120, extracting the operation content of the paper operation from the second image through a character recognition algorithm, analyzing the operation content, and determining a target knowledge point to be learned.

In the present embodiment, the job content includes test question content and answer content. Illustratively, the text in the second image can be recognized through an image text recognition algorithm, so that the test question content and the answer content in the paper job are obtained.

Compared with an image character recognition algorithm, the character recognition algorithm based on the stroke sequence is more accurate, and can recognize answer contents in paper quality operation based on the character recognition algorithm based on the stroke sequence and test question contents in paper quality operation based on the image character recognition algorithm. Illustratively, fig. 7 is a flowchart for identifying answer content provided by an embodiment of the present application. As shown in fig. 7, the step of identifying the answer content specifically includes S1201-S1202:

s1201, determining the stroke writing sequence of each character in the second image according to the drawing sequence of each writing in the second image.

For example, the writing scripts in the lattice units can be drawn into a certain stroke of the character, and the writing sequence of the stroke can be obtained according to the drawing sequence of the writing scripts. A plurality of strokes can form a character, and the stroke writing sequence of the corresponding character can be obtained according to the writing sequence of the strokes.

And S1202, recognizing the answer content in the second image according to the stroke writing sequence of each character.

In this embodiment, fig. 8 is a flowchart for recognizing text based on stroke writing order provided by an embodiment of the present application. As shown in FIG. 8, the stroke writing order-based recognition of the text specifically includes S12021-S12022:

s12021, according to the stroke writing sequence of each character, the matched target character is screened out from the preset character database.

S12022, under the condition that the target characters do not exist in the preset character database, the target characters corresponding to the stroke writing sequence are identified through an image character identification algorithm, and the target characters are marked as the stroke writing sequence errors.

Illustratively, each character in the preset character database corresponds to a correct stroke writing sequence, the stroke writing sequence of the character is compared with each correct stroke writing sequence in the preset character database, and the character corresponding to the same correct stroke writing sequence is determined to be a target character of the stroke writing sequence. If the preset character database does not have the correct stroke writing sequence which is the same as the stroke writing sequence, the stroke writing sequence can be indicated to be wrong. At the moment, the target characters corresponding to the stroke writing sequence can be identified through the image character identification algorithm, the target characters are marked as stroke writing sequence errors, so that the stroke writing sequence errors of the target characters can be found when a user checks the analysis result, the stroke writing sequence corresponding to the target characters is corrected, and the learning efficiency of the user is improved.

In this embodiment, the target knowledge point may be understood as a knowledge shortboard for which the user needs to be intensively learned. The answer content in the job content can be compared with the standard answers of the test question content to determine the accuracy of the answer content. And taking the knowledge points with the accuracy lower than that of the test question content of the ruled line as target knowledge points to be learned, so that the user can perform consolidated learning aiming at the target knowledge points, and the answer accuracy is improved to hundreds.

The mastery degree of the knowledge points is not only related to the correct answer rate, but also related to the answer duration, and the longer the answer duration is, the lower the mastery degree of the knowledge points by the user is, so that the mastery degree of the knowledge points by the user can be reflected by determining the answer duration of the user. In this embodiment, fig. 9 is a flowchart for determining a question answering duration according to the embodiment of the present application. As shown in fig. 9, the step of determining the answer duration specifically includes S1203-S1205:

and S1203, determining writing time of the handwriting corresponding to the dot matrix unit according to the acquisition time of the first image.

Illustratively, when a user uses a dot matrix pen to write an answer in a question answering area printed with dot matrix units, a first image shot by the dot matrix pen records the process of the user writing the answer, and therefore the acquisition time of the first image is the writing time of writing handwriting of the dot matrix units in the first image.

S1204, determining the answer writing handwriting of the test question content according to the position information of the writing handwriting and the position information of the test question content.

Illustratively, the blank area below the test question content is the corresponding answer area, so the writing below the test question content can be used as the answer writing of the test question content according to the position information of the writing and the position information of the test question content.

And S1205, determining the answer duration of the test question content according to the writing time of the answer writing.

Illustratively, the answer duration of the test question content is obtained by subtracting the writing time of the first handwriting from the writing time of the last handwriting in the answer writing.

In another embodiment, the time length of answering questions and the operation content are analyzed together to analyze the mastering condition of the user on the knowledge points, and the target knowledge points of the user are accurately determined, so that the user can learn the target knowledge points more conveniently. Illustratively, fig. 10 is a flowchart of determining a target knowledge point in the embodiment of the present application. As shown in fig. 10, the step of determining the target knowledge point specifically includes S1206-S1208:

and S1206, acquiring the answer content corresponding to each test question content from the job content, and modifying the answer content according to the answer content and the standard answers of the test question content to obtain a modification result.

In this embodiment, the correction result includes the correct answer rate and the wrong content. And comparing the answer content with the standard answer to determine a wrong part, and obtaining the answer accuracy according to the score proportion of the wrong part in the standard answer.

S1207, analyzing the correction result and the answering time length through the pre-trained answer analysis model to obtain the learning score output by the answer analysis model.

In this embodiment, the answer analysis model is a neural network model for predicting the learning score of the knowledge point corresponding to the test question content of the user according to the error part, the answer accuracy and the answer duration in the correction result. The learning score can represent the mastery degree of the knowledge points by the user, wherein the higher the learning score is, the higher the mastery degree is, and the lower the learning score is, the lower the mastery degree is.

And S1208, taking the knowledge points corresponding to the test question content as target knowledge points under the condition that the learning score is smaller than the preset score threshold.

In the present embodiment, the preset score threshold is set as the lowest learning score when the user is proficient in mastering the knowledge point corresponding to the test question content. When the learning score is higher than or equal to a preset score threshold value, indicating that the user is skilled to master the knowledge points corresponding to the test question content; and when the learning score is lower than the preset score threshold value, indicating that the user is not skilled in mastering the knowledge points corresponding to the test question content. Therefore, under the condition that the learning score is lower than the preset score threshold value, the knowledge point of the test question content can be used as the target knowledge point to be learned by the user, so that the user can strengthen the learning of the target knowledge point, the learning short boards are supplemented in time, and the learning efficiency and the learning effect of the user are improved.

S130, acquiring a target exercise from a preset exercise library according to the target knowledge points, and generating a target operation file according to the target exercise.

In this embodiment, exercises related to various knowledge points are collected in advance, and the knowledge points and corresponding exercises are stored in a preset exercise library in an associated manner. After the target knowledge points of the user are determined, target exercises suitable for the learning level of the user are searched from a preset exercise library according to the target knowledge points, and customized target operation files are generated according to the target exercises. Illustratively, the target exercise is overlapped with the dot matrix image to generate a target job file, and the target job file is printed on a piece of paper by a printing device, and a user can answer the paper by using a dot matrix pen to strengthen the learning of the target knowledge points. When a user answers, the dot matrix pen shoots a first image, operation content and answering duration are obtained based on the first image, then the mastery degree of the user on the knowledge point is analyzed again, a target system is generated based on the mastery degree, a target operation file is generated, a closed loop process of targeted learning is formed in the whole learning process, and the improvement of the learning efficiency of the user is facilitated.

In summary, the paper job processing method provided by the embodiment of the present application determines writing handwriting in a paper job according to dot matrix units in a plurality of first images, and generates a second image of the paper job according to the writing handwriting, wherein the first image is obtained by shooting with a dot matrix pen when the dot matrix pen writes in the paper job printed with the dot matrix units; extracting the operation content of the paper operation from the second image through a character recognition algorithm, analyzing the operation content and determining a target knowledge point to be learned; and acquiring a target exercise from a preset exercise library according to the target knowledge point, and generating a target operation file according to the target exercise. By the technical means, when a user writes on the paper operation printed with the dot matrix unit by using the dot matrix pen, the image containing the dot matrix unit and the writing handwriting is obtained, and the highly restored paper operation image is generated according to the dot matrix unit and the writing handwriting in the image, so that the accuracy of the paper operation image and the identification accuracy of operation contents are improved, and the reliability of an analysis result is ensured. Analyzing the mastery degree of the knowledge points corresponding to the test question contents by the user according to the answer duration and the correction result of each test question content in the operation contents, thereby determining the target knowledge points which the user needs to strengthen learning. And summarizing the target exercises corresponding to the target knowledge points in the preset exercise library into a target operation file, so that the user can strengthen the learning of the target knowledge points by finishing the target operation file, and the learning efficiency of the user is improved.

On the basis of the foregoing embodiment, fig. 11 is a schematic structural diagram of a paper job processing apparatus according to an embodiment of the present application. Referring to fig. 11, the paper job processing apparatus provided in this embodiment specifically includes: a job acquisition module 21, a job analysis module 22, and a job customization module 23.

The operation acquisition module is configured to determine writing handwriting in paper operation according to dot matrix units in a plurality of first images, and generate a second image of the paper operation according to the writing handwriting, wherein the first image is obtained by shooting with a dot matrix pen when the dot matrix pen writes in the paper operation printed with the dot matrix units;

the job analysis module is configured to extract job contents of paper jobs from the second image through a character recognition algorithm, analyze the job contents and determine a target knowledge point to be learned;

On the basis of the above-described embodiment, the paper job processing apparatus includes a printing module including: the dot matrix image acquisition unit is configured to acquire a preset dot matrix image before determining writing in the paper operation according to dot matrix units in the first images, wherein the dot matrix image comprises a plurality of different dot matrix units, each dot matrix unit comprises a preset number of code points, and each code point is a pixel point in a preset pixel matrix; the image overlapping unit is configured to overlap the test question image and the dot matrix image to obtain a test question file to be printed; and the printing unit is configured to send the test question file to be printed to a printing device connected in advance so as to enable the printing device to print the paper job printed with the dot matrix unit.

On the basis of the above embodiment, the image superimposing unit includes: the position recording subunit is configured to determine the position information of the test question content in the dot matrix image according to the dot matrix unit covered by each test question content in the test question image after the test question image and the dot matrix image are subjected to overlapping processing, and store the test question content and the corresponding position information in an associated manner; and the retention subunit is configured to delete the dot matrix unit covered by the test question content in the test question image and retain the dot matrix unit of the answer area in the test question image.

On the basis of the above embodiment, the job acquisition module includes: a position determination unit configured to identify a dot matrix unit in the first image and determine position information of the dot matrix unit in the dot matrix image; the handwriting determining unit is configured to generate corresponding writing handwriting according to the pixel points in the dot matrix unit and determine the position information of the corresponding writing handwriting according to the position information of the dot matrix unit; the test question acquisition unit is configured to acquire test question contents corresponding to the paper operation according to the position information of the dot matrix unit; and the handwriting and test question drawing unit is configured to draw the handwriting and the test question content respectively according to the position information of the handwriting and the position information of the test question content to obtain a second image.

On the basis of the above embodiment, the handwriting and test question drawing unit includes: the first writing time determining subunit is configured to determine writing time of writing handwriting corresponding to the dot matrix unit according to the acquisition time of the first image; and the handwriting drawing subunit is configured to draw the handwriting at the corresponding position information in sequence according to the writing time sequence of the handwriting.

On the basis of the above embodiment, the job analysis module includes: a stroke writing order determining unit configured to determine a stroke writing order of each character in the second image according to the drawing order of each writing trace in the second image; and the answer content identification unit is configured to identify the answer content in the second image according to the stroke writing sequence of each character.

On the basis of the above embodiment, the answer content identification unit includes: the character matching subunit is configured to screen out matched target characters from a preset character database according to the stroke writing sequence of each character; and the character marking subunit is configured to identify the target characters corresponding to the stroke writing sequence through an image character recognition algorithm under the condition that the target characters do not exist in the preset character database, and mark the target characters as stroke writing sequence errors.

On the basis of the above embodiment, the paper job processing apparatus includes a question answering duration determining module, and the question answering duration determining module includes: the writing time determining unit is configured to determine the writing time of the handwriting corresponding to the dot matrix unit according to the acquisition time of the first image after the test question content corresponding to the paper operation is acquired; an answer handwriting determining unit configured to determine answer handwriting of the test content according to the position information of the writing handwriting and the position information of the test content; and the answer duration determining unit is configured to determine the answer duration of the test question content according to the writing time of the answer writing.

On the basis of the above embodiment, the job analysis module includes: the correcting unit is configured to acquire the answer content corresponding to each test question content from the job content, correct the answer content according to the answer content and the standard answers of the test question content, and obtain a correcting result; the analysis unit is configured to analyze the correction result and the answer duration through a pre-trained answer analysis model to obtain a learning score output by the answer analysis model; and the knowledge point determining unit is configured to take the knowledge points corresponding to the test question content as target knowledge points when the learning score is smaller than a preset score threshold value.

On the basis of the embodiment, the printing device is a thermal sensitive printing device, and the dot matrix pen is provided with an infrared camera and a light supplementing light source; or the printing device is a thermal-sensitive carbon ribbon printing device, and the dot matrix pen is provided with an infrared camera.

In the above, the paper job processing apparatus provided in this embodiment of the present application determines, according to the dot matrix units in the multiple first images, the writing handwriting in the paper job, and generates, according to the writing handwriting, the second image of the paper job, where the first image is obtained by shooting with a dot matrix pen when the dot matrix pen writes in the paper job printed with the dot matrix units; extracting the operation content of the paper operation from the second image through a character recognition algorithm, analyzing the operation content and determining a target knowledge point to be learned; and acquiring a target exercise from a preset exercise library according to the target knowledge point, and generating a target operation file according to the target exercise. Through the technical means, when a user writes on the paper operation printed with the dot matrix unit by using the dot matrix pen, the image containing the dot matrix unit and the writing handwriting is obtained, and the highly restored paper operation image is generated according to the dot matrix unit and the writing handwriting in the image, so that the precision of the paper operation image and the identification accuracy of operation contents are improved, and the reliability of an analysis result is ensured. Analyzing the mastery degree of the knowledge points corresponding to the test question contents by the user according to the answer duration and the correction result of each test question content in the operation contents, thereby determining the target knowledge points which the user needs to strengthen learning. And summarizing the target exercises corresponding to the target knowledge points in the preset exercise library into a target operation file, so that the user can strengthen the learning of the target knowledge points by finishing the target operation file, and the learning efficiency of the user is improved.

The paper job processing device provided by the embodiment of the application can be used for executing the paper job processing method provided by the embodiment, and has corresponding functions and beneficial effects.

Fig. 12 is a schematic structural diagram of a paper job processing apparatus provided in an embodiment of the present application, and referring to fig. 12, the paper job processing apparatus includes: a processor 31, a memory 32, a communication device 33, an input device 34, and an output device 35. The number of processors 31 in the paper job processing apparatus may be one or more, and the number of memories 32 in the paper job processing apparatus may be one or more. The processor 31, the memory 32, the communication device 33, the input device 34, and the output device 35 of the paper work processing apparatus may be connected by a bus or other means.

The memory 32 serves as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the paper job processing method of any embodiment of the present application (e.g., the job acquisition module 21, the job analysis module 22, and the job customization module 23 in the paper job processing apparatus). The memory 32 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the device, and the like. Further, the memory 32 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The communication device 33 is used for data transmission.

The processor 31 executes various functional applications of the device and data processing by executing software programs, instructions, and modules stored in the memory 32, that is, implements the above-described paper job processing method.

The input device 33 may be used to receive input numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 35 may include a display device such as a display screen.

The paper job processing equipment provided by the embodiment can be used for executing the paper job processing method provided by the embodiment, and has corresponding functions and beneficial effects.

Embodiments of the present application also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a paper job processing method, including: determining writing handwriting in paper operation according to dot matrix units in the plurality of first images, and generating a second image of the paper operation according to the writing handwriting, wherein the first image is obtained by shooting by a dot matrix pen when the dot matrix pen writes in the paper operation printed with the dot matrix units; extracting the operation content of the paper operation from the second image through a character recognition algorithm, analyzing the operation content and determining a target knowledge point to be learned; and acquiring a target exercise from a preset exercise library according to the target knowledge point, and generating a target operation file according to the target exercise.

Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system connected to the first computer system through a network (such as the internet). The second computer system may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations, e.g., in different computer systems connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.

Of course, the storage medium provided in the embodiments of the present application and containing computer-executable instructions is not limited to the above paper job processing method, and may also perform related operations in the paper job processing method provided in any embodiment of the present application.

The paper job processing apparatus, the storage medium, and the paper job processing device provided in the above embodiments may execute the paper job processing method provided in any embodiment of the present application, and reference may be made to the paper job processing method provided in any embodiment of the present application without detailed technical details described in the above embodiments.

The foregoing is considered as illustrative of the preferred embodiments of the invention and the technical principles employed. The present application is not limited to the particular embodiments described herein, and various obvious changes, adaptations and substitutions may be made by those skilled in the art without departing from the scope of the present application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A paper job processing method, comprising:

extracting the operation content of the paper operation from the second image through a character recognition algorithm, analyzing the operation content, and determining a target knowledge point to be learned;

2. The paper job processing method of claim 1, further comprising, prior to said determining the writing in the paper job from the lattice elements in the plurality of first images:

acquiring a preset dot matrix image, wherein the dot matrix image comprises a plurality of different dot matrix units, each dot matrix unit comprises a preset number of code points, and each code point is a pixel point in a preset pixel matrix;

3. The paper job processing method according to claim 2, further comprising, after the superimposing process of the test question image and the dot matrix image, the step of:

4. The paper job processing method of claim 3, wherein determining handwriting in the paper job from dot matrix units in the plurality of first images, and generating a second image of the paper job from the handwriting, comprises:

5. The paper job processing method according to claim 4, wherein the drawing the writing script and the test question content respectively according to the position information of the writing script and the position information of the test question content comprises:

6. The paper job processing method of claim 5, wherein extracting job content of the paper job from the second image via a text recognition algorithm comprises:

7. The paper job processing method according to claim 6, wherein said recognizing the answer content in the second image according to the stroke writing order of each character comprises:

8. The paper job processing method according to claim 4, further comprising, after said obtaining the test question content corresponding to the paper job:

9. The paper job processing method of claim 8, wherein the analyzing the job content to determine the target knowledge point to be learned comprises:

analyzing the correcting result and the answering duration through a pre-trained answering analysis model to obtain a learning score output by the answering analysis model;

10. The paper job processing method according to claim 2, wherein the printing device is a thermal printing device, and the dot matrix pen is provided with an infrared camera and a supplementary light source; or the printing device is a thermal-sensitive carbon ribbon printing device, and the dot matrix pen is provided with an infrared camera.

11. A paper job processing apparatus comprising:

12. A paper job processing apparatus, comprising: one or more processors; a storage device storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the paper job processing method of any one of claims 1-10.

13. A storage medium containing computer-executable instructions for performing the paper job processing method of any of claims 1-10 when executed by a computer processor.