CN116152828B - Job correcting method, system, terminal and storage medium - Google Patents
Job correcting method, system, terminal and storage medium Download PDFInfo
- Publication number
- CN116152828B CN116152828B CN202310430554.4A CN202310430554A CN116152828B CN 116152828 B CN116152828 B CN 116152828B CN 202310430554 A CN202310430554 A CN 202310430554A CN 116152828 B CN116152828 B CN 116152828B
- Authority
- CN
- China
- Prior art keywords
- error
- prone
- homework
- determining
- student
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/22—Character recognition characterised by the type of writing
- G06V30/226—Character recognition characterised by the type of writing of cursive writing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/19007—Matching; Proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19107—Clustering techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a job correcting method, a system, a terminal and a storage medium, wherein the method comprises the following steps: obtaining answer images of student homework, and comparing answer scripts in the answer images with standard answers to obtain homework scores; performing handwriting style recognition on the answer handwriting, and generating an operation writing suggestion according to the handwriting style recognition result; acquiring homework writing videos corresponding to homework of students, and carrying out eye movement identification on the students according to the homework writing videos to obtain eye movement data; determining error-prone knowledge points in student work according to the eye movement data, and generating error-prone exercise suggestions according to the error-prone knowledge points; and generating homework correcting results of the student homework according to the homework score, the homework writing advice and the error-prone exercise advice. According to the embodiment of the invention, the error-prone exercise advice of the student homework can be effectively generated based on the error-prone knowledge points, the error-prone exercise effect can be effectively achieved on the students based on the error-prone exercise advice, the consolidation of the error-prone knowledge points by the students is ensured, and the teaching quality is improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a job modifying method, a job modifying system, a job modifying terminal, and a job modifying storage medium.
Background
During teaching, it is often necessary to consolidate the learned knowledge by students completing the work. However, the correction of the homework brings much extra burden to the teacher, and especially when the number of students carried by the teacher is large, the pressure of the homework correction by the teacher is more obvious.
With the development of computer technology, intelligent correction technology for student homework is presented. The intelligent correcting technology aiming at the student homework can automatically correct the homework submitted by the student, and greatly reduces the pressure of correcting the homework off line by a teacher.
In the existing homework correction process, only the homework questions in the homework of students are corrected in a correct way, effective exercise suggestions cannot be given according to the homework conditions of the students, and the teaching quality is reduced.
Disclosure of Invention
The embodiment of the invention aims to provide a job correcting method, a system, a terminal and a storage medium, which aim to solve the problem that effective exercise suggestions cannot be given in the existing job correcting process.
The embodiment of the invention is realized in such a way that a job modifying method comprises the following steps:
obtaining answer images of student homework, and comparing answer handwriting in the answer images with standard answers to obtain homework scores;
Performing handwriting style recognition on the answer handwriting, and generating an operation writing suggestion according to the handwriting style recognition result;
acquiring homework writing videos corresponding to homework of students, and carrying out eye movement identification on the students according to the homework writing videos to obtain eye movement data;
determining error-prone knowledge points in the student work according to the eye movement data, and generating error-prone exercise suggestions according to the error-prone knowledge points;
and generating an homework modifying result of the student homework according to the homework score, the homework writing advice and the error-prone exercise advice.
Preferably, the eye movement recognition for the students according to the homework writing video comprises:
acquiring student images in the homework writing video, and performing gaze point identification and eye jump identification on the student images to obtain gaze point coordinates and eye jump information;
generating a gaze point track of the student according to each gaze point coordinate;
wherein the eye movement data includes the gaze point coordinates, the gaze point trajectory, and the eye jump information.
Preferably, the determining the error-prone knowledge points in the student homework according to the eye movement data and generating error-prone exercise advice according to the error-prone knowledge points includes:
Respectively carrying out coordinate matching on the coordinates of each fixation point and the answer areas of each homework title in the homework of the students, and determining a fixation point set of each homework title according to the coordinate matching result;
performing stem fixation analysis on the corresponding operation questions according to each fixation point set, and determining a first error-prone question in each operation question according to the stem fixation analysis result;
determining a distraction time point of the student according to the gaze point coordinates, and determining a second error-prone problem in each homework problem according to the distraction time point;
determining a third error-prone problem in each operation problem according to the gaze point track, and determining a fourth error-prone problem in each operation problem according to the eye jump information;
and respectively acquiring knowledge points of the first error-prone problem, the second error-prone problem, the third error-prone problem and the fourth error-prone problem to obtain error-prone knowledge points, and carrying out error-prone problem practice problem query according to the error-prone knowledge points to obtain error-prone practice suggestions.
Preferably, the performing a stem gazing analysis on the corresponding task questions according to each gaze point set, and determining a first error-prone question in each task question according to the stem gazing analysis result, includes:
Respectively obtaining the coordinate distance of the gaze point coordinates between adjacent time points in each gaze point set;
if the coordinate distance is greater than a first distance threshold, deleting the gaze point coordinate corresponding to the coordinate distance;
respectively acquiring a stem region in each operation question, and carrying out coordinate matching on the gazing point set and the stem region to obtain stem gazing times;
if any of the stem gazing times is smaller than the first time threshold, determining the operation question corresponding to the stem gazing times as a first error-prone question.
Preferably, the determining a distraction time point of the student according to the gaze point coordinates, and determining a second error-prone problem in each homework problem according to the distraction time point includes:
acquiring an homework area of the student homework in the student image, and respectively calculating gaze offset distances between each gaze point coordinate and the homework area in the same frame of the student image;
if any one of the gaze offset distances is greater than a second distance threshold, determining gaze point coordinates corresponding to the gaze offset distance as candidate gaze points;
performing fixation point clustering according to coordinates of candidate fixation points to obtain a candidate point set, wherein the distance between different candidate fixation points in the same candidate point set is smaller than a third distance threshold value, and the time point difference value is smaller than a first time length threshold value;
If the number of the candidate fixation points in any candidate point set is larger than a number threshold, determining a distraction time range according to the time points of each candidate fixation point in the candidate point set;
and determining the homework questions written by the students as the second error-prone questions within the distraction time range.
Preferably, the determining the third error prone problem in each task topic according to the gaze point track, and determining the fourth error prone problem in each task topic according to the eye jump information includes:
respectively acquiring a stem region in each operation question, and matching the gazing point track with each stem region to obtain a stem gazing track of each operation question;
respectively inquiring the track fixation time length of each stem fixation track;
if any one of the track gazing time lengths is smaller than a second time length threshold, determining an operation question corresponding to the track gazing time length as the third error-prone question;
determining the number of times of reading the homework questions by students according to the track direction of the gazing track of each question stem;
if any student reading number is larger than a second number threshold, determining the homework questions corresponding to the student reading number as the third error-prone questions;
Generating answer time ranges according to the gaze point sets of the operation questions, and respectively determining the number of the eye hops in the answer time ranges according to the eye hop information to obtain the answer number of the eye hops of the operation questions;
and if the answering jump number is greater than a third number threshold, determining the operation question corresponding to the answering jump number as the fourth error-prone question.
Preferably, the step of performing handwriting style recognition on the answer handwriting and generating an operation writing suggestion according to the handwriting style recognition result includes:
respectively carrying out character matching on each handwriting character in the answering handwriting and a preset character, and respectively determining the handwriting style of each handwriting character according to a character matching result;
respectively obtaining the writing times of each handwriting style, and determining the handwriting style corresponding to the maximum writing times as the handwriting recommending style;
respectively acquiring the character area of each handwriting character, determining a character standard area according to the character type of each handwriting character, and respectively calculating a first area difference value between the character area of each handwriting character and the corresponding character standard area;
if any one of the first area difference values is larger than a first area threshold value, determining the handwriting character corresponding to the area difference value as an abnormal character, and carrying out stroke splitting on each abnormal character to obtain a stroke set;
Respectively inquiring the stroke standard areas of all character strokes in the stroke set, and calculating a second area difference value between the stroke area of each character stroke and the corresponding stroke standard area;
if any second area difference value is larger than a second area threshold value, carrying out abnormal marking on character strokes corresponding to the second area difference value;
and generating a stroke writing prompt according to the abnormal marking times of the strokes of each character, and generating a job writing suggestion according to the stroke writing prompt and the handwriting recommending style.
It is another object of an embodiment of the present invention to provide a job modifying system, the system including:
the answer comparison module is used for obtaining answer images of student homework and comparing answer scripts in the answer images with standard answers to obtain homework scores;
the writing prompting module is used for carrying out handwriting style recognition on the answer handwriting and generating an operation writing suggestion according to the handwriting style recognition result;
the eye movement identification module is used for acquiring homework writing videos corresponding to the homework of the students, and carrying out eye movement identification on the students according to the homework writing videos to obtain eye movement data;
The error-prone problem determination module is used for determining error-prone knowledge points in the student work according to the eye movement data and generating error-prone exercise suggestions according to the error-prone knowledge points;
and the result output module is used for generating the homework correction result of the student homework according to the homework score, the homework writing advice and the error-prone exercise advice.
It is a further object of an embodiment of the present invention to provide a terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, which processor implements the steps of the method as described above when executing the computer program.
It is a further object of embodiments of the present invention to provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above method.
According to the embodiment of the invention, the answer scripts in the answer images are compared with the standard answers, so that the homework questions in the homework of the students can be effectively corrected, homework scores are obtained, the handwriting style recognition is carried out on the answer scripts, homework writing suggestions can be effectively generated, the handwriting style of the students can be effectively provided with the effect of writing suggestions based on the homework writing suggestions, error-prone knowledge points in the homework writing process of the students can be effectively determined based on the eye movement data of the students, error-prone exercise suggestions of the homework of the students can be effectively generated based on the error-prone knowledge points, the exercise effect of the error-prone questions can be effectively provided for the students based on the error-prone exercise suggestions, the consolidation of the error-prone knowledge points by the students is ensured, and the teaching quality is improved.
Drawings
FIG. 1 is a flow chart of a job modifying method according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a job modifying system according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a terminal device according to a third embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In order to illustrate the technical scheme of the invention, the following description is made by specific examples.
Example 1
Referring to fig. 1, a flowchart of a job modifying method according to a first embodiment of the present invention is provided, and the job modifying method can be applied to any terminal device or system, and the job modifying method includes the steps of:
step S10, obtaining answer images of student homework, and comparing answer scripts in the answer images with standard answers to obtain homework scores;
the method comprises the steps of obtaining answer images by shooting images of questions and answers of students in student homework, obtaining answer scripts by performing character recognition (OCR, optical character recognition) on answer areas of the homework questions in the answer images, obtaining corresponding standard answers based on the question identifications of the homework questions, comparing the answer scripts with the corresponding standard answers to determine whether the homework questions are correct or not, calculating the sum of question scores among the homework questions with correct answer, and obtaining the homework scores.
Step S20, handwriting style recognition is carried out on the answer handwriting, and an operation writing suggestion is generated according to the handwriting style recognition result;
the handwriting style recognition is performed on the answering handwriting so as to determine the writing state of the student corresponding to the homework of the student when the student writes the homework, and the homework writing suggestion can be effectively given based on the handwriting style recognition result.
Optionally, in this step, the step of performing handwriting style recognition on the answer handwriting, and generating an operation writing suggestion according to the handwriting style recognition result includes:
respectively carrying out character matching on each handwriting character in the answering handwriting and a preset character, and respectively determining the handwriting style of each handwriting character according to a character matching result;
the method comprises the steps that preset characters with different fonts are locally preset, the fonts of the preset characters can be set according to requirements, for example, the fonts of the preset characters can be set to be regular script, song Ti, bold, imitation Song, and the like, and the font types corresponding to the handwriting characters can be effectively determined by respectively carrying out character matching on the handwriting characters in the answering handwriting and the preset characters, and the font types are used for representing the handwriting styles of the corresponding handwriting characters;
Respectively obtaining the writing times of each handwriting style, and determining the handwriting style corresponding to the maximum writing times as the handwriting recommending style;
the writing style corresponding to the maximum writing times is determined as the writing recommended style, so that students can know own writing habits effectively, and optionally, in the step, if the writing style corresponding to the maximum writing times is matched with a preset style blacklist, a writing style error prompt is sent to the student homework to prompt students, parents or teachers that the writing style of the current students is wrong in an abnormal state, the writing style corresponding to the maximum writing times is deleted, the step and the subsequent steps for respectively acquiring the writing times of each writing style are carried out are returned until the writing style corresponding to the maximum writing times is not matched with the preset style blacklist, and the preset style blacklist can be set according to requirements, for example, the preset style blacklist comprises the styles such as cursive writing or young circles;
respectively acquiring the character area of each handwriting character, determining a character standard area according to the character type of each handwriting character, and respectively calculating a first area difference value between the character area of each handwriting character and the corresponding character standard area;
Connecting stroke vertexes of each handwriting character to obtain stroke patterns, calculating the area of each handwriting pattern to obtain the character area, wherein the character type is used for standardizing the character number of each handwriting character corresponding to a preset character, matching the character type with a prestored area lookup table to obtain the standard area, and storing corresponding relations between different character types and corresponding standard areas in the area lookup table;
if any one of the first area difference values is larger than a first area threshold value, determining the handwriting character corresponding to the area difference value as an abnormal character, and carrying out stroke splitting on each abnormal character to obtain a stroke set;
the first area threshold value can be set according to requirements, if any first area difference value is larger than the first area threshold value, the situation that writing of handwriting characters corresponding to the first area difference value is larger is judged, and the handwriting characters are determined to be abnormal characters;
optionally, in the step, determining whether the handwriting character corresponding to the first area difference value is an abnormal character by calculating an absolute value of the first area difference value and comparing the absolute value of the first area difference value with a first area threshold value;
Respectively inquiring the stroke standard areas of all character strokes in the stroke set, and calculating a second area difference value between the stroke area of each character stroke and the corresponding stroke standard area;
wherein, each character stroke is matched with the area lookup table to obtain the standard area of the stroke, and the character stroke can be ' one ', ' one or more "
”、“/>
"etc.;
if any second area difference value is larger than a second area threshold value, carrying out abnormal marking on character strokes corresponding to the second area difference value;
the second area threshold value can be set according to requirements, and if any second area difference value is larger than the second area threshold value, the condition that the character strokes corresponding to the second area difference value have abnormality of writing size is judged;
generating a stroke writing prompt according to the abnormal marking times of each character stroke, and generating a job writing suggestion according to the stroke writing prompt and the handwriting recommending style;
the method comprises the steps of sorting according to the number of abnormal marks of each character stroke to obtain a stroke abnormal sorting table, and prompting the first three character strokes in the stroke abnormal sorting table to write strokes of students so as to prompt the students to correct writing of the first three character strokes. In the step, standard stroke images corresponding to the first three character strokes are obtained, and homework writing suggestions are generated according to the standard stroke images and handwriting recommendation styles, so that the handwriting styles and the strokes during homework writing of students can be effectively provided with the suggestion prompting effect, the homework writing of the students is planned, and the teaching quality is improved.
Step S30, acquiring homework writing videos corresponding to homework of the students, and carrying out eye movement identification on the students according to the homework writing videos to obtain eye movement data;
the homework writing video can be obtained based on any image collecting equipment, and when students write homework, face images of the students are synchronously collected, so that the homework writing video is obtained.
Optionally, in this step, the eye movement recognition is performed on the student according to the homework writing video, including:
the method comprises the steps of obtaining student images in an homework writing video, performing gaze point identification and eye jump identification on the student images to obtain gaze point coordinates and eye jump information, and generating gaze point tracks of students according to the gaze point coordinates; the eye movement data comprises gaze point coordinates, gaze point tracks and eye jump information.
Step S40, determining error-prone knowledge points in the student work according to the eye movement data, and generating error-prone exercise suggestions according to the error-prone knowledge points;
optionally, in this step, the determining an error-prone knowledge point in the student homework according to the eye movement data, and generating an error-prone exercise suggestion according to the error-prone knowledge point includes:
Respectively carrying out coordinate matching on the coordinates of each fixation point and the answer areas of each homework title in the homework of the students, and determining a fixation point set of each homework title according to the coordinate matching result;
judging whether the gaze point coordinates fall in a question answering area of the operation questions or not by judging whether the gaze point coordinates fall in the question answering area of the operation questions or not respectively, judging whether the gaze point coordinates are matched with the operation questions or not, and generating a gaze point set according to the gaze point coordinates matched with the operation questions;
performing stem fixation analysis on the corresponding operation questions according to each fixation point set, and determining a first error-prone question in each operation question according to the stem fixation analysis result;
determining a distraction time point of the student according to the gaze point coordinates, and determining a second error-prone problem in each homework problem according to the distraction time point;
determining a third error-prone problem in each operation problem according to the gaze point track, and determining a fourth error-prone problem in each operation problem according to the eye jump information;
and respectively acquiring knowledge points of the first error-prone problem, the second error-prone problem, the third error-prone problem and the fourth error-prone problem to obtain error-prone knowledge points, and carrying out error-prone problem practice problem query according to the error-prone knowledge points to obtain error-prone practice suggestions.
Further, in this step, the performing a stem gaze analysis on the corresponding task questions according to each gaze point set, and determining a first error prone question in each task question according to the stem gaze analysis result, including:
respectively obtaining the coordinate distance of the gaze point coordinates between adjacent time points in each gaze point set;
if the coordinate distance is greater than a first distance threshold, deleting the gaze point coordinate corresponding to the coordinate distance;
the first distance threshold can be set according to requirements, and for each gaze point coordinate in the gaze point set, the sum of distances between the gaze point coordinates and different gaze point coordinates is obtained in the same gaze point set to obtain the coordinate distance, if the coordinate distance is larger than the first distance threshold, the gaze point coordinate corresponding to the coordinate distance is judged to be far away from the other gaze point coordinates in the same gaze point set, and the concentration of the gaze point coordinate positions in each gaze point set is improved by deleting the gaze point coordinate corresponding to the coordinate distance;
respectively acquiring a stem region in each operation question, and carrying out coordinate matching on the gazing point set and the stem region to obtain stem gazing times;
The method comprises the steps of determining a stem area based on a stem mark of each homework question, wherein the stem area is used for representing the position of a stem word, and obtaining the gazing times of the stem word of each homework question when a student writes the homework by matching a gazing point set with the stem area in coordinates;
if any of the stem gazing times is smaller than a first time number threshold, determining an operation question corresponding to the stem gazing times as a first error-prone question;
the first time number threshold can be set according to requirements, if the number of times of looking at the questions is smaller than the first time number threshold, it is determined that when the students write the current homework questions, the number of times of looking at the questions is smaller, effective information of the questions is obtained less, and therefore the probability of errors is larger when the students write the current homework questions, and therefore the homework questions corresponding to the number of times of looking at the questions are determined to be first error-prone questions.
Further, the determining the distraction time point of the student according to the gaze point coordinates, and determining the second error-prone problem in each homework problem according to the distraction time point includes:
acquiring an homework area of the student homework in the student image, and respectively calculating gaze offset distances between each gaze point coordinate and the homework area in the same frame of the student image;
If any one of the gaze offset distances is greater than a second distance threshold, determining gaze point coordinates corresponding to the gaze offset distance as candidate gaze points;
the homework area comprises a text area and a question answering area of each homework question, the second distance threshold can be set according to requirements, if the gazing deviation distance is larger than the second distance threshold, it is judged that students are not currently looking at the homework of the students, namely, the students are in a distraction state at present, and the gazing point coordinates corresponding to the gazing deviation distance are determined to be candidate gazing points;
clustering the gaze points according to the coordinates of each candidate gaze point to obtain a candidate point set;
the method comprises the steps that through clustering the positions of the gaze points of candidate gaze points, the distances between different candidate gaze points in the same candidate point set can be effectively controlled to be smaller than a third distance threshold, and the time point difference value is smaller than a first time length threshold, so that the accuracy of the candidate point set is improved;
if the number of the candidate fixation points in any candidate point set is larger than a number threshold, determining a distraction time range according to the time points of each candidate fixation point in the candidate point set;
determining the homework questions written by the students as the second error-prone questions within the distraction time range;
The method comprises the steps of obtaining a time point of the earliest candidate fixation point in a candidate point set, obtaining a distraction time starting point, obtaining a time point of the latest candidate fixation point in the candidate point set, obtaining a distraction time end point, and determining a distraction time range according to the distraction time starting point and the distraction time end point.
Preferably, in this step, the determining a third error prone problem in each task topic according to the gaze point track, and determining a fourth error prone problem in each task topic according to the eye jump information includes:
respectively acquiring a stem region in each operation question, and matching the gazing point track with each stem region to obtain a stem gazing track of each operation question; the method comprises the steps of respectively obtaining gaze point tracks falling in each stem area to obtain stem gaze tracks of the task questions;
respectively inquiring the track fixation time length of each stem fixation track;
if any one of the track gazing time lengths is smaller than a second time length threshold, determining an operation question corresponding to the track gazing time length as the third error-prone question;
if the track gazing duration is smaller than the second duration threshold, the situation that the student thinks about the homework questions is relatively long is judged, and the student grasps knowledge points of the homework questions is relatively poor, so that the homework questions corresponding to the track gazing duration are determined to be third error-prone questions;
Determining the number of times of reading the homework questions by students according to the track direction of the gazing track of each question stem;
if any student reading number is larger than a second number threshold, determining the homework questions corresponding to the student reading number as the third error-prone questions;
when the learned eyes read the questions again, the track direction in the stem gazing track returns to the question head from the question tail, so that whether the students read the questions repeatedly or not can be effectively determined according to the track direction in each stem gazing track when the students write the homework questions, and the number of times of reading the questions by the students is obtained;
in the step, the second time threshold can be set according to the requirement, if the number of times of reading the homework questions by the students is larger than the second time threshold, the confidence that the students do not answer the homework questions is judged, namely, the knowledge points of the homework questions by the students are not mastered fully, so that the homework questions corresponding to the number of times of reading the homework questions by the students are determined to be third error-prone questions;
generating answer time ranges according to the gaze point sets of the operation questions, and respectively determining the number of the eye hops in the answer time ranges according to the eye hop information to obtain the answer number of the eye hops of the operation questions;
If the answering jump number is larger than a third number threshold, determining an operation question corresponding to the answering jump number as the fourth error-prone question;
the third time threshold can be set according to requirements, when the number of answering hops is larger, the longer the information searching process of the students on the homework questions is judged, namely, the students grasp knowledge points of the homework questions, so that if the number of answering hops is larger than the third time threshold, the homework questions corresponding to the number of answering hops are determined to be fourth error-prone questions.
Step S50, generating an homework correction result of the student homework according to the homework score, the homework writing advice and the error-prone exercise advice;
the handwriting style of the students can be effectively provided with the effect of the writing advice based on the homework writing advice, the students can be effectively provided with the effect of the exercise of error-prone questions based on the error-prone exercise advice, the consolidation of the error-prone knowledge points by the students is ensured, and the teaching quality is improved.
In the embodiment, by comparing answer scripts in the answer images with standard answers, the homework questions in the homework of the students can be effectively modified in error to obtain homework scores, homework writing suggestions can be effectively generated by handwriting style recognition of the answer scripts, the effect of writing suggestions can be effectively achieved on the handwriting style of the students based on the homework writing suggestions, error-prone knowledge points in the homework writing process of the students can be effectively determined based on eye movement data of the students, error-prone exercise suggestions of the homework of the students can be effectively generated based on the error-prone knowledge points, the exercise effect of the error-prone questions can be effectively achieved on the students based on the error-prone exercise suggestions, consolidation of the error-prone knowledge points by the students is guaranteed, and teaching quality is improved.
Example two
Referring to fig. 2, a schematic structure diagram of a job modifying system 100 according to a second embodiment of the present invention includes: answer comparison module 10, writing prompt module 11, eye movement identification module 12, error prone problem determination module 13 and result output module 14, wherein:
the answer comparison module 10 is used for obtaining answer images of students' homework, and comparing answer scripts in the answer images with standard answers to obtain homework scores.
The writing prompting module 11 is used for carrying out handwriting style recognition on the answer handwriting and generating an operation writing suggestion according to the handwriting style recognition result.
Optionally, the writing prompting module 11 is further configured to: respectively carrying out character matching on each handwriting character in the answering handwriting and a preset character, and respectively determining the handwriting style of each handwriting character according to a character matching result;
respectively obtaining the writing times of each handwriting style, and determining the handwriting style corresponding to the maximum writing times as the handwriting recommending style;
respectively acquiring the character area of each handwriting character, determining a character standard area according to the character type of each handwriting character, and respectively calculating a first area difference value between the character area of each handwriting character and the corresponding character standard area;
If any one of the first area difference values is larger than a first area threshold value, determining the handwriting character corresponding to the area difference value as an abnormal character, and carrying out stroke splitting on each abnormal character to obtain a stroke set;
respectively inquiring the stroke standard areas of all character strokes in the stroke set, and calculating a second area difference value between the stroke area of each character stroke and the corresponding stroke standard area;
if any second area difference value is larger than a second area threshold value, carrying out abnormal marking on character strokes corresponding to the second area difference value;
and generating a stroke writing prompt according to the abnormal marking times of the strokes of each character, and generating a job writing suggestion according to the stroke writing prompt and the handwriting recommending style.
The eye movement identification module 12 is configured to obtain homework writing video corresponding to the homework of the student, and perform eye movement identification on the student according to the homework writing video, so as to obtain eye movement data.
Optionally, the eye movement identification module 12 is further configured to: acquiring student images in the homework writing video, and performing gaze point identification and eye jump identification on the student images to obtain gaze point coordinates and eye jump information;
Generating a gaze point track of the student according to each gaze point coordinate;
wherein the eye movement data includes the gaze point coordinates, the gaze point trajectory, and the eye jump information.
And the error-prone problem determination module 13 is used for determining error-prone knowledge points in the student homework according to the eye movement data and generating error-prone exercise suggestions according to the error-prone knowledge points.
Optionally, the error prone problem determination module 13 is further configured to: respectively carrying out coordinate matching on the coordinates of each fixation point and the answer areas of each homework title in the homework of the students, and determining a fixation point set of each homework title according to the coordinate matching result;
performing stem fixation analysis on the corresponding operation questions according to each fixation point set, and determining a first error-prone question in each operation question according to the stem fixation analysis result;
determining a distraction time point of the student according to the gaze point coordinates, and determining a second error-prone problem in each homework problem according to the distraction time point;
determining a third error-prone problem in each operation problem according to the gaze point track, and determining a fourth error-prone problem in each operation problem according to the eye jump information;
and respectively acquiring knowledge points of the first error-prone problem, the second error-prone problem, the third error-prone problem and the fourth error-prone problem to obtain error-prone knowledge points, and carrying out error-prone problem practice problem query according to the error-prone knowledge points to obtain error-prone practice suggestions.
Further, the error prone problem determination module 13 is further configured to: respectively obtaining the coordinate distance of the gaze point coordinates between adjacent time points in each gaze point set;
if the coordinate distance is greater than a first distance threshold, deleting the gaze point coordinate corresponding to the coordinate distance;
respectively acquiring a stem region in each operation question, and carrying out coordinate matching on the gazing point set and the stem region to obtain stem gazing times;
if any of the stem gazing times is smaller than the first time threshold, determining the operation question corresponding to the stem gazing times as a first error-prone question.
Preferably, the error prone problem determination module 13 is further configured to: acquiring an homework area of the student homework in the student image, and respectively calculating gaze offset distances between each gaze point coordinate and the homework area in the same frame of the student image;
if any one of the gaze offset distances is greater than a second distance threshold, determining gaze point coordinates corresponding to the gaze offset distance as candidate gaze points;
performing fixation point clustering according to coordinates of candidate fixation points to obtain a candidate point set, wherein the distance between different candidate fixation points in the same candidate point set is smaller than a third distance threshold value, and the time point difference value is smaller than a first time length threshold value;
If the number of the candidate fixation points in any candidate point set is larger than a number threshold, determining a distraction time range according to the time points of each candidate fixation point in the candidate point set;
and determining the homework questions written by the students as the second error-prone questions within the distraction time range.
Still further, the error prone problem determination module 13 is further configured to: respectively acquiring a stem region in each operation question, and matching the gazing point track with each stem region to obtain a stem gazing track of each operation question;
respectively inquiring the track fixation time length of each stem fixation track;
if any one of the track gazing time lengths is smaller than a second time length threshold, determining an operation question corresponding to the track gazing time length as the third error-prone question;
determining the number of times of reading the homework questions by students according to the track direction of the gazing track of each question stem;
if any student reading number is larger than a second number threshold, determining the homework questions corresponding to the student reading number as the third error-prone questions;
generating answer time ranges according to the gaze point sets of the operation questions, and respectively determining the number of the eye hops in the answer time ranges according to the eye hop information to obtain the answer number of the eye hops of the operation questions;
And if the answering jump number is greater than a third number threshold, determining the operation question corresponding to the answering jump number as the fourth error-prone question.
And a result output module 14, configured to generate a job modification result of the student job according to the job score, the job writing suggestion, and the error-prone exercise suggestion.
According to the embodiment, the answer scripts in the answer images are compared with the standard answers, the homework questions in the homework of the students can be effectively subjected to error correction, homework scores are obtained, handwriting style recognition is carried out on the answer scripts, homework writing suggestions can be effectively generated, the handwriting style of the students can be effectively provided with the effect of writing suggestions based on the homework writing suggestions, error-prone knowledge points in the homework writing process of the students can be effectively determined based on eye movement data of the students, error-prone exercise suggestions of the homework of the students can be effectively generated based on the error-prone knowledge points, the exercise effect of the error-prone questions can be effectively achieved for the students based on the error-prone exercise suggestions, consolidation of the error-prone knowledge points by the students is guaranteed, and teaching quality is improved.
Example III
Fig. 3 is a block diagram of a terminal device 2 according to a third embodiment of the present application. As shown in fig. 3, the terminal device 2 of this embodiment includes: a processor 20, a memory 21 and a computer program 22 stored in said memory 21 and executable on said processor 20, for example a program of a job modifying method. The steps of the various embodiments of the job modifying method described above are implemented by processor 20 when executing the computer program 22.
Illustratively, the computer program 22 may be partitioned into one or more modules that are stored in the memory 21 and executed by the processor 20 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program 22 in the terminal device 2. The terminal device may include, but is not limited to, a processor 20, a memory 21.
The processor 20 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 21 may be an internal storage unit of the terminal device 2, such as a hard disk or a memory of the terminal device 2. The memory 21 may be an external storage device of the terminal device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal device 2. Further, the memory 21 may also include both an internal storage unit and an external storage device of the terminal device 2. The memory 21 is used for storing the computer program as well as other programs and data required by the terminal device. The memory 21 may also be used for temporarily storing data that has been output or is to be output.
In addition, each functional module in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Wherein the computer readable storage medium may be nonvolatile or volatile. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each method embodiment described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable storage medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable storage medium may be appropriately scaled according to the requirements of jurisdictions in which such computer readable storage medium does not include electrical carrier signals and telecommunication signals, for example, according to jurisdictions and patent practices.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (8)
1. A method of job modification, the method comprising:
obtaining answer images of student homework, and comparing answer handwriting in the answer images with standard answers to obtain homework scores;
performing handwriting style recognition on the answer handwriting, and generating an operation writing suggestion according to the handwriting style recognition result;
acquiring homework writing videos corresponding to homework of students, and carrying out eye movement identification on the students according to the homework writing videos to obtain eye movement data;
determining error-prone knowledge points in the student work according to the eye movement data, and generating error-prone exercise suggestions according to the error-prone knowledge points;
Generating an homework modifying result of the student homework according to the homework score, the homework writing advice and the error-prone exercise advice;
the eye movement recognition is carried out on students according to the homework writing video, and the eye movement recognition method comprises the following steps:
acquiring student images in the homework writing video, and performing gaze point identification and eye jump identification on the student images to obtain gaze point coordinates and eye jump information;
generating a gaze point track of the student according to each gaze point coordinate;
wherein the eye movement data includes the gaze point coordinates, the gaze point trajectories, and the eye jump information;
the step of determining error-prone knowledge points in the student work according to the eye movement data and generating error-prone exercise suggestions according to the error-prone knowledge points comprises the following steps:
respectively carrying out coordinate matching on the coordinates of each fixation point and the answer areas of each homework title in the homework of the students, and determining a fixation point set of each homework title according to the coordinate matching result;
performing stem fixation analysis on the corresponding operation questions according to each fixation point set, and determining a first error-prone question in each operation question according to the stem fixation analysis result;
determining a distraction time point of the student according to the gaze point coordinates, and determining a second error-prone problem in each homework problem according to the distraction time point;
Determining a third error-prone problem in each operation problem according to the gaze point track, and determining a fourth error-prone problem in each operation problem according to the eye jump information;
and respectively acquiring knowledge points of the first error-prone problem, the second error-prone problem, the third error-prone problem and the fourth error-prone problem to obtain error-prone knowledge points, and carrying out error-prone problem practice problem query according to the error-prone knowledge points to obtain error-prone practice suggestions.
2. The job modifying method according to claim 1, wherein the performing a stem gaze analysis on the corresponding job title according to each gaze point set, and determining a first error prone problem in each job title according to the stem gaze analysis result, comprises:
respectively obtaining the coordinate distance of the gaze point coordinates between adjacent time points in each gaze point set;
if the coordinate distance is greater than a first distance threshold, deleting the gaze point coordinate corresponding to the coordinate distance;
respectively acquiring a stem region in each operation question, and carrying out coordinate matching on the gazing point set and the stem region to obtain stem gazing times;
if any of the stem gazing times is smaller than the first time threshold, determining the operation question corresponding to the stem gazing times as a first error-prone question.
3. The job modifying method of claim 1, wherein the determining the distraction time point of the student according to the gaze point coordinates and determining the second error prone problem in each job title according to the distraction time point comprises:
acquiring an homework area of the student homework in the student image, and respectively calculating gaze offset distances between each gaze point coordinate and the homework area in the same frame of the student image;
if any one of the gaze offset distances is greater than a second distance threshold, determining gaze point coordinates corresponding to the gaze offset distance as candidate gaze points;
performing fixation point clustering according to coordinates of candidate fixation points to obtain a candidate point set, wherein the distance between different candidate fixation points in the same candidate point set is smaller than a third distance threshold value, and the time point difference value is smaller than a first time length threshold value;
if the number of the candidate fixation points in any candidate point set is larger than a number threshold, determining a distraction time range according to the time points of each candidate fixation point in the candidate point set;
and determining the homework questions written by the students as the second error-prone questions within the distraction time range.
4. The job modifying method of claim 1, wherein the determining a third error prone problem in each job title according to the gaze point locus and determining a fourth error prone problem in each job title according to the eye jump information comprises:
respectively acquiring a stem region in each operation question, and matching the gazing point track with each stem region to obtain a stem gazing track of each operation question;
respectively inquiring the track fixation time length of each stem fixation track;
if any one of the track gazing time lengths is smaller than a second time length threshold, determining an operation question corresponding to the track gazing time length as the third error-prone question;
determining the number of times of reading the homework questions by students according to the track direction of the gazing track of each question stem;
if any student reading number is larger than a second number threshold, determining the homework questions corresponding to the student reading number as the third error-prone questions;
generating answer time ranges according to the gaze point sets of the operation questions, and respectively determining the number of the eye hops in the answer time ranges according to the eye hop information to obtain the answer number of the eye hops of the operation questions;
and if the answering jump number is greater than a third number threshold, determining the operation question corresponding to the answering jump number as the fourth error-prone question.
5. A method of adapting a job as claimed in any one of claims 1 to 4, wherein said performing handwriting style recognition on said answering handwriting and generating a job writing suggestion based on said handwriting style recognition result comprises:
respectively carrying out character matching on each handwriting character in the answering handwriting and a preset character, and respectively determining the handwriting style of each handwriting character according to a character matching result;
respectively obtaining the writing times of each handwriting style, and determining the handwriting style corresponding to the maximum writing times as the handwriting recommending style;
respectively acquiring the character area of each handwriting character, determining a character standard area according to the character type of each handwriting character, and respectively calculating a first area difference value between the character area of each handwriting character and the corresponding character standard area;
if any one of the first area difference values is larger than a first area threshold value, determining the handwriting character corresponding to the area difference value as an abnormal character, and carrying out stroke splitting on each abnormal character to obtain a stroke set;
respectively inquiring the stroke standard areas of all character strokes in the stroke set, and calculating a second area difference value between the stroke area of each character stroke and the corresponding stroke standard area;
If any second area difference value is larger than a second area threshold value, carrying out abnormal marking on character strokes corresponding to the second area difference value;
and generating a stroke writing prompt according to the abnormal marking times of the strokes of each character, and generating a job writing suggestion according to the stroke writing prompt and the handwriting recommending style.
6. A job modifying system, the system comprising:
the answer comparison module is used for obtaining answer images of student homework and comparing answer scripts in the answer images with standard answers to obtain homework scores;
the writing prompting module is used for carrying out handwriting style recognition on the answer handwriting and generating an operation writing suggestion according to the handwriting style recognition result;
the eye movement identification module is used for acquiring homework writing videos corresponding to the homework of the students, and carrying out eye movement identification on the students according to the homework writing videos to obtain eye movement data;
the error-prone problem determination module is used for determining error-prone knowledge points in the student work according to the eye movement data and generating error-prone exercise suggestions according to the error-prone knowledge points;
the result output module is used for generating an operation correction result of the student operation according to the operation score, the operation writing proposal and the error-prone exercise proposal;
The eye movement identification module is further configured to: acquiring student images in the homework writing video, and performing gaze point identification and eye jump identification on the student images to obtain gaze point coordinates and eye jump information;
generating a gaze point track of the student according to each gaze point coordinate;
wherein the eye movement data includes the gaze point coordinates, the gaze point trajectories, and the eye jump information;
the error prone problem determination module is further configured to: respectively carrying out coordinate matching on the coordinates of each fixation point and the answer areas of each homework title in the homework of the students, and determining a fixation point set of each homework title according to the coordinate matching result;
performing stem fixation analysis on the corresponding operation questions according to each fixation point set, and determining a first error-prone question in each operation question according to the stem fixation analysis result;
determining a distraction time point of the student according to the gaze point coordinates, and determining a second error-prone problem in each homework problem according to the distraction time point;
determining a third error-prone problem in each operation problem according to the gaze point track, and determining a fourth error-prone problem in each operation problem according to the eye jump information;
and respectively acquiring knowledge points of the first error-prone problem, the second error-prone problem, the third error-prone problem and the fourth error-prone problem to obtain error-prone knowledge points, and carrying out error-prone problem practice problem query according to the error-prone knowledge points to obtain error-prone practice suggestions.
7. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 5 when the computer program is executed.
8. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310430554.4A CN116152828B (en) | 2023-04-21 | 2023-04-21 | Job correcting method, system, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310430554.4A CN116152828B (en) | 2023-04-21 | 2023-04-21 | Job correcting method, system, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116152828A CN116152828A (en) | 2023-05-23 |
| CN116152828B true CN116152828B (en) | 2023-06-27 |
Family
ID=86354650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310430554.4A Active CN116152828B (en) | 2023-04-21 | 2023-04-21 | Job correcting method, system, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116152828B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118629055B (en) * | 2024-08-14 | 2024-10-11 | 深圳懂你教育科技有限公司 | Teaching data rapid input method for teaching system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010055540A (en) * | 2008-08-29 | 2010-03-11 | Cosmotopia Japan Inc | Rating support program |
| CN101819723B (en) * | 2010-04-16 | 2011-11-16 | 湘潭大学 | Networked interactive multifunctional prescribed form penmanship practice system and method |
| CN101853579A (en) * | 2010-06-11 | 2010-10-06 | 吕军 | Multifunctional writing device and system for electrification instruction |
| JP2012068782A (en) * | 2010-09-22 | 2012-04-05 | Rubic Jp:Kk | Score counting system |
| CN104765280B (en) * | 2015-03-13 | 2018-05-01 | 吉林医药学院 | The three-dimensional aobvious control comprehensive training system of no-manned plane three-dimensional |
| JP6856583B2 (en) * | 2018-07-25 | 2021-04-07 | ファナック株式会社 | Sensing system, work system, augmented reality image display method, augmented reality image storage method, and program |
| CN112382151B (en) * | 2020-11-16 | 2022-11-18 | 深圳市商汤科技有限公司 | Online learning method and device, electronic equipment and storage medium |
-
2023
- 2023-04-21 CN CN202310430554.4A patent/CN116152828B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN116152828A (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109815932B (en) | Test paper correcting method and device, electronic equipment and storage medium | |
| CN108932508B (en) | Method and system for intelligently identifying and correcting subjects | |
| CN109670504B (en) | Handwritten answer recognition and correction method and device | |
| US10395656B2 (en) | Method and device for processing speech instruction | |
| CN110363194B (en) | NLP-based intelligent examination paper reading method, device, equipment and storage medium | |
| CN110008933B (en) | Universal intelligent marking system and method | |
| US11790641B2 (en) | Answer evaluation method, answer evaluation system, electronic device, and medium | |
| CN109271401B (en) | Topic searching and correcting method and device, electronic equipment and storage medium | |
| CN109583429B (en) | Method and device for correcting application questions in test paper in batches | |
| CN111597908A (en) | Test paper correcting method and test paper correcting device | |
| CN116152828B (en) | Job correcting method, system, terminal and storage medium | |
| CN109712043B (en) | Answer correcting method and device | |
| CN112990180B (en) | Question judging method, device, equipment and storage medium | |
| CN113641876A (en) | Method and system for practicing calligraphy based on dot matrix code and computer readable storage medium | |
| US20020067852A1 (en) | Handwriting recognition system and method using compound characters for improved recognition accuracy | |
| CN113205084B (en) | English dictation correction method and device and electronic equipment | |
| CN110569401A (en) | paper marking method and device, computer equipment and storage medium | |
| CN115272018A (en) | Job processing method, job processing apparatus, electronic apparatus, and storage medium | |
| CN115757702A (en) | Choice correcting method, storage medium and equipment | |
| CN115359496A (en) | Handwritten Chinese character recognition method and device, computing equipment and storage medium | |
| CN114663891A (en) | Daily work wrong question book generation method and system based on configured answer sheet | |
| CN113033480B (en) | Objective question reading method, device, equipment and storage medium based on answer sheet | |
| CN111046802A (en) | Evaluation method, device and equipment based on vector character and storage medium | |
| CN118629055B (en) | Teaching data rapid input method for teaching system | |
| CN110555396A (en) | Examination paper reading method of intelligent exercise book, computer readable storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |