CN110795997A - Teaching method and device based on long-term and short-term memory and computer equipment - Google Patents

Teaching method and device based on long-term and short-term memory and computer equipment Download PDF

Info

Publication number
CN110795997A
CN110795997A CN201910886610.9A CN201910886610A CN110795997A CN 110795997 A CN110795997 A CN 110795997A CN 201910886610 A CN201910886610 A CN 201910886610A CN 110795997 A CN110795997 A CN 110795997A
Authority
CN
China
Prior art keywords
preset
answer sheet
teaching
value
long
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.)
Granted
Application number
CN201910886610.9A
Other languages
Chinese (zh)
Other versions
CN110795997B (en
Inventor
张奇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN201910886610.9A priority Critical patent/CN110795997B/en
Priority to PCT/CN2019/116338 priority patent/WO2021051502A1/en
Publication of CN110795997A publication Critical patent/CN110795997A/en
Application granted granted Critical
Publication of CN110795997B publication Critical patent/CN110795997B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06V30/40—Document-oriented image-based pattern recognition
    • G06V30/41—Analysis of document content
    • G06V30/413—Classification of content, e.g. text, photographs or tables
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • 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
    • G06V30/14—Image acquisition
    • G06V30/148—Segmentation of character regions
    • G06V30/153—Segmentation of character regions using recognition of characters or words
    • 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
    • G06V30/32—Digital ink
    • G06V30/36—Matching; Classification
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • 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
    • 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

Abstract

The application discloses a teaching method, a teaching device, computer equipment and a storage medium based on long-term and short-term memory, wherein the method comprises the following steps: acquiring a specified answer sheet picture, and performing character recognition processing on the specified answer sheet picture to obtain an answer sheet text; receiving a grading result of the teacher end on the answer sheet text; acquiring learning characteristic data of students corresponding to the answer sheet text to obtain an estimation result output by a grading estimation model; calculating the difference degree value between the estimated result and the scoring result; if the difference degree value is larger than a preset error threshold value, generating a deduction knowledge point; acquiring a teaching time period corresponding to each deduction knowledge point; calculating an association index between the teaching time periods; and acquiring a designated association index and a designated time period of which the ranking is greater than a preset ranking threshold, and sending reminding information for improving the teaching quality to the teacher end, wherein the reminding information is accompanied with the designated time period. Thereby effectively improving the teaching quality.

Description

Teaching method and device based on long-term and short-term memory and computer equipment
Technical Field
The present application relates to the field of computers, and in particular, to a teaching method, apparatus, computer device and storage medium based on long-term and short-term memory.
Background
The online intelligent examination and approval test paper simplifies a plurality of links such as test paper storage, distribution, transportation, recovery and check in the traditional paper marking mode into only one paper marking process, and the others are completed by a computer in a unified way, so that manpower and material resources are greatly saved, and the whole paper marking time is shortened. However, the intelligent examination and approval test paper is too heavy to result in that only the knowledge of the student is not well mastered, but the reason why the knowledge of the student is not well mastered (i.e. the teaching quality is to be improved) cannot be known. Therefore, the conventional technology cannot know which parts of the teaching quality are to be improved, and therefore a technical scheme for accurately acquiring which parts of the teaching quality need to be improved is urgently needed.
Disclosure of Invention
The application mainly aims to provide a teaching method, a teaching device, computer equipment and a storage medium based on long-term and short-term memory, and aims to improve teaching quality.
In order to achieve the above object, the present application provides a teaching method based on long-term and short-term memory, comprising the following steps:
acquiring a specified answer sheet picture, and performing character recognition processing on the specified answer sheet picture to obtain an answer sheet text, wherein the specified answer sheet picture is a picture obtained by performing image acquisition on a paper test sheet with a finished answer;
sending the answer sheet text to a teacher end, and receiving a grading result of the teacher end on the answer sheet text;
acquiring learning characteristic data of students corresponding to the answer sheet text, and inputting the learning characteristic data into a preset trained score estimation model so as to obtain an estimation result output by the score estimation model, wherein the score estimation model is formed by training based on a long-term and short-term memory model;
calculating a difference degree value between the estimated result and the scoring result according to a preset difference degree value calculation method, and judging whether the difference degree value is greater than a preset error threshold value, wherein the error threshold value is greater than or equal to 0;
if the difference degree value is larger than a preset error threshold value, generating a deduction knowledge point according to the position to be deducted in the answer sheet text;
calling a preset knowledge point teaching time table, and acquiring teaching time periods corresponding to each deduction knowledge point according to the time table;
calculating to obtain the association indexes among the teaching time periods according to a preset time period association index calculation method, and performing descending order on the association indexes according to the numerical value to obtain an association index table;
and acquiring a designated association index with a ranking larger than a preset ranking threshold value in the association index table, acquiring a designated time period corresponding to the designated association index, and sending reminding information for improving the teaching quality to the teacher end, wherein the reminding information is accompanied with the designated time period.
Further, the step of performing character recognition processing on the specified answer sheet picture to obtain an answer sheet text includes:
collecting numerical values of an R color channel, a G color channel and a B color channel in an RGB color model of a pixel point in the specified answer sheet picture, and setting the RGB color of the pixel point in the specified answer sheet picture as (0,0,0), (255 ) or (Q, Q, Q) according to a preset color setting method, wherein Q is a preset numerical value which is more than 0 and less than 255, so as to obtain a temporary picture consisting of three colors;
calculating the areas occupied by the three colors in the temporary picture, and respectively performing character segmentation processing on the areas occupied by the two colors with smaller areas so as to obtain a first type of character and a second type of character which are segmented;
extracting the characteristics of the first font characters and the characteristics of the second font characters, and inputting the characteristics into a preset character classification model based on a support vector machine for classification, so that the first font characters are classified into handwritten characters, or the second font characters are classified into handwritten characters;
and combining all the divided handwritten characters into handwritten character texts, and recording the handwritten character texts as answer sheet texts.
Further, the step of collecting a numerical value of an R color channel, a numerical value of a G color channel, and a numerical value of a B color channel in an RGB color model of a pixel point in the specified answer sheet picture, and setting the RGB color of the pixel point in the specified answer sheet picture to (0,0,0), (255 ) or (Q, Q) according to a preset color setting method, where Q is a preset numerical value that is greater than 0 and less than 255, includes:
collecting the numerical value of an R color channel, the numerical value of a G color channel and the numerical value of a B color channel in an RGB color model of a pixel point in the specified answer sheet picture, and according to a formula: f1 ═ MIN { ROUND [ (a1R + a2G + a3B)/L,0], a }, obtaining a color impact value F1, where MIN is a minimum function, ROUND is a rounding function, a1, a2, a3 are positive numbers greater than 0 and less than L, L is an integer greater than 0, a is a first threshold parameter with a preset value within a range (0,255), and R, G, B are a value of an R color channel, a value of a G color channel, and a value of a B color channel in an RGB color model of a specified pixel point in the specified picture, respectively;
determining whether the value of the color impact value F1 is equal to a;
if the color impact value F1 is equal to A, then according to the formula: obtaining a color influence value F2 by taking F2 ═ MAX { ROUND [ (a1R + a2G + a3B)/L,0], B }, where MAX is a maximum function, B is a second threshold parameter within a preset value range (0,255), and B is greater than a;
determining whether the value of the color impact value F2 is equal to B;
if the value of the color impact value F2 is not equal to B, the RGB color of the designated pixel point is set to (255,255, 255).
Further, the score estimation model includes a coding long-short term memory network and a decoding long-short term memory network which are connected in sequence, the learning characteristic data is input into a preset trained score estimation model, so as to obtain an estimation result output by the score estimation model, wherein the score estimation model is trained on the basis of the long-short term memory model, and the method includes the following steps:
inputting the learning characteristic data into the long-short term memory network for coding for processing to obtain a hidden state vector sequence in the long-short term memory network for coding;
inputting the hidden state vector sequence into the decoding long-short term memory network for processing to obtain a predicted knowledge point and a corresponding mastery degree value output by the decoding long-short term memory network;
and taking the knowledge points with the mastery degree value larger than a preset mastery degree threshold value as an estimation result, and outputting the estimation result.
Further, the step of inputting the learning feature data into the long-short term memory network for coding for processing to obtain a hidden state vector sequence in the long-short term memory network for coding includes:
according to the formula: h ist＝LSTMenc(xt，ht-1) Obtaining the hidden state vector h in the long-short term memory network for encodingtWhere t is the t-th time period, htFor the hidden state vector corresponding to the t-th time segment, ht-1For the hidden state vector corresponding to the t-1 th time segment, XtFor learning feature data of the t-th time period, LSTMencThe encoding operation is performed by using a long-term and short-term memory network for encoding;
according to the formula:
Figure BDA0002207491770000041
eij＝score(si，hj) Obtaining the final hidden state vector c in the long-short term memory network for encodingi，aijIs a weight parameter, wherein there are n time periods,siscore(s) for the ith hidden state vector in the long-short term memory network for encodingi，hj) According to s by using a preset score functioniAnd hjA calculated score;
forming a hidden state vector sequence c by using the final hidden state vectors corresponding to a plurality of preset time periods1、c2...、cn。
Further, each of the teaching time periods has m tags, the tags record tag values, and the step of calculating the association index between the teaching time periods according to a preset time period association index calculation method includes:
mapping the teaching time period into a high-dimensional vector of a high-dimensional virtual space according to the label numerical value, wherein the dimension of the high-dimensional vector is m;
according to the formula:
and calculating to obtain a correlation index DIS between the two teaching time periods, wherein C is a high-dimensional vector corresponding to one teaching time period, Ci is the ith component vector of the high-dimensional vector C, the high-dimensional vector C has m component vectors in total, D is a high-dimensional vector corresponding to the other teaching time period, Di is the ith component vector of the high-dimensional vector D, and the high-dimensional vector D has m component vectors in total.
Further, the teacher end is provided with a voice input device, and sends reminding information of teaching quality improvement to the teacher end, wherein after the step of attaching the reminding information to the designated time period, the method comprises the following steps:
acquiring voice data acquired by the teacher end by using the voice input device;
recognizing the voice data into a voice text according to a preset voice recognition technology;
judging whether the voice text has specified keywords or not;
if the specified keywords exist in the voice text, acquiring specified knowledge points corresponding to the specified keywords according to the corresponding relation between preset keywords and knowledge points;
attaching the voice data to a specified position in the scoring result, wherein the specified position is a position corresponding to the specified knowledge point.
The application provides a teaching device based on long-term and short-term memory, includes:
the answer sheet text acquisition unit is used for acquiring a specified answer sheet picture, and performing character recognition processing on the specified answer sheet picture to obtain an answer sheet text, wherein the specified answer sheet picture is a picture obtained by performing image acquisition on a paper test sheet which has already answered;
the answer sheet text sending unit is used for sending the answer sheet text to a teacher end and receiving a grading result of the teacher end on the answer sheet text;
the estimation result obtaining unit is used for obtaining learning characteristic data of students corresponding to the answer sheet texts and inputting the learning characteristic data into a preset score estimation model after training is completed so as to obtain estimation results output by the score estimation model, wherein the score estimation model is formed by training based on a long-term and short-term memory model;
an error threshold value judging unit, configured to calculate a difference degree value between the estimated result and the scoring result according to a preset difference degree value calculation method, and judge whether the difference degree value is greater than a preset error threshold value, where the error threshold value is greater than or equal to 0;
the deduction knowledge point generating unit is used for generating deduction knowledge points according to the deducted positions in the answer sheet text if the difference degree value is larger than a preset error threshold value;
the teaching time period acquisition unit is used for calling a preset knowledge point teaching time table and acquiring teaching time periods corresponding to each deduction knowledge point according to the time table;
the association index calculation unit is used for calculating association indexes among the teaching time periods according to a preset time period association index calculation method, and performing descending order on the association indexes according to the numerical value to obtain an association index table;
and the reminding information sending unit is used for acquiring the specified association index of which the rank is greater than a preset ranking threshold value in the association index table, acquiring a specified time period corresponding to the specified association index, and sending reminding information for improving the teaching quality to the teacher end, wherein the specified time period is attached to the reminding information.
The present application provides a computer device comprising a memory storing a computer program and a processor implementing the steps of any of the above methods when the processor executes the computer program.
The present application provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any of the above.
The teaching method and device based on long-term and short-term memory, the computer equipment and the storage medium obtain the specified answer sheet picture, and perform character recognition processing on the specified answer sheet picture to obtain an answer sheet text; sending the answer sheet text to a teacher end, and receiving a grading result of the teacher end on the answer sheet text; acquiring learning characteristic data of students corresponding to the answer sheet texts, and acquiring estimation results output by the grading estimation model; calculating the difference degree value between the estimated result and the scoring result; if the difference degree value is larger than a preset error threshold value, generating a deduction knowledge point; acquiring a teaching time period corresponding to each deduction knowledge point; calculating to obtain a correlation index between the teaching time periods; and acquiring a designated association index with a ranking larger than a preset ranking threshold value in the association index table, acquiring a designated time period corresponding to the designated association index, and sending reminding information for improving the teaching quality to the teacher end, wherein the reminding information is accompanied with the designated time period. Thereby effectively improving the teaching quality.
Drawings
FIG. 1 is a flow chart of a teaching method based on long-term and short-term memory according to an embodiment of the present application;
FIG. 2 is a block diagram schematically illustrating the structure of a teaching device based on long-term and short-term memory according to an embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, an embodiment of the present application provides a teaching method based on long-term and short-term memory, including the following steps:
s1, acquiring a specified answer sheet picture, and performing character recognition processing on the specified answer sheet picture to obtain an answer sheet text, wherein the specified answer sheet picture is a picture obtained by performing image acquisition on a paper test sheet with a finished answer;
s2, sending the answer sheet text to a teacher end, and receiving a grading result of the teacher end on the answer sheet text;
s3, acquiring learning characteristic data of a student corresponding to the answer sheet text, and inputting the learning characteristic data into a preset trained score estimation model so as to obtain an estimation result output by the score estimation model, wherein the score estimation model is trained on the basis of a long-term and short-term memory model;
s4, calculating a difference degree value between the estimated result and the scoring result according to a preset difference degree value calculation method, and judging whether the difference degree value is greater than a preset error threshold value, wherein the error threshold value is greater than or equal to 0;
s5, if the difference degree value is larger than a preset error threshold value, generating a deduction knowledge point according to the position of the deducted points in the answer sheet text;
s6, calling a preset knowledge point teaching time table, and acquiring teaching time periods corresponding to each deduction knowledge point according to the time table;
s7, calculating to obtain the correlation indexes among the teaching time periods according to a preset time period correlation index calculation method, and arranging the correlation indexes in a descending order according to the numerical value to obtain a correlation index table;
s8, acquiring the appointed correlation index with the ranking larger than the preset ranking threshold value in the correlation index table, acquiring the appointed time period corresponding to the appointed correlation index, and sending reminding information for improving the teaching quality to the teacher end, wherein the reminding information is attached with the appointed time period.
As described in step S1, the specified answer sheet picture is obtained, and character recognition processing is performed on the specified answer sheet picture to obtain an answer sheet text, where the specified answer sheet picture is a picture obtained by image acquisition of a paper test paper on which a question is answered. The character recognition processing refers to recognizing characters in the picture as character texts. The Character Recognition process may be performed by any method such as OCR (Optical Character Recognition). Further, the character recognition processing of the specified answer sheet picture includes: and recognizing a handwritten character text from the specified answer sheet picture, and taking the handwritten character text as an answer sheet text. Therefore, the network overhead is reduced, and the information sending efficiency is improved.
As described in the above step S2, the answer sheet text is sent to the teacher end, and the scoring result of the teacher end on the answer sheet text is received. The scoring result may be any form of scoring result, such as one or more of a sub-score for each question (or knowledge point), a total score for the entire answer sheet text, a comment corresponding to the sub-score, and a total comment corresponding to the total score.
As described in step S3, learning feature data of the student corresponding to the answer sheet text is obtained, and the learning feature data is input into a preset trained score estimation model, so as to obtain an estimation result output by the score estimation model, where the score estimation model is trained based on a long-term and short-term memory model. The long-short term memory model is a model using a long-short term memory network, wherein the long-short term memory network is a time recurrent neural network and is suitable for processing and predicting important events with relatively long intervals and delays in a time sequence. The estimation result can be any form of estimation result, such as total score, or knowledge point of grasp. Further, the scoring prediction model comprises a coding long-short term memory network and a decoding long-short term memory network which are connected in sequence, and the scoring prediction model is processed by the following processes: inputting the learning characteristic data into the long-short term memory network for coding for processing to obtain a hidden state vector sequence in the long-short term memory network for coding; inputting the hidden state vector sequence into the decoding long-short term memory network for processing to obtain a predicted knowledge point and a corresponding mastery degree value output by the decoding long-short term memory network; and taking the knowledge points with the mastery degree value larger than a preset mastery degree threshold value as an estimation result, and outputting the estimation result.
As described in step S4, according to a predetermined difference value calculation method, a difference value between the estimated result and the scoring result is calculated, and it is determined whether the difference value is greater than a predetermined error threshold, where the error threshold is greater than or equal to 0. The difference degree value calculating method may be any method (related to the estimated result and the scoring result), for example, a difference method is adopted to calculate the difference between the estimated result and the scoring result (at this time, the estimated score of the estimated result is taken, and the corresponding scoring result is the total score); or the number of the same knowledge points (the same knowledge points refer to the knowledge points with the same score and the same estimated mastered knowledge points) is used as the difference degree value. The present application preferably takes the number of identical knowledge points as the degree of difference value.
As described in step S5, if the difference degree value is greater than the preset error threshold, a deduction knowledge point is generated according to the position of the deduction in the answer sheet text. If the difference degree value is larger than the preset error threshold value, the teaching quality is not expected, and therefore, the quality of teaching of which parts needs to be analyzed needs to be improved. Therefore, according to the positions of the marks to be deducted in the answer sheet text, generating mark deduction knowledge points for subsequent analysis.
As described in step S6, a preset knowledge point teaching schedule is retrieved, and a teaching time period corresponding to each deduction knowledge point is obtained according to the schedule. Therefore, the obtained teaching time periods are all suspicious time periods for improving the teaching quality. However, since the missing points of knowledge are difficult to avoid, it is necessary to further analyze which of these time periods is a major problem in teaching quality.
As described in step S7, the correlation indexes between the teaching time periods are calculated according to a preset time period correlation index calculation method, and the correlation indexes are arranged in descending order according to the magnitude of the value, so as to obtain a correlation index table. The preset time period correlation index calculation method includes: mapping the teaching time period into a high-dimensional vector of a high-dimensional virtual space according to the label numerical value, wherein the dimension of the high-dimensional vector is m; according to the formula:
Figure BDA0002207491770000091
and calculating to obtain a correlation index DIS between the two teaching time periods, wherein C is a high-dimensional vector corresponding to one teaching time period, Ci is the ith component vector of the high-dimensional vector C, the high-dimensional vector C has m component vectors, D is a high-dimensional vector corresponding to the other teaching time period, Ci is the ith component vector of the high-dimensional vector D, and the high-dimensional vector D has m component vectors. Wherein, the label refers to factors which have influence on the teaching quality, such as: whether the knowledge point is taught after a physical education course; the association degree of the knowledge point in the whole knowledge point network; the degree of easy learning of the knowledge point; the importance of the knowledge point, etc. Thereby obtaining an index of correlation between the teaching time periods.
As described in step S8, the designated association index with a rank greater than the preset ranking threshold in the association index table is obtained, the designated time period corresponding to the designated association index is obtained, and the reminding information for improving teaching quality is sent to the teacher end, where the reminding information is accompanied by the designated time period. The designated time periods corresponding to the designated association indexes indicate that the designated time periods are time periods having a large influence on the teaching quality, and if the teaching quality is corrected according to the designated time periods, the teaching quality can be more effectively improved.
Further, after the step of sending the reminding information of the improvement of the teaching quality to the teacher end, the method further includes: acquiring voice data acquired by the teacher end by using the voice input device; recognizing the voice data into a voice text according to a preset voice recognition technology; judging whether the voice text has specified keywords or not; if the specified keywords exist in the voice text, acquiring specified knowledge points corresponding to the specified keywords according to the corresponding relation between preset keywords and knowledge points; attaching the voice data to a specified position in the scoring result, wherein the specified position is a position corresponding to the specified knowledge point.
In one embodiment, the step S1 of performing character recognition processing on the specified answer sheet picture to obtain an answer sheet text includes:
s101, collecting numerical values of an R color channel, a G color channel and a B color channel in an RGB color model of a pixel point in the specified answer sheet picture, and setting the RGB color of the pixel point in the specified answer sheet picture as (0,0,0), (255 ) or (Q, Q, Q) according to a preset color setting method, wherein Q is a preset numerical value which is more than 0 and less than 255, so that a temporary picture consisting of three colors is obtained;
s102, calculating the occupied areas of the three colors in the temporary picture, and respectively performing character segmentation processing on the occupied areas of the two colors with smaller areas so as to obtain segmented first font characters and segmented second font characters;
s103, extracting the characteristics of the first font characters and the characteristics of the second font characters, and inputting the characteristics into a preset character classification model based on a support vector machine for classification, so that the first font characters are classified into handwritten characters, or the second font characters are classified into handwritten characters;
and S104, combining all the divided handwritten characters into a handwritten character text, and recording the handwritten character text as an answer sheet text.
As described above, the handwritten character text and the print character text recognized by the color setting method are realized. The method makes the distinction between the handwritten characters and the print characters more obvious, specifically, the RGB color of the pixel points in the specified answer sheet picture is set to be (0,0,0), (255 ) or (Q, Q, Q), wherein Q is a preset numerical value which is larger than 0 and smaller than 255, so that a temporary picture which is composed of three colors is obtained, the occupied areas of the three colors are calculated, and the occupied areas of the two colors with smaller areas are respectively subjected to character segmentation processing (the color area with the largest area is a background), so that the segmented first type of character characters and the segmented second type of character characters (which type of character is unknown temporarily is the handwritten characters) are obtained. The support vector machine is a generalized linear classifier which performs binary classification on data according to a supervised learning mode and is suitable for comparing characters to be recognized with prestored characters so as to output the most similar characters. And therefore, the characteristics of the first type of font characters and the characteristics of the second type of font characters are extracted, and the characters are input into a preset character classification model based on a support vector machine for classification, so that the character is known to be handwritten. And finally, combining all the divided handwritten characters into handwritten character texts, and recording the handwritten character texts as answer sheet texts. When the teacher end performs the examination paper evaluation, only the answer paper content of the student is needed, so that the examination paper evaluation method only takes the answer paper content of the student as the answer paper text to reduce the network overhead. In addition, the RGB color of the pixel point is set to (0,0,0), (255 ) or (Q, Q, Q), so that the identification of the background color is more accurate (due to the influence of light when a picture is shot, the RGB value of the background color is not pure white, and the identification method of the traditional scheme can cause the inaccuracy of the identification of the background area, thereby influencing the extraction of the handwritten characters). The features of the first font characters and the features of the second font characters are, for example, special points in pixel points corresponding to the characters: such as extreme points or isolated points, etc.
In one embodiment, the step S101 of acquiring values of R color channel, G color channel and B color channel in an RGB color model of a pixel point in the specified answer sheet picture, and setting the RGB color of the pixel point in the specified answer sheet picture to (0,0,0), (255 ) or (Q, Q) according to a preset color setting method, where Q is a preset value greater than 0 and less than 255, includes:
s1011, collecting the numerical value of the R color channel, the numerical value of the G color channel and the numerical value of the B color channel in the RGB color model of the pixel point in the specified answer sheet picture, and according to a formula: f1 ═ MIN { ROUND [ (a1R + a2G + a3B)/L,0], a }, obtaining a color impact value F1, where MIN is a minimum function, ROUND is a rounding function, a1, a2, a3 are positive numbers greater than 0 and less than L, L is an integer greater than 0, a is a first threshold parameter with a preset value within a range (0,255), and R, G, B are a value of R color channel, a value of G color channel, and a value of B color channel in the RGB color model of the designated pixel point in the designated picture, respectively;
s1012, judging whether the value of the color influence numerical value F1 is equal to A or not;
s1013, if the color impact value F1 is equal to a, according to the formula: obtaining a color impact value F2 by taking F2 ═ MAX { ROUND [ (a1R + a2G + a3B)/L,0], B }, where MAX is a maximum function, B is a second threshold parameter within a preset value range (0,255), and B is greater than a;
s1014, judging whether the value of the color influence numerical value F2 is equal to B;
and S1015, if the color influence numerical value F2 is not equal to B, setting the RGB color of the specified pixel point to (255 ).
As described above, the acquisition of the numerical value of the R color channel, the numerical value of the G color channel, and the numerical value of the B color channel in the RGB color model of the pixel point in the specified answer sheet picture is realized, and the RGB color of the pixel point in the specified answer sheet picture is set to (0,0,0), (255,255,255) or (Q, Q) according to a preset color setting method. Specifically, two formulas are employed: f1 ═ MIN { ROUND [ (a1R + a2G + a3B)/L,0], a }, F2 ═ MAX { ROUND [ (a1R + a2G + a3B)/L,0], B }, to set the designated pixel point to (0,0,0), (255,255,255), or (Q, Q). Further, if the value of the color impact value F1 is not equal to a, the RGB color of the designated pixel point is set to (0,0, 0). Further, if the value of the color impact value F2 is equal to B, the RGB color of the designated pixel point is set to (Q, Q). Thus, ternary processing is realized, so that the background, the printed characters and the handwritten characters are completely distinguished, and the character recognition is more accurate. The ROUND function is a rounding function, ROUND (M, s) refers to rounding a real number M in decimal places s, where s is an integer greater than or equal to 0, e.g., ROUND (8.3, 0) ═ 8.
In one embodiment, the score estimation model includes a coding long-short term memory network and a decoding long-short term memory network connected in sequence, and the learning feature data is input into a preset trained score estimation model to obtain an estimation result output by the score estimation model, where the score estimation model is trained based on the long-short term memory model in step S3, including:
s301, inputting the learning characteristic data into the long-short term memory network for coding for processing to obtain a hidden state vector sequence in the long-short term memory network for coding;
s302, inputting the hidden state vector sequence into the decoding long-short term memory network for processing to obtain a predicted knowledge point and a corresponding mastery degree value output by the decoding long-short term memory network;
and S303, taking the knowledge points with the degree of mastery value larger than a preset degree of mastery threshold value as an estimation result, and outputting the estimation result.
As mentioned above, the estimation result output by the grading estimation model is obtained. The encoding in the long-short term memory network for encoding of the present application is to convert input information into a vector sequence of a specified length, and the decoding in the long-short term memory network for decoding is to convert the input vector sequence into a predicted vector sequence. The decoding long-short term memory network can be operated by any method, such as the following formula:eij＝score(si，hj)，
Figure BDA0002207491770000122
wherein c isiFinal hidden state vector c in long-short term memory network for said encodingi，aijIs a weight parameter, wherein n time periods (since the mastery degree of the knowledge point changes with the change of time, for example, a certain knowledge point is forgotten in the case of not using and not reviewing in the long-term and short-term memory network, n time periods are set by using the time characteristics of the long-term and short-term memory network) are shared, and si is the ith hidden state vector in the long-term and short-term memory network for decoding, score(s)i，hj) Refers to the score, W, calculated from si and hj using a preset score functionCFor the weight, p is the output probability, yt is the output of the long-short term memory network for decoding corresponding to the t-th time period, and x is the input (directly related to the learning characteristic data). And then taking the knowledge points with the mastery degree value larger than a preset mastery degree threshold value as an estimation result, and outputting the estimation result, thereby taking the knowledge points with high mastery degree value as the estimation result.
In one embodiment, the step S301 of inputting the learning feature data into the long-short term memory network for encoding and processing to obtain a hidden state vector sequence in the long-short term memory network for encoding includes:
s3011, according to the formula: h ist＝LSTMenc(xt，ht-1) Obtaining the hidden state vector h in the long-short term memory network for encodingtWhere t is the t-th time period, htFor the hidden state vector corresponding to the t-th time segment, ht-1For the hidden state vector corresponding to the t-1 th time segment, XtFor learning feature data of the t-th time period, LSTMencThe encoding operation is performed by using a long-term and short-term memory network for encoding;
s3012, according to the formula:
Figure BDA0002207491770000131
eij＝score(si，hj) Obtaining the final hidden state vector c in the long-short term memory network for encodingi，aijIs a weight parameter, where there are n time periods, siScore(s) for the ith hidden state vector in the long-short term memory network for encodingi，hj) According to s by using a preset score functioniAnd hjA calculated score;
s3013, forming a hidden state vector sequence c by using the final hidden state vectors corresponding to a plurality of preset time periods1、c2...、cn。
As described above, the learning feature data is input into the long-short term memory network for encoding and processed to obtain the hidden state vector sequence in the long-short term memory network for encoding. This application uses the formula: h ist＝LSTMenc(xt，ht-1) Obtaining the hidden state vector h in the long-short term memory network for encodingtThen according to the formula:
Figure BDA0002207491770000132
eij＝score(si，hj) Obtaining the final hidden state vector c in the long-short term memory network for encodingiThat is, the attention mechanism is introduced to automatically capture the important information for the outcome, so as to finally hide the state vectorThe sequence is used as the decoding basis of the long-term and short-term memory network for decoding. Due to the adoption of the attention mechanism, the weight distribution is more accurate, and the prediction accuracy is favorably improved. Accordingly, the final hidden state vectors corresponding to a plurality of preset time periods form a hidden state vector sequence c1、c2...、cnAnd thus serves as a decoding basis for the long-term and short-term memory network for decoding.
In one embodiment, each of the teaching time periods has m tags, each of the tags is recorded with a tag value, and the step S7 of calculating the correlation index between the teaching time periods according to a preset time period correlation index calculation method includes:
s701, mapping the teaching time period into a high-dimensional vector of a high-dimensional virtual space according to the label numerical value, wherein the dimension of the high-dimensional vector is m;
s702, according to a formula:
Figure BDA0002207491770000141
and calculating to obtain a correlation index DIS between the two teaching time periods, wherein C is a high-dimensional vector corresponding to one teaching time period, Ci is the ith component vector of the high-dimensional vector C, the high-dimensional vector C has m component vectors in total, D is a high-dimensional vector corresponding to the other teaching time period, Di is the ith component vector of the high-dimensional vector D, and the high-dimensional vector D has m component vectors in total.
As described above, the calculation of the association index between the teaching time periods according to the preset time period association index calculation method is realized. Wherein, the label refers to factors which have influence on the teaching quality, such as: whether the knowledge point is taught after a physical education course; the association degree of the knowledge point in the whole knowledge point network; the degree of easy learning of the knowledge point; the importance of the knowledge point, etc. According to the label value, the teaching time period is mapped into a high-dimensional vector of a high-dimensional virtual space, the dimension of the high-dimensional vector is m, factors influencing the time period are accurately mapped into the high-dimensional vector in a numerical mode (namely, the label value is used as the numerical value of the component vector of the high-dimensional vector), and therefore the calculation of the association degree between the time periods is possible. Then according to the formula:
Figure BDA0002207491770000142
and calculating to obtain a correlation index DIS between the two teaching time periods, so as to obtain the degree of correlation between the influencing factors of the two teaching time periods, and thus, the degree of correlation is taken as a basis for judging whether the teaching quality needs to be improved.
In one embodiment, the teacher 'S terminal is provided with a voice input device, and the sending of the reminder information for improving teaching quality to the teacher' S terminal, wherein the reminder information is accompanied by the step S8 of specifying the time period, and the method includes:
s81, acquiring voice data acquired by the teacher end by using the voice input device;
s82, recognizing the voice data into a voice text according to a preset voice recognition technology;
s83, judging whether the voice text has the appointed key words or not;
s84, if the voice text has the appointed key words, acquiring appointed knowledge points corresponding to the appointed key words according to the corresponding relation between the preset key words and the knowledge points;
and S85, attaching the voice data to a specified position in the scoring result, wherein the specified position is a position corresponding to the specified knowledge point.
As described above, attaching the voice data to a specified position in the scoring result is achieved, wherein the specified position is a position corresponding to the specified knowledge point. Wherein the speech input means is for example a microphone array. The voice recognition technology is used for recognizing voice as text, so that data processing is more convenient. The keywords may be set as knowledge points themselves, or as words related to the knowledge points themselves. Accordingly, the voice data is attached to a specified position in the scoring result. Because the voice commentary is more concise and easier for students to understand, the voice commentary is easier for students to be aware of mistakes made, thereby mastering the deduction knowledge points again. Moreover, due to the adoption of the keyword judgment mode, the teacher end can realize targeted voice input without searching questions corresponding to the knowledge points one by one, so that the method is more efficient and quicker.
According to the teaching method based on the long-term and short-term memory, the specified answer sheet picture is obtained, and character recognition processing is carried out on the specified answer sheet picture to obtain an answer sheet text; sending the answer sheet text to a teacher end, and receiving a grading result of the teacher end on the answer sheet text; acquiring learning characteristic data of students corresponding to the answer sheet texts, and acquiring estimation results output by the grading estimation model; calculating the difference degree value between the estimated result and the scoring result; if the difference degree value is larger than a preset error threshold value, generating a deduction knowledge point; acquiring a teaching time period corresponding to each deduction knowledge point; calculating to obtain a correlation index between the teaching time periods; and acquiring a designated association index with a ranking larger than a preset ranking threshold value in the association index table, acquiring a designated time period corresponding to the designated association index, and sending reminding information for improving the teaching quality to the teacher end, wherein the reminding information is accompanied with the designated time period. Thereby effectively improving the teaching quality.
Referring to fig. 2, an embodiment of the present application provides a teaching device based on long-term and short-term memory, including:
an answer sheet text obtaining unit 10, configured to obtain a specified answer sheet picture, and perform character recognition processing on the specified answer sheet picture to obtain an answer sheet text, where the specified answer sheet picture is a picture obtained by image acquisition of a paper test sheet on which a question is answered;
the answer sheet text sending unit 20 is configured to send the answer sheet text to a teacher end, and receive a scoring result of the teacher end on the answer sheet text;
the estimation result obtaining unit 30 is configured to obtain learning feature data of a student corresponding to the answer sheet text, and input the learning feature data into a preset trained score estimation model, so as to obtain an estimation result output by the score estimation model, where the score estimation model is trained based on a long-term and short-term memory model;
an error threshold value judging unit 40, configured to calculate a difference degree value between the estimated result and the scoring result according to a preset difference degree value calculation method, and judge whether the difference degree value is greater than a preset error threshold value, where the error threshold value is greater than or equal to 0;
a deduction knowledge point generating unit 50, configured to generate a deduction knowledge point according to a position to be deducted from the answer sheet text if the difference degree value is greater than a preset error threshold;
a teaching time period obtaining unit 60, configured to retrieve a preset knowledge point teaching time table, and obtain a teaching time period corresponding to each deduction knowledge point according to the time table;
the correlation index calculating unit 70 is configured to calculate correlation indexes between the teaching time periods according to a preset time period correlation index calculating method, and arrange the correlation indexes in a descending order according to the magnitude of the numerical values to obtain a correlation index table;
and the reminding information sending unit 80 is configured to obtain a specified association index with a rank greater than a preset ranking threshold in the association index table, obtain a specified time period corresponding to the specified association index, and send reminding information for improving teaching quality to the teacher end, where the reminding information is accompanied by the specified time period.
The operations performed by the units correspond to the steps of the teaching method based on long-term and short-term memory in the foregoing embodiment one to one, and are not described herein again.
In one embodiment, the paper test paper with the answered questions includes handwritten characters and print characters, and the answer paper text obtaining unit 10 includes:
a temporary picture acquiring subunit, configured to acquire a numerical value of an R color channel, a numerical value of a G color channel, and a numerical value of a B color channel in an RGB color model of a pixel point in the specified answer sheet picture, and set the RGB color of the pixel point in the specified answer sheet picture to (0,0,0), (255 ) or (Q, Q) according to a preset color setting method, where Q is a preset numerical value that is greater than 0 and less than 255, so as to obtain a temporary picture composed of three colors;
the area calculation subunit is used for calculating the areas occupied by the three colors in the temporary picture and respectively performing character segmentation processing on the areas occupied by the two colors with smaller areas so as to obtain the segmented first font characters and the segmented second font characters;
the handwritten character classification subunit is used for extracting the characteristics of the first type of font characters and the characteristics of the second type of font characters, and inputting the characteristics into a preset character classification model based on a support vector machine for classification, so that the first type of font is classified into handwritten characters, or the second type of font is classified into handwritten characters;
and the answer sheet text acquisition subunit is used for combining all the divided handwritten characters into handwritten character texts and recording the handwritten character texts as answer sheet texts.
The operations executed by the sub-units correspond to the steps of the teaching method based on long-term and short-term memory in the foregoing embodiment one to one, and are not described herein again.
In one embodiment, the temporary picture taking subunit includes:
a color influence value F1 obtaining module, configured to collect a value of an R color channel, a value of a G color channel, and a value of a B color channel in an RGB color model of a pixel point in the specified answer sheet picture, and according to a formula: f1 ═ MIN { ROUND [ (a1R + a2G + a3B)/L,0], a }, obtaining a color impact value F1, where MIN is a minimum function, ROUND is a rounding function, a1, a2, a3 are positive numbers greater than 0 and less than L, L is an integer greater than 0, a is a first threshold parameter with a preset value within a range (0,255), and R, G, B are a value of R color channel, a value of G color channel, and a value of B color channel in the RGB color model of the designated pixel point in the designated picture, respectively;
a color impact numerical value F1 judging module, configured to judge whether the value of the color impact numerical value F1 is equal to A;
a color impact numerical value F2 obtaining module, configured to, if the color impact numerical value F1 is equal to A, according to the formula: obtaining a color impact value F2 by taking F2 ═ MAX { ROUND [ (a1R + a2G + a3B)/L,0], B }, where MAX is a maximum function, B is a second threshold parameter within a preset value range (0,255), and B is greater than a;
a color impact numerical value F2 judging module, configured to judge whether the value of the color impact numerical value F2 is equal to B;
and the color setting module is used for setting the RGB color of the specified pixel point to be (255,255,255) if the value of the color influence numerical value F2 is not equal to B.
The operations executed by the modules correspond to the steps of the teaching method based on long-term and short-term memory in the foregoing embodiment one to one, and are not described herein again.
In one embodiment, the score estimation model includes a long-short term memory network for encoding and a long-short term memory network for decoding, which are connected in sequence, and the estimation result obtaining unit 30 includes:
the coding subunit is used for inputting the learning characteristic data into the long-short term memory network for coding for processing to obtain a hidden state vector sequence in the long-short term memory network for coding;
a predicted knowledge point obtaining subunit, configured to input the hidden state vector sequence into the decoding long-short term memory network for processing, so as to obtain a predicted knowledge point and a corresponding degree of mastery value output by the decoding long-short term memory network;
and the estimation result output subunit is used for taking the knowledge points with the mastery degree value larger than a preset mastery degree threshold value as estimation results and outputting the estimation results.
The operations executed by the sub-units correspond to the steps of the teaching method based on long-term and short-term memory in the foregoing embodiment one to one, and are not described herein again.
In one embodiment, the encoding subunit includes:
a hidden state vector acquisition module configured to: h ist＝LSTMenc(xt，ht-1) Obtaining the hidden state vector h in the long-short term memory network for encodingtWhere t is the t-th time period, htFor the hidden state vector corresponding to the t-th time segment, ht-1For the hidden state vector corresponding to the t-1 th time segment, XtFor learning feature data of the t-th time period, LSTMencThe encoding operation is performed by using a long-term and short-term memory network for encoding;
a final hidden state vector acquisition module configured to:
Figure BDA0002207491770000181
eij＝score(si，hj) Obtaining the final hidden state vector c in the long-short term memory network for encodingi，aijIs a weight parameter, where there are n time periods, siScore(s) for the ith hidden state vector in the long-short term memory network for encodingi，hj) According to s by using a preset score functioniAnd hjA calculated score;
a hidden state vector sequence obtaining module, configured to form a hidden state vector sequence c from final hidden state vectors corresponding to multiple preset time periods1、c2...、cn。
The operations executed by the modules correspond to the steps of the teaching method based on long-term and short-term memory in the foregoing embodiment one to one, and are not described herein again.
In one embodiment, each of the teaching periods has m tags, the tags are recorded with tag values, and the correlation index calculation unit 70 includes:
a high-dimensional vector mapping subunit, configured to map the teaching time period into a high-dimensional vector of a high-dimensional virtual space according to the tag value, where the dimension of the high-dimensional vector is m;
a correlation index calculating subunit configured to:
Figure BDA0002207491770000191
and calculating to obtain a correlation index DIS between the two teaching time periods, wherein C is a high-dimensional vector corresponding to one teaching time period, Ci is the ith component vector of the high-dimensional vector C, the high-dimensional vector C has m component vectors in total, D is a high-dimensional vector corresponding to the other teaching time period, Di is the ith component vector of the high-dimensional vector D, and the high-dimensional vector D has m component vectors in total.
The operations executed by the sub-units correspond to the steps of the teaching method based on long-term and short-term memory in the foregoing embodiment one to one, and are not described herein again.
In one embodiment, the teacher end is provided with a voice input device, and the device comprises:
the voice data acquisition unit is used for acquiring voice data acquired by the teacher end by using the voice input device;
the voice text acquisition unit is used for recognizing the voice data into a voice text according to a preset voice recognition technology;
a specified keyword judgment unit for judging whether a specified keyword exists in the voice text;
the appointed knowledge point acquisition unit is used for acquiring appointed knowledge points corresponding to appointed keywords according to the corresponding relation between preset keywords and knowledge points if the appointed keywords exist in the voice text;
and the voice data attaching unit is used for attaching the voice data to a specified position in the scoring result, wherein the specified position is a position corresponding to the specified knowledge point.
The operations performed by the units correspond to the steps of the teaching method based on long-term and short-term memory in the foregoing embodiment one to one, and are not described herein again.
The teaching device based on long-term and short-term memory obtains a specified answer sheet picture, and performs character recognition processing on the specified answer sheet picture to obtain an answer sheet text; sending the answer sheet text to a teacher end, and receiving a grading result of the teacher end on the answer sheet text; acquiring learning characteristic data of students corresponding to the answer sheet texts, and acquiring estimation results output by the grading estimation model; calculating the difference degree value between the estimated result and the scoring result; if the difference degree value is larger than a preset error threshold value, generating a deduction knowledge point; acquiring a teaching time period corresponding to each deduction knowledge point; calculating to obtain a correlation index between the teaching time periods; and acquiring a designated association index with a ranking larger than a preset ranking threshold value in the association index table, acquiring a designated time period corresponding to the designated association index, and sending reminding information for improving the teaching quality to the teacher end, wherein the reminding information is accompanied with the designated time period. Thereby effectively improving the teaching quality.
Referring to fig. 3, an embodiment of the present invention further provides a computer device, where the computer device may be a server, and an internal structure of the computer device may be as shown in the figure. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for storing data used by teaching methods based on long-term and short-term memory. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a teaching method based on long-short term memory.
The processor executes the teaching method based on long-term and short-term memory, wherein the steps of the method are respectively in one-to-one correspondence with the steps of executing the teaching method based on long-term and short-term memory of the foregoing embodiment, and are not described herein again.
It will be understood by those skilled in the art that the structures shown in the drawings are only block diagrams of some of the structures associated with the embodiments of the present application and do not constitute a limitation on the computer apparatus to which the embodiments of the present application may be applied.
The computer equipment acquires a specified answer sheet picture, and performs character recognition processing on the specified answer sheet picture to obtain an answer sheet text; sending the answer sheet text to a teacher end, and receiving a grading result of the teacher end on the answer sheet text; acquiring learning characteristic data of students corresponding to the answer sheet texts, and acquiring estimation results output by the grading estimation model; calculating the difference degree value between the estimated result and the scoring result; if the difference degree value is larger than a preset error threshold value, generating a deduction knowledge point; acquiring a teaching time period corresponding to each deduction knowledge point; calculating to obtain a correlation index between the teaching time periods; and acquiring a designated association index with a ranking larger than a preset ranking threshold value in the association index table, acquiring a designated time period corresponding to the designated association index, and sending reminding information for improving the teaching quality to the teacher end, wherein the reminding information is accompanied with the designated time period. Thereby effectively improving the teaching quality.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for teaching based on long-term and short-term memory is implemented, where the steps included in the method are respectively in one-to-one correspondence with the steps of executing the method for teaching based on long-term and short-term memory in the foregoing embodiments, and are not described herein again.
The computer-readable storage medium obtains a specified answer sheet picture, and performs character recognition processing on the specified answer sheet picture to obtain an answer sheet text; sending the answer sheet text to a teacher end, and receiving a grading result of the teacher end on the answer sheet text; acquiring learning characteristic data of students corresponding to the answer sheet texts, and acquiring estimation results output by the grading estimation model; calculating the difference degree value between the estimated result and the scoring result; if the difference degree value is larger than a preset error threshold value, generating a deduction knowledge point; acquiring a teaching time period corresponding to each deduction knowledge point; calculating to obtain a correlation index between the teaching time periods; and acquiring a designated association index with a ranking larger than a preset ranking threshold value in the association index table, acquiring a designated time period corresponding to the designated association index, and sending reminding information for improving the teaching quality to the teacher end, wherein the reminding information is accompanied with the designated time period. Thereby effectively improving the teaching quality.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.

Claims (10)

1. A teaching method based on long-term and short-term memory is characterized by comprising the following steps:
acquiring a specified answer sheet picture, and performing character recognition processing on the specified answer sheet picture to obtain an answer sheet text, wherein the specified answer sheet picture is a picture obtained by performing image acquisition on a paper test sheet with a finished answer;
sending the answer sheet text to a teacher end, and receiving a grading result of the teacher end on the answer sheet text;
acquiring learning characteristic data of students corresponding to the answer sheet text, and inputting the learning characteristic data into a preset trained score estimation model so as to obtain an estimation result output by the score estimation model, wherein the score estimation model is formed by training based on a long-term and short-term memory model;
calculating a difference degree value between the estimated result and the scoring result according to a preset difference degree value calculation method, and judging whether the difference degree value is greater than a preset error threshold value, wherein the error threshold value is greater than or equal to 0;
if the difference degree value is larger than a preset error threshold value, generating a deduction knowledge point according to the position to be deducted in the answer sheet text;
calling a preset knowledge point teaching time table, and acquiring teaching time periods corresponding to each deduction knowledge point according to the time table;
calculating to obtain the association indexes among the teaching time periods according to a preset time period association index calculation method, and performing descending order on the association indexes according to the numerical value to obtain an association index table;
and acquiring a designated association index with a ranking larger than a preset ranking threshold value in the association index table, acquiring a designated time period corresponding to the designated association index, and sending reminding information for improving the teaching quality to the teacher end, wherein the reminding information is accompanied with the designated time period.
2. The teaching method based on long-term and short-term memory as claimed in claim 1, wherein the paper test paper with the answered questions comprises handwritten characters and printed characters, and the step of performing character recognition processing on the specified answer sheet pictures to obtain answer sheet texts comprises:
collecting numerical values of an R color channel, a G color channel and a B color channel in an RGB color model of a pixel point in the specified answer sheet picture, and setting the RGB color of the pixel point in the specified answer sheet picture as (0,0,0), (255 ) or (Q, Q, Q) according to a preset color setting method, wherein Q is a preset numerical value which is more than 0 and less than 255, so as to obtain a temporary picture consisting of three colors;
calculating the areas occupied by the three colors in the temporary picture, and respectively performing character segmentation processing on the areas occupied by the two colors with smaller areas so as to obtain a first type of character and a second type of character which are segmented;
extracting the characteristics of the first font characters and the characteristics of the second font characters, and inputting the characteristics into a preset character classification model based on a support vector machine for classification, so that the first font characters are classified into handwritten characters, or the second font characters are classified into handwritten characters;
and combining all the divided handwritten characters into handwritten character texts, and recording the handwritten character texts as answer sheet texts.
3. The teaching method based on long-term and short-term memory as claimed in claim 2, wherein the step of collecting the numerical values of R color channel, G color channel and B color channel in the RGB color model of the pixel points in the specified answer sheet picture and setting the RGB color of the pixel points in the specified answer sheet picture to (0,0,0), (255 ) or (Q, Q) according to a preset color setting method, wherein Q is a preset numerical value greater than 0 and less than 255 comprises:
collecting the numerical value of an R color channel, the numerical value of a G color channel and the numerical value of a B color channel in an RGB color model of a pixel point in the specified answer sheet picture, and according to a formula: f1 ═ MIN { ROUND [ (a1R + a2G + a3B)/L,0], a }, obtaining a color impact value F1, where MIN is a minimum function, ROUND is a rounding function, a1, a2, a3 are positive numbers greater than 0 and less than L, L is an integer greater than 0, a is a first threshold parameter with a preset value within a range (0,255), and R, G, B are a value of R color channel, a value of G color channel, and a value of B color channel in the RGB color model of the designated pixel point in the designated picture, respectively;
determining whether the value of the color impact value F1 is equal to a;
if the color impact value F1 is equal to A, then according to the formula: obtaining a color impact value F2 by taking F2 ═ MAX { ROUND [ (a1R + a2G + a3B)/L,0], B }, where MAX is a maximum function, B is a second threshold parameter within a preset value range (0,255), and B is greater than a;
determining whether the value of the color impact value F2 is equal to B;
if the value of the color impact value F2 is not equal to B, the RGB color of the designated pixel point is set to (255 ).
4. The teaching method based on long-short term memory as claimed in claim 1, wherein the score estimation model comprises a coding long-short term memory network and a decoding long-short term memory network which are connected in sequence, the learning feature data is input into a preset trained score estimation model, so as to obtain an estimation result output by the score estimation model, and the score estimation model is trained based on the long-short term memory model and comprises the following steps:
inputting the learning characteristic data into the long-short term memory network for coding for processing to obtain a hidden state vector sequence in the long-short term memory network for coding;
inputting the hidden state vector sequence into the decoding long-short term memory network for processing to obtain a predicted knowledge point and a corresponding mastery degree value output by the decoding long-short term memory network;
and taking the knowledge points with the mastery degree value larger than a preset mastery degree threshold value as an estimation result, and outputting the estimation result.
5. The method as claimed in claim 4, wherein the step of inputting the learning feature data into the coding long-short term memory network for processing to obtain the hidden state vector sequence in the coding long-short term memory network comprises:
according to the formula: h ist＝LSTMenc(xt,ht-1) Obtaining the hidden state vector h in the long-short term memory network for encodingtWhere t is the t-th time period, htFor the hidden state vector corresponding to the t-th time segment, ht-1For the hidden state vector corresponding to the t-1 th time segment, XtFor learning feature data of the t-th time period, LSTMencThe encoding operation is performed by using a long-term and short-term memory network for encoding;
according to the formula:
Figure FDA0002207491760000031
eij＝score(si,hj) Obtaining the final hidden state vector c in the long-short term memory network for encodingi，aijIs a weight parameter, where there are n time periods, siScore(s) for the ith hidden state vector in the long-short term memory network for encodingi,hj) According to s by using a preset score functioniAnd hjA calculated score;
forming a hidden state vector sequence c by using the final hidden state vectors corresponding to a plurality of preset time periods1、c2…、cn。
6. The teaching method based on long-short term memory as claimed in claim 1, wherein each of the teaching time periods has m tags, the tags are recorded with tag values, and the step of calculating the correlation index between the teaching time periods according to a preset time period correlation index calculation method comprises:
mapping the teaching time period into a high-dimensional vector of a high-dimensional virtual space according to the label numerical value, wherein the dimension of the high-dimensional vector is m;
according to the formula:
and calculating to obtain a correlation index DIS between the two teaching time periods, wherein C is a high-dimensional vector corresponding to one teaching time period, Ci is the ith component vector of the high-dimensional vector C, the high-dimensional vector C has m component vectors in total, D is a high-dimensional vector corresponding to the other teaching time period, Di is the ith component vector of the high-dimensional vector D, and the high-dimensional vector D has m component vectors in total.
7. The teaching method based on long-short term memory according to claim 1, wherein the teacher's terminal is provided with a voice input device, and the step of sending a reminding message of teaching quality improvement to the teacher's terminal, wherein the step of giving the reminding message the specified time period is followed by the step of:
acquiring voice data acquired by the teacher end by using the voice input device;
recognizing the voice data into a voice text according to a preset voice recognition technology;
judging whether the voice text has specified keywords or not;
if the specified keywords exist in the voice text, acquiring specified knowledge points corresponding to the specified keywords according to the corresponding relation between preset keywords and knowledge points;
attaching the voice data to a specified position in the scoring result, wherein the specified position is a position corresponding to the specified knowledge point.
8. A teaching device based on long-term and short-term memory, comprising:
the answer sheet text acquisition unit is used for acquiring a specified answer sheet picture, and performing character recognition processing on the specified answer sheet picture to obtain an answer sheet text, wherein the specified answer sheet picture is a picture obtained by performing image acquisition on a paper test sheet which has already answered;
the answer sheet text sending unit is used for sending the answer sheet text to a teacher end and receiving a grading result of the teacher end on the answer sheet text;
the estimation result obtaining unit is used for obtaining learning characteristic data of students corresponding to the answer sheet texts and inputting the learning characteristic data into a preset score estimation model after training is completed so as to obtain estimation results output by the score estimation model, wherein the score estimation model is formed by training based on a long-term and short-term memory model;
an error threshold value judging unit, configured to calculate a difference degree value between the estimated result and the scoring result according to a preset difference degree value calculation method, and judge whether the difference degree value is greater than a preset error threshold value, where the error threshold value is greater than or equal to 0;
the deduction knowledge point generating unit is used for generating deduction knowledge points according to the deducted positions in the answer sheet text if the difference degree value is larger than a preset error threshold value;
the teaching time period acquisition unit is used for calling a preset knowledge point teaching time table and acquiring teaching time periods corresponding to each deduction knowledge point according to the time table;
the association index calculation unit is used for calculating association indexes among the teaching time periods according to a preset time period association index calculation method, and performing descending order on the association indexes according to the numerical value to obtain an association index table;
and the reminding information sending unit is used for acquiring the specified association index of which the rank is greater than a preset ranking threshold value in the association index table, acquiring a specified time period corresponding to the specified association index, and sending reminding information for improving the teaching quality to the teacher end, wherein the specified time period is attached to the reminding information.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
CN201910886610.9A 2019-09-19 2019-09-19 Teaching method and device based on long-short-term memory and computer equipment Active CN110795997B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201910886610.9A CN110795997B (en) 2019-09-19 2019-09-19 Teaching method and device based on long-short-term memory and computer equipment
PCT/CN2019/116338 WO2021051502A1 (en) 2019-09-19 2019-11-07 Long short-term memory-based teaching method and apparatus, and computer device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910886610.9A CN110795997B (en) 2019-09-19 2019-09-19 Teaching method and device based on long-short-term memory and computer equipment

Publications (2)

Publication Number Publication Date
CN110795997A true CN110795997A (en) 2020-02-14
CN110795997B CN110795997B (en) 2023-07-28

Family

ID=69427350

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910886610.9A Active CN110795997B (en) 2019-09-19 2019-09-19 Teaching method and device based on long-short-term memory and computer equipment

Country Status (2)

Country Link
CN (1) CN110795997B (en)
WO (1) WO2021051502A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111091733A (en) * 2020-03-19 2020-05-01 浙江正元智慧科技股份有限公司 Auxiliary detection system for real-time teaching achievements of teachers
CN114419636A (en) * 2022-01-10 2022-04-29 北京百度网讯科技有限公司 Text recognition method, device, equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180174589A1 (en) * 2016-12-19 2018-06-21 Samsung Electronics Co., Ltd. Speech recognition method and apparatus
CN109389091A (en) * 2018-10-22 2019-02-26 重庆邮电大学 The character identification system and method combined based on neural network and attention mechanism
WO2019075820A1 (en) * 2017-10-20 2019-04-25 深圳市鹰硕技术有限公司 Test paper reviewing system

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10706955B2 (en) * 2010-03-23 2020-07-07 Iogenetics, Llc Bioinformatic processes for determination of peptide binding
CN103164994B (en) * 2013-03-15 2015-01-07 南京信息工程大学 Operation exercise correction and feedback method
CN106981227A (en) * 2017-05-24 2017-07-25 亳州学院 A kind of Mathematical Teaching System
CN109117738A (en) * 2018-07-19 2019-01-01 江苏黄金屋教育发展股份有限公司 Method to go over files based on artificial intelligence
CN109284355B (en) * 2018-09-26 2020-09-22 杭州大拿科技股份有限公司 Method and device for correcting oral arithmetic questions in test paper
CN109902683A (en) * 2019-03-07 2019-06-18 大连大学 Paper core point and Data Input method and system
CN110110585B (en) * 2019-03-15 2023-05-30 西安电子科技大学 Intelligent paper reading implementation method and system based on deep learning and computer program

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180174589A1 (en) * 2016-12-19 2018-06-21 Samsung Electronics Co., Ltd. Speech recognition method and apparatus
WO2019075820A1 (en) * 2017-10-20 2019-04-25 深圳市鹰硕技术有限公司 Test paper reviewing system
CN109389091A (en) * 2018-10-22 2019-02-26 重庆邮电大学 The character identification system and method combined based on neural network and attention mechanism

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111091733A (en) * 2020-03-19 2020-05-01 浙江正元智慧科技股份有限公司 Auxiliary detection system for real-time teaching achievements of teachers
CN111091733B (en) * 2020-03-19 2020-06-30 浙江正元智慧科技股份有限公司 Auxiliary detection system for real-time teaching achievements of teachers
CN114419636A (en) * 2022-01-10 2022-04-29 北京百度网讯科技有限公司 Text recognition method, device, equipment and storage medium

Also Published As

Publication number Publication date
WO2021051502A1 (en) 2021-03-25
CN110795997B (en) 2023-07-28

Similar Documents

Publication Publication Date Title
CN109086756B (en) Text detection analysis method, device and equipment based on deep neural network
CN109271401B (en) Topic searching and correcting method and device, electronic equipment and storage medium
CN110569356B (en) Interviewing method and device based on intelligent interviewing interaction system and computer equipment
WO2021253904A1 (en) Test case set generation method, apparatus and device, and computer readable storage medium
CN111368049B (en) Information acquisition method, information acquisition device, electronic equipment and computer readable storage medium
CN112507125A (en) Triple information extraction method, device, equipment and computer readable storage medium
CN111046133A (en) Question-answering method, question-answering equipment, storage medium and device based on atlas knowledge base
CN112817561B (en) Transaction type functional point structured extraction method and system for software demand document
CN111177345B (en) Intelligent question-answering method and device based on knowledge graph and computer equipment
CN110728182B (en) Interview method and device based on AI interview system and computer equipment
CN110851641A (en) Cross-modal retrieval method and device and readable storage medium
CN110929524A (en) Data screening method, device, equipment and computer readable storage medium
JP2017211689A (en) Classification model device, classification model learning method, and classification model learning program
CN112989117B (en) Video classification method and device, electronic equipment and computer storage medium
CN114298035A (en) Text recognition desensitization method and system thereof
CN110795997B (en) Teaching method and device based on long-short-term memory and computer equipment
CN110232128A (en) Topic file classification method and device
CN110705490A (en) Visual emotion recognition method
CN110852071B (en) Knowledge point detection method, device, equipment and readable storage medium
CN116049367A (en) Visual-language pre-training method and device based on non-supervision knowledge enhancement
CN113505786A (en) Test question photographing and judging method and device and electronic equipment
Rama et al. LSTM autoencoders for dialect analysis
CN116244474A (en) Learner learning state acquisition method based on multi-mode emotion feature fusion
CN115935969A (en) Heterogeneous data feature extraction method based on multi-mode information fusion
CN115690566A (en) Deep sea animal new species identification method based on deep migration clustering learning

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