CN116798046A - Automatic modification method, device, medium and program product for junior middle school mathematical formulas - Google Patents
Automatic modification method, device, medium and program product for junior middle school mathematical formulas Download PDFInfo
- Publication number
- CN116798046A CN116798046A CN202310416086.5A CN202310416086A CN116798046A CN 116798046 A CN116798046 A CN 116798046A CN 202310416086 A CN202310416086 A CN 202310416086A CN 116798046 A CN116798046 A CN 116798046A
- Authority
- CN
- China
- Prior art keywords
- formula
- correction
- formulas
- map
- format
- 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
Links
- 238000002715 modification method Methods 0.000 title claims description 6
- 238000012937 correction Methods 0.000 claims abstract description 194
- 238000000034 method Methods 0.000 claims abstract description 57
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 25
- 239000004816 latex Substances 0.000 claims description 21
- 229920000126 latex Polymers 0.000 claims description 21
- 230000004048 modification Effects 0.000 claims description 15
- 238000012986 modification Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 6
- 230000006978 adaptation Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 14
- 230000008569 process Effects 0.000 abstract description 13
- 230000014509 gene expression Effects 0.000 description 17
- 230000006870 function Effects 0.000 description 13
- 239000000243 solution Substances 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 241000208140 Acer Species 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Character Discrimination (AREA)
Abstract
The application discloses a method, equipment, medium and program product for automatically modifying a junior middle school mathematical formula, wherein the method comprises the following steps: based on the hand-written answer picture, obtaining a formula in a map format; classifying the formulas in the map format; and carrying out formula equivalent correction on the classified formulas in the map format to generate correction results. The method of the application divides all junior middle school formulas into seven categories, classifies formulas in a form of a map, carries out different processing on formulas in different forms of map, generates correction results, can cover all junior middle school formula types including simple formulas or complex formulas, and can provide an automatic correction solution of a full link without manual intervention from handwriting answering of students to the whole process of generating correction results, thereby having high intelligent degree and greatly facilitating users.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to an automatic modification method, device, medium and program product for a junior middle school mathematical formula.
Background
Mathematics is always the key discipline, and formulas are the basis and core of mathematics. The intelligent application of the mathematical discipline aspects is not limited to the processing of formulas, including but not limited to formula detection, recognition of handwriting formulas of printing bodies, formula extraction, formula standardization, formula semantic understanding, formula equivalence judgment and the like. The formula processing technology is widely applied to scenes such as intelligent search of mathematical questions, repeated investigation of mathematical questions, recommendation of mathematical questions, correction of mathematical questions and the like.
At present, there are direct matching equivalent for simple expressions such as numbers, letters, scores and the like and equivalent judgment for simple four-rule operation. At present, the result types of the rapid calculation questions of primary and secondary schools are simpler, mainly relate to numbers, fractions, decimal numbers and the like, and mainly relate to basic four-rule addition and subtraction operation. Therefore, in the image recognition, the correction can be mostly accomplished directly by direct comparison with the standard answer. The gap-filling question correcting method for primary and secondary schools judges the correctness by converting the gap-filling question correcting method into an expression of basic operation and enumerating all correct results.
In the process of realizing the technical scheme of the embodiment of the application, the inventor at least discovers that the following technical problems exist in the prior art:
the automatic correction of the operation is involved, and simple extraction and operation are only carried out from the recognized latex expression, such as for the latex expression: frac {3} {2}, representing a score, the score has two objects: a numerator and a denominator. By extracting the content 3 in the first curly brace of the numerator- > frac and the content 2 in the second curly brace of the denominator- > frac from \frac {3} {2} respectively, the numerator and denominator objects are obtained: 2 and 3. During correction, the comparison of \frac {3} {2} is not performed any more, but the purpose of correction judgment is achieved through the most basic digital calculation and comparison of 2 and 3.
The correctness is judged by converting the expression into the expression of basic operation and enumerating all correct results, the types of the related expressions are simple and incomplete, and the corresponding correction algorithm is also simple.
The related algorithm is modified by the existing junior middle school mathematical formula, the related formula is simple in type, the equivalence can be completed by matching and deformation enumeration, and modification of other types of formulas or complex formulas can not be completed. For automatic correction of mathematical formulas, there is no complete solution for the full link.
In summary, the existing formula modifying method has the technical problems that all junior middle school mathematical formula types cannot be covered and an automatic modifying solution of a full link cannot be provided.
Disclosure of Invention
The embodiment of the application provides a method, equipment, medium and program product for automatically modifying a junior middle school mathematical formula, which solve the technical problems that the existing formula modifying method cannot cover all junior middle school mathematical formula types and cannot provide an automatic modifying solution of a full link.
In one aspect, the embodiment of the application provides a method for automatically modifying a mathematical formula of junior middle school, which comprises the following steps: based on the hand-written answer picture, obtaining a formula in a map format; classifying the formulas in the map format; and carrying out formula equivalent correction on the classified formulas in the map format to generate correction results.
Optionally, the formula for obtaining the map format specifically includes: generating a formula in latex format based on the handwriting answer picture; and converting the formula in the latex format into the formula in the map format.
Optionally, before the classifying the formula in the multiple format, the method further includes: and carrying out formula error correction on the formula in the map format.
Optionally, the performing formula error correction on the formula in the multiple format specifically includes: and carrying out formula error correction on the format of the multiple format based on the correct answer.
Optionally, after performing formula correction on the formula in the multiple format, the method further includes: performing formula equivalence correction by using a formula in a map format before error correction; when the correction result is an error or null value, the formula of the corrected map format is used for formula equivalent correction.
Optionally, the formula of the classified map format is subjected to formula equivalent modification, which specifically includes: when the classified formula in the map format is a basic mathematical formula, a basic equivalent correction algorithm is adopted to correct the formula.
Optionally, the performing formula equivalent modification on the classified formula in the map format specifically includes: when the classified formula in the form of the map is not a basic mathematical formula, converting the classified formula in the form of the map into the basic mathematical formula; and adopting a basic equivalence correction algorithm to carry out formula equivalence correction.
On the other hand, the embodiment of the application also provides computer equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the automatic modification method of the junior middle school mathematical formula when executing the computer program.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, realizes the steps of the automatic modification method of the junior middle school mathematical formula.
The embodiment of the application also provides a computer program product, which comprises a computer program, wherein the computer program realizes the steps of the automatic change method of the junior middle school mathematical formula when being executed by a processor.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
based on the hand-written answer picture, obtaining a formula in a map format; classifying the formulas in the map format; and carrying out formula equivalent correction on the classified formulas in the map format to generate correction results. The method of the application divides all junior middle school formulas into seven categories, classifies formulas in a form of a map, carries out different processing on formulas in different forms of map, generates correction results, can cover all junior middle school formula types including simple formulas or complex formulas, and can provide an automatic correction solution of a full link without manual intervention from handwriting answering of students to the whole process of generating correction results, thereby having high intelligent degree and greatly facilitating users.
Further, the formula for obtaining the map format specifically includes: generating a formula in latex format based on the handwriting answer picture; and converting the formula in the latex format into the formula in the map format. The formula in the latex format can be converted into the formula in the multiple format, so that automatic correction can be conveniently performed by adopting a symbol computing system, and the method is simple and efficient.
Still further, before the classifying the formula in the multiple format, the method further includes: and carrying out formula error correction on the formula in the map format. Because the handwriting formula is not as standard as the printing body, the result identified from the handwriting answer picture can be wrong, and the fault tolerance can be increased by carrying out formula error correction on the formula in the form of a map, thereby being beneficial to improving the accuracy of the correction result.
Furthermore, the performing formula error correction on the formula in the multiple format specifically includes: and carrying out formula error correction on the formulas in the multiple format based on the correct answers. Misjudgment of the recognition result in the handwriting answer picture, such as the lower case letter L of the number 1 which is recognized as L or the upper case letter I of the number I, cannot be judged in the process of formula error correction, and correct error correction can be realized by referring to the content of a correct answer. For example, the correct answer contains the capital letter I, the number 1 is modified into the capital letter I, so that the correction rate can be greatly corrected, and the accuracy of the correction result is further improved.
Still further, after performing formula correction on the formula in the multiple format, the method further includes: performing formula equivalence correction by using a formula in a map format before error correction; when the correction result is an error or null value, the formula of the corrected map format is used for formula equivalent correction. When the correction result of the formula equivalent correction using the map format before correction is correct, the formula correction is described as unnecessary operation, and the correction result is directly output. And when the correction result is wrong, the formula of the corrected map format can be used for carrying out formula equivalent correction, so that the error rate of the correction result can be reduced, misjudgment under the condition of no correction is avoided, and the accuracy of the correction result is improved. In addition, when the correction result is a null value, the automatic correction process is described as a problem, and the formula error correction processing can be performed on the formula in the form of a map, so that the input accuracy is improved, and the probability of subsequent errors of the system is reduced.
Still further, the formula of the classified map format is subjected to formula equivalent modification, specifically: when the classified formula in the map format is a basic mathematical formula, a basic equivalent correction algorithm is adopted to correct the formula. When the classified formula in the map format is a basic mathematical formula, the basic equivalent correction algorithm is directly adopted to correct the formula, so that correction efficiency can be improved.
Still further, the performing formula equivalent modification on the classified formulas in the multiple format specifically includes: when the classified formula in the form of the map is not a basic mathematical formula, converting the classified formula in the form of the map into the basic mathematical formula; and adopting a basic equivalence correction algorithm to carry out formula equivalence correction. When the classified formulas in the form of the map format are not basic mathematical formulas, the formulas in the form of the map format after classification are converted into the basic mathematical formulas to carry out subsequent formula equivalent correction, so that different types of formulas can be processed, and diversified formula types can be covered.
Drawings
FIG. 1 is a flow chart of a method for automatically modifying a mathematical formula of a junior middle school according to an embodiment of the application;
FIG. 2 is a flow chart of an automatic modification technique of a junior middle school mathematical formula according to an embodiment of the application;
FIG. 3 is a diagram showing a handwritten answer picture of student 1 in an embodiment of the application;
FIG. 4 is a diagram of a handwritten response of student 2 in an embodiment of the application;
fig. 5 is a handwritten answer picture of a student 3 in an embodiment of the application.
Detailed Description
The embodiment of the application provides a method, equipment, medium and program product for automatically modifying a junior middle school mathematical formula, which solve the technical problems that the existing formula modifying method cannot cover all junior middle school formula types and cannot provide an automatic modifying solution of a full link.
The technical scheme of an embodiment of the application aims to solve the problems, and the general idea is as follows:
based on the hand-written answer picture, obtaining a formula in a map format; classifying the formulas in the map format; and carrying out formula equivalent correction on the classified formulas in the map format to generate correction results. The method of the application divides all junior middle school formulas into seven categories, classifies formulas in a form of a map, carries out different processing on formulas in different forms of map, generates correction results, can cover all junior middle school formula types including simple formulas or complex formulas, and can provide an automatic correction solution of a full link without manual intervention from handwriting answering of students to the whole process of generating correction results, thereby having high intelligent degree and greatly facilitating users.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments. It will be apparent that the described embodiments of the application are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, a method for automatically modifying a mathematical formula of junior middle school according to an embodiment of the present application will be described in detail.
Step 101: based on the hand-written answer picture, obtaining a formula in a map format;
step 102: the formulas in the map format are classified.
Step 103: carrying out formula equivalent correction on the classified formulas in the map format to generate correction results
When the handwritten answer picture is input, execution of step 101 is started: based on the handwriting answer picture, a formula in a map format is obtained.
Step 101 is implemented in the following steps: the application is based on the development of a symbol computing system, and a basic algorithm for judging an equivalent formula is realized by using a map open java sdk, so that a map format is required to be acquired.
After the equation in the map format is obtained, step 102 is started to be executed: the formulas in the map format are classified.
Step 102 is implemented in the following manner: different types of formulas are different in equivalent modification pretreatment, so that formulas are classified according to different pretreatment modes. As shown in the following table, all junior middle school mathematical formulas are divided into seven major classes including angles, coordinates, intervals, piecewise functions, sets of equations and inequality, algebraic and equality classes, inequality and continuous inequality.
For example, a formula in latex format of a handwritten answer picture may be collected, and a batch of seed samples (X, Y) may be made (latex, formula class); then, according to the seed samples, data enhancement is carried out by changing numerical values, adding and subtracting modes and the like, so as to generate more samples; training fasttet text classification model to realize formula classification function.
After the classification is completed, step 103 is started: and carrying out formula equivalent correction on the classified formulas in the map format to generate correction results.
In the specific implementation process, preprocessing the classified formulas in the form of the map, and performing formula equivalent correction on the preprocessed formulas in the form of the map, wherein when the formulas are equivalent, the generated correction result is correct; and when not equivalent, the generated correction result is erroneous.
In order to convert a latex format formula into a multiple format formula, the automatic correction is conveniently performed by adopting a symbol computing system, and the method is simple and efficient, and the step 101 of obtaining the multiple format formula comprises the following steps: generating a formula in latex format based on the handwriting answer picture; and converting the latex format formula into a map format formula.
In a specific implementation, for example: the method comprises the steps of using OCR character recognition software to recognize a handwritten answer picture as a formula in a latex format, converting the formula in the latex format into a formula in a map format, on one hand, cleaning and converting a latex command, on the other hand, extracting formula entities of each command acting domain by using a formula tree hierarchical structure and operation priority, and then placing the extracted formula entities in a proper position in the map formula so as to realize a latex2map algorithm, such as \frac {2} {3} conversion into 2/3. And (3) customizing a set of format specifications by using the non-map arithmetic formula types, and forming a cleaned formula text by using the regular expression. Such as permutation and combination A_2^3, is converted to A2, 3.
Specifically, the regular expression achieves the purpose of replacement by matching the character string pattern. Such as the sub function:
re.sub(Pattern, submode, aimstr)
for the target character string aimstr, a general Pattern is induced by a regular expression, and then the Pattern is uniformly replaced by a specified content submode
aimstr = “A_2^3”
Sub (r "([ AC ]) _ ([ d+) ] (] d+) (- /) d+)", r "\1[ -, 2, -/-, 3]", aimstr) is replaced by regularization to obtain A2, 3.
Because the handwritten formula is not as canonical as the printed matter, the result identified from the handwritten answer picture may be incorrect, so as to increase the fault tolerance, and to be beneficial to improving the accuracy of the correction result, before classifying the formula in the form of a multiple in step 102, the method further includes: and performing formula error correction on the formulas in the map format.
In a specific implementation, for example: OCR character recognition software, the recognized formula contains S1n, because the writing of the sine function is fixed, this type of error can be directly modified to Sin.
In order to greatly correct the correction rate and further improve the accuracy of the correction result, formula correction is performed on a formula in a map format, specifically: based on the correct answer, formula error correction is performed on the format of the map format.
In a specific implementation, for example: OCR character recognition software can have recognition errors due to the close writing to characters. This type of error correction is in two steps.
(1) Error correction is achieved by comparing the correct answers. For example: the answer does not contain 6 but has the letter b, and if the student answer has 6 or not, the letter b is rewritten to the 6 in the student answer. Similarly, z and 2,1 and l, etc.
(2) Based on a map format junior middle school formula set, an answer formula sequence and an identification formula sequence are mainly constructed, a data set of the formula sequence after error correction is generated, an error correction model of a junior middle school mathematical formula is trained, and error correction is performed on an error formula. And simultaneously, the formulas before and after error correction are reserved for subsequent correction. The model is divided into an error-detect module and an error-correct module. Through the error-correction module, the character to be corrected is found, and the output is d= [0.2,0.3,0.6,0.1], wherein d_i represents the probability that the character at the position is an error character. The random mask of bert is changed to specify a mask according to the error-correction module. And selecting 10% of positions with d_i >0.5 in the d vector for mask, and decoding a correct formula sequence.
In order to improve the accuracy of the correction result, after formula correction is performed on the formula in the form of a multiple, the method further comprises the following steps: performing formula equivalence correction by using a formula in a map format before error correction; when the correction result is an error or null value, the formula of the corrected map format is used for formula equivalent correction.
In a specific implementation, for example: and carrying out formula equivalent correction by using a formula in a map format before error correction to generate a correction result. When the correction result is correct, the formula error correction is described as unnecessary operation, and the correction result is directly output; when the correction result is wrong or null, the formula of the corrected map format is used for formula equivalent correction, the correction result is directly output, the error rate of the correction result can be reduced, misjudgment under the condition of no correction is avoided, and the accuracy of the correction result is improved. When the correction result is null, the automatic correction process is described as a problem, and the formula error correction processing can be performed on the formula in the map format, so that the input accuracy is improved, and the probability of subsequent errors of the system is reduced.
In order to improve the correction efficiency, when the classified formula of the map format is a basic mathematical formula, the classified formula of the map format is subjected to formula equivalent correction, specifically: when the classified formula in the map format is a basic mathematical formula, a basic equivalent correction algorithm is adopted to correct the formula.
In a specific implementation, for example: classifying the formula in the form of a map can distinguish whether the formula in the form of a map belongs to a basic mathematical formula, wherein the basic mathematical formula is a number, an expression, an equation, etc., for example, a+b, 3, 2 x-3=4. When the classified formula in the map format is a basic mathematical formula, a basic equivalent correction algorithm is adopted to correct the formula.
The basic equivalence correction algorithm corrects the application scene according to the gap-filling question answer, and the formula equivalence is divided into the following 7 types:
(1) Mathematical term (position change) equivalent
(2) Radian angle conversion equivalent (other conversion equivalents)
(3) Simplified and expanded equivalents
(4) The interval is equivalent to the unequal range
(5) Fractional, and percent interconversion equivalents
(6) The interval is equivalent to the unequal range
(7) Element position change equivalence in collection point set
When the classified formula in the form of map is a basic mathematical formula, the 7 formulas are equivalent to be judged by using a symbolic computing system map. The method is concretely realized as follows:
and step A, subtracting the formulas on two sides of the equal sign respectively from the input equation, and converting the equation into a mathematical algebraic formula.
And step B, subtracting the two target formulas to be compared, and calculating a result by utilizing simple and eval functions of the map. ( And (3) injection: for the numerical-free belt-type expression, direct eval calculation can obtain a algebraic expression or a algebraic expression, and the numerical-type expression is not the simplest result )
Step C, if the result is 0, the description formula is equivalent; if the formula is not 0, the formula is not equivalent.
In order to be able to process different types of formulas, covering diversified formulas types, step 103, performing formula equivalent modification on the classified formulas in the map format, and specifically includes: when the classified formula in the form of the map is not a basic mathematical formula, converting the classified formula in the form of the map into the basic mathematical formula; and adopting a basic equivalence correction algorithm to carry out formula equivalence correction.
In particular applications, for example: by classifying the formulas in the form of a map, it is possible to distinguish whether the formulas in the form of map belong to the basic mathematical formulas or to which type of formulas in the form of non-basic mathematical formulas.
When the classified formulas in the map format are not basic mathematical formulas, the formulas in the map formats of different types need to be converted into the basic mathematical formulas, and then the basic equivalent correction algorithm is adopted to carry out the equivalent correction of the formulas. Formula equivalence correction using a basic equivalence correction algorithm has been described in detail, and the conversion of different types of formulas in map format into basic mathematical formulas will be described below.
(1) Coordinate correction, the comma is rewritten with the plus and minus signs respectively. And converting the point coordinates into an addition type and a subtraction type, and judging that the two rewritten formulas are equivalent through a basic equivalent algorithm, so that the original coordinates are equivalent.
(2) Segment function correction: and extracting each section of function expression in the piecewise function, and respectively adopting a basic equivalence algorithm to correct, wherein if one expression is not equivalent, the whole piecewise function is not equivalent.
(3) And (3) angle correction, namely uniformly converting minutes and seconds into degrees, dividing the degrees by 60 and 3600 respectively, removing the degree marks, converting the degrees into numerical value equivalent comparison, and judging whether the degrees are equivalent by using a basic equivalent algorithm.
Referring to fig. 2-5, the automatic correction technical scheme of the junior middle school mathematical formula is explained by taking the handwriting answer pictures of the student 1, the student 2 and the student 3 as input, wherein the correct answer is。
Step one, input
Step two, latex2map, latex format to table format
Step three, formula error correction
Taking student 1 as an example, the formula in the form of a map of student 1 performs error correction processing.
Pre-error correction maple: (-0.5, a+6/5) post-error correction maple: (-0.5, a+b/5)
Step four, formula classification
Formulas in the map format for student 1, student 2, and student 3 are classified into point coordinates.
Step five, equivalent correction of point coordinates
Taking student 1 as an example, firstly carrying out formula equivalent modification on a formula in a map format before error correction, and if the generated result is correct, outputting a modification result and ending the flow. And if the generated result is an error or null value, carrying out formula equivalent correction on the formula in the corrected map format, and outputting a correction result.
(1) The formula of the map format before error correction of student 1 is converted into a basic mathematical formula.
(2) And (3) carrying out formula equivalent correction on the formula in the form of the map before error correction of the student 1 by adopting a basic equivalent correction algorithm, and outputting a result 0 to indicate that the answer is wrong.
(3) The formula in corrected map format for student 1 is converted into a basic mathematical formula.
(4) And (3) carrying out formula equivalent correction on the formula in the corrected map format of the student 1 by adopting a basic equivalent correction algorithm, and outputting a correct result to indicate that the answer is correct.
Another embodiment of the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method for automatically modifying a mathematical formula of a junior middle school when executing the computer program.
Another embodiment of the present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a method for automatically modifying a mathematical formula of a junior middle school.
Another embodiment of the present application provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of a method for automatically modifying a mathematical formula of a junior middle school.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
based on the hand-written answer picture, obtaining a formula in a map format; classifying the formulas in the map format; and carrying out formula equivalent correction on the classified formulas in the map format to generate correction results. The method of the application divides all junior middle school formulas into seven categories, classifies formulas in a form of a map, carries out different processing on formulas in different forms of map, generates correction results, can cover all junior middle school formula types including simple formulas or complex formulas, and can provide an automatic correction solution of a full link without manual intervention from handwriting answering of students to the whole process of generating correction results, thereby having high intelligent degree and greatly facilitating users.
Further, the obtaining a formula in a map format specifically includes: generating a formula in latex format based on the handwriting answer picture; and converting the latex format formula into a map format formula. The formula in the latex format can be converted into the formula in the multiple format, so that automatic correction can be conveniently performed by adopting a symbol computing system, and the method is simple and efficient.
Still further, before classifying the formula in the map format, further includes: and performing formula error correction on the formulas in the map format. Because the handwriting formula is not as standard as the printing body, the result identified from the handwriting answer picture can be wrong, and the fault tolerance can be increased by carrying out formula error correction on the formula in the form of a map, thereby being beneficial to improving the accuracy of the correction result.
Furthermore, formula error correction is performed on the formula in the map format, specifically: based on the correct answer, formula correction is performed on the formulas in the map format. Misjudgment of the recognition result in the handwriting answer picture, such as the lower case letter L of the number 1 which is recognized as L or the upper case letter I of the number I, cannot be judged in the process of formula error correction, and correct error correction can be realized by referring to the content of a correct answer. For example, the correct answer contains the capital letter I, the number 1 is modified into the capital letter I, so that the correction rate can be greatly corrected, and the accuracy of the correction result is further improved.
Still further, after performing formula correction on the formula in the map format, the method further includes: performing formula equivalence correction by using a formula in a map format before error correction; when the correction result is an error or null value, the formula of the corrected map format is used for formula equivalent correction. When the correction result of the formula equivalent correction using the map format before correction is correct, the formula correction is described as unnecessary operation, and the correction result is directly output. And when the correction result is wrong, the formula of the corrected map format can be used for carrying out formula equivalent correction, so that the error rate of the correction result can be reduced, misjudgment under the condition of no correction is avoided, and the accuracy of the correction result is improved. In addition, when the correction result is a null value, the automatic correction process is described as a problem, and the formula error correction processing can be performed on the formula in the form of a map, so that the input accuracy is improved, and the probability of subsequent errors of the system is reduced.
Still further, the classified formulas in the form of map are subjected to formula equivalent modification, specifically: when the classified formula in the map format is a basic mathematical formula, a basic equivalent correction algorithm is adopted to correct the formula. When the classified formula in the map format is a basic mathematical formula, the basic equivalent correction algorithm is directly adopted to correct the formula, so that correction efficiency can be improved.
Still further, the formula of the classified map format is subjected to formula equivalent modification, which specifically comprises: when the classified formula in the form of the map is not a basic mathematical formula, converting the classified formula in the form of the map into the basic mathematical formula; and adopting a basic equivalence correction algorithm to carry out formula equivalence correction. When the classified formula in the form of the map is not a basic mathematical formula, the classified formula in the form of the map is converted into the basic mathematical formula to carry out subsequent formula equivalent correction, so that different types of formulas can be processed, and diversified formula types can be covered.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. An automatic modification method for a junior middle school mathematical formula, which is characterized by comprising the following steps:
based on the hand-written answer picture, obtaining a formula in a map format;
classifying the formulas in the map format;
and carrying out formula equivalent correction on the classified formulas in the map format to generate correction results.
2. The method of claim 1, wherein the obtaining a formula in a map format specifically comprises:
generating a formula in latex format based on the handwriting answer picture;
and converting the formula in the latex format into the formula in the map format.
3. The method of claim 1, further comprising, prior to said classifying the formula in the map format:
and carrying out formula error correction on the formula in the map format.
4. The method of claim 3, wherein the performing formula correction on the formula in the map format is specifically:
and carrying out formula error correction on the formulas in the multiple format based on the correct answers.
5. The method of claim 3, further comprising, after said performing formula correction on said formulas in the map format:
performing formula equivalence correction by using a formula in a map format before error correction;
when the correction result is an error or null value, the formula of the corrected map format is used for formula equivalent correction.
6. The method of claim 1, wherein the formula equivalent modification is performed on the classified formula in the map format, specifically:
when the classified formula in the map format is a basic mathematical formula, a basic equivalent correction algorithm is adopted to correct the formula.
7. The method of claim 1, wherein the performing formula equivalence adaptation on the classified formula in the map format specifically comprises:
when the classified formula in the form of the map is not a basic mathematical formula, converting the classified formula in the form of the map into the basic mathematical formula;
and adopting a basic equivalence correction algorithm to carry out formula equivalence correction.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1-7 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1-7.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310416086.5A CN116798046B (en) | 2023-04-19 | 2023-04-19 | Automatic modification method, device, medium and program product for junior middle school mathematical formulas |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310416086.5A CN116798046B (en) | 2023-04-19 | 2023-04-19 | Automatic modification method, device, medium and program product for junior middle school mathematical formulas |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116798046A true CN116798046A (en) | 2023-09-22 |
| CN116798046B CN116798046B (en) | 2024-05-17 |
Family
ID=88042867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310416086.5A Active CN116798046B (en) | 2023-04-19 | 2023-04-19 | Automatic modification method, device, medium and program product for junior middle school mathematical formulas |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116798046B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096564A (en) * | 2016-06-17 | 2016-11-09 | 福建网龙计算机网络信息技术有限公司 | A kind of mathematics corrects method automatically |
| CN109271945A (en) * | 2018-09-27 | 2019-01-25 | 广东小天才科技有限公司 | Method and system for realizing job correction on line |
| CN110781681A (en) * | 2019-10-12 | 2020-02-11 | 电子科技大学 | Translation model-based elementary mathematic application problem automatic solving method and system |
| US20200090539A1 (en) * | 2018-08-13 | 2020-03-19 | Hangzhou Dana Technology Inc. | Method and system for intelligent identification and correction of questions |
| CN111753503A (en) * | 2020-06-19 | 2020-10-09 | 兰州大学 | Blind person oriented mathematical formula editing method and device |
| CN112732868A (en) * | 2020-12-30 | 2021-04-30 | 科大讯飞股份有限公司 | Answer analysis method for answers, electronic device and storage medium |
| CN113407675A (en) * | 2021-06-24 | 2021-09-17 | 作业帮教育科技（北京）有限公司 | Automatic education subject correcting method and device and electronic equipment |
| WO2022082988A1 (en) * | 2020-10-22 | 2022-04-28 | 深圳市鹰硕技术有限公司 | Automatic correction method and device for multi-subject homework |
| CN114863446A (en) * | 2022-05-24 | 2022-08-05 | 武汉天喻教育科技有限公司 | Handwritten answer recognition and comparison method, device, equipment and storage medium |
| CN114926853A (en) * | 2022-05-24 | 2022-08-19 | 科大讯飞股份有限公司 | Method, device, equipment and storage medium for correcting math questions |
| CN115080690A (en) * | 2022-06-17 | 2022-09-20 | 瀚云瑞科技(北京)有限公司 | NLP-based automatic correction method and system for test paper text |
| CN115203441A (en) * | 2022-09-19 | 2022-10-18 | 江西风向标智能科技有限公司 | Method, system, storage medium and equipment for analyzing high school mathematical formula |
| CN115346221A (en) * | 2022-07-05 | 2022-11-15 | 东南大学 | Deep learning-based mathematical formula recognition and automatic correction method for pupils |
| CN115661836A (en) * | 2022-11-08 | 2023-01-31 | 太保科技有限公司 | Automatic correction method, device and system and readable storage medium |
-
2023
- 2023-04-19 CN CN202310416086.5A patent/CN116798046B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096564A (en) * | 2016-06-17 | 2016-11-09 | 福建网龙计算机网络信息技术有限公司 | A kind of mathematics corrects method automatically |
| US20200090539A1 (en) * | 2018-08-13 | 2020-03-19 | Hangzhou Dana Technology Inc. | Method and system for intelligent identification and correction of questions |
| CN109271945A (en) * | 2018-09-27 | 2019-01-25 | 广东小天才科技有限公司 | Method and system for realizing job correction on line |
| CN110781681A (en) * | 2019-10-12 | 2020-02-11 | 电子科技大学 | Translation model-based elementary mathematic application problem automatic solving method and system |
| CN111753503A (en) * | 2020-06-19 | 2020-10-09 | 兰州大学 | Blind person oriented mathematical formula editing method and device |
| WO2022082988A1 (en) * | 2020-10-22 | 2022-04-28 | 深圳市鹰硕技术有限公司 | Automatic correction method and device for multi-subject homework |
| CN112732868A (en) * | 2020-12-30 | 2021-04-30 | 科大讯飞股份有限公司 | Answer analysis method for answers, electronic device and storage medium |
| CN113407675A (en) * | 2021-06-24 | 2021-09-17 | 作业帮教育科技（北京）有限公司 | Automatic education subject correcting method and device and electronic equipment |
| CN114863446A (en) * | 2022-05-24 | 2022-08-05 | 武汉天喻教育科技有限公司 | Handwritten answer recognition and comparison method, device, equipment and storage medium |
| CN114926853A (en) * | 2022-05-24 | 2022-08-19 | 科大讯飞股份有限公司 | Method, device, equipment and storage medium for correcting math questions |
| CN115080690A (en) * | 2022-06-17 | 2022-09-20 | 瀚云瑞科技(北京)有限公司 | NLP-based automatic correction method and system for test paper text |
| CN115346221A (en) * | 2022-07-05 | 2022-11-15 | 东南大学 | Deep learning-based mathematical formula recognition and automatic correction method for pupils |
| CN115203441A (en) * | 2022-09-19 | 2022-10-18 | 江西风向标智能科技有限公司 | Method, system, storage medium and equipment for analyzing high school mathematical formula |
| CN115661836A (en) * | 2022-11-08 | 2023-01-31 | 太保科技有限公司 | Automatic correction method, device and system and readable storage medium |
Non-Patent Citations (4)
| Title |
|---|
| CHI-SING MAN: "Crystallographic Texture and Group Representations", 《 JOURNAL OF ELASTICITY》, 5 July 2022 (2022-07-05), pages 196 - 198 * |
| 吴学栋，祖彬，王忠良: "《计算机在轻化工程中的应用》", 东北林业大学出版社, pages: 196 - 198 * |
| 吴艳;: "初中数学作业批改方式亟需创新", 中国新通信, no. 01, 5 January 2020 (2020-01-05), pages 217 * |
| 曾芳华;: "智慧教室在高等数学教学测评中的应用探究", 邢台职业技术学院学报, no. 03, 28 June 2018 (2018-06-28), pages 26 - 28 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116798046B (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mahdavi et al. | ICDAR 2019 CROHME+ TFD: Competition on recognition of handwritten mathematical expressions and typeset formula detection | |
| EP3660733B1 (en) | Method and system for information extraction from document images using conversational interface and database querying | |
| CN106980856B (en) | Formula identification method and system and symbolic reasoning calculation method and system | |
| CN110751137A (en) | Method and system for automatically solving mathematical problem | |
| CN104268603A (en) | Intelligent marking method and system for text objective questions | |
| CN109961146A (en) | Mathematical problem answers method and device | |
| JP7088661B2 (en) | Paper form data conversion system, OCR engine learning image generator and image analyzer | |
| Pacha et al. | Towards self-learning optical music recognition | |
| CN113255331B (en) | Text error correction method, device and storage medium | |
| CN113177435A (en) | Test paper analysis method and device, storage medium and electronic equipment | |
| CN115565179A (en) | Method, system and device for correcting errors after character recognition | |
| CN115661836A (en) | Automatic correction method, device and system and readable storage medium | |
| CN117746078B (en) | Object detection method and system based on user-defined category | |
| CN112508966B (en) | Interactive image segmentation method and system | |
| CN116798046B (en) | Automatic modification method, device, medium and program product for junior middle school mathematical formulas | |
| CN115984875B (en) | Stroke similarity evaluation method and system for hard-tipped pen regular script copy work | |
| Hajihashemi et al. | A pattern recognition based Holographic Graph Neuron for Persian alphabet recognition | |
| CN110929013A (en) | Image question-answer implementation method based on bottom-up entry and positioning information fusion | |
| CN116704508A (en) | Information processing method and device | |
| CN110728321A (en) | Training method and device for recognizing fractional image, and recognition method and device | |
| Choudhary et al. | Offline handwritten mathematical expression evaluator using convolutional neural network | |
| CN115761235A (en) | Zero sample semantic segmentation method, system, equipment and medium based on knowledge distillation | |
| Chaowicharat et al. | A step toward an automatic handwritten homework grading system for mathematics | |
| CN115359486A (en) | Method and system for determining custom information in document image | |
| CN115346221A (en) | Deep learning-based mathematical formula recognition and automatic correction method for pupils |
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 |