Application question correction method, device, storage medium and electronic device

By obtaining students' answer information, preprocessing and binary tree traversal operations, verifying calculation errors in the expression sequence, and matching them with the standard sequence, the problem of inefficiency in traditional manual correction is solved, and automatic correction of mathematical application questions is realized. Reduces costs and improves accuracy.

CN114722245BActive Publication Date: 2024-12-13BEIJING KANSHI HIGH-TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210314721.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-28
Publication Date
2024-12-13
Estimated Expiration
2042-03-28

AI Technical Summary

Technical Problem

The traditional way of relying on teachers to manually correct math application questions cannot meet the needs of modern online learning, especially when the number of students far exceeds that of teachers, which is inefficient and costly.

Method used

By obtaining students' answer information, preprocessing and binary tree traversal operations, verifying calculation errors in the expression sequence, and matching them with the standard sequence, automatic correction is achieved.

Benefits of technology

It realizes automatic correction of mathematical application problems, improves efficiency, reduces labor costs, and improves the accuracy and efficiency of correction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114722245B_ABST
    Figure CN114722245B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a method, device, storage medium and electronic device for correcting application questions, belonging to the field of education, and the method comprises: obtaining answer information of students for target questions; preprocessing the answer information to determine the expression sequence corresponding to each step in the answer information; verifying each expression in the expression sequence based on a binary tree and traversal operation to determine whether there is a calculation error step in the expression sequence; if there is no calculation error step in the expression sequence, matching the expression sequence with the standard sequence corresponding to the target question, and determining whether the student has answered correctly according to the matching result. Automatic correction of mathematical application questions is realized, which effectively improves efficiency and reduces labor costs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of education, and in particular, to a method, device, storage medium and electronic device for correcting application questions. Background Art

[0002] With the continuous development and progress of computer technology and data processing technology, more and more learning basically relies on the Internet for online learning, and the number of students usually far exceeds the number of teachers. Therefore, the traditional method of relying on teachers to manually correct mathematical word problems cannot meet the needs of modern online learning. Summary of the invention

[0003] In order to solve the problems existing in the related art, the present disclosure provides a method, device, storage medium and electronic device for correcting application questions.

[0004] In order to achieve the above-mentioned purpose, the present disclosure provides a method for correcting application questions in a first aspect, the method comprising:

[0005] Obtaining students' answer information for target questions;

[0006] Preprocessing the answer information to determine an expression sequence corresponding to each step in the answer information;

[0007] Verify each expression in the expression sequence based on the binary tree and traversal operation to determine whether there is a calculation error step in the expression sequence;

[0008] In the case where there are no calculation errors in the expression sequence, the expression sequence is matched with the standard sequence corresponding to the target question, and whether the student's answer is correct is determined based on the matching result.

[0009] Optionally, the step of checking each expression in the expression sequence based on the binary tree and the traversal operation to determine whether there is a calculation error in the expression sequence includes:

[0010] For the first expression in the expression sequence, construct a binary tree and perform post-root traversal to obtain a suffix expression, wherein the first expression is any expression in the expression sequence;

[0011] Perform symbol segmentation on the suffix expression to obtain an element list;

[0012] Perform a traversal operation on the element list, the traversal operation comprising:

[0013] In the case where it is determined that the first element currently traversed is an operand, determining whether the last two elements of the first element are the operand and the operator in sequence;

[0014] In the case where it is determined that the last two elements of the first element are not an operand and an operator in sequence, putting the first element into a recursive list;

[0015] When it is determined that the last two elements of the first element are an operand and an operator in sequence, a recursive element is calculated based on the first element and the last two elements, and the recursive element is added to the recursive list, and the traversal index skips the last two elements;

[0016] After determining that the traversal of the elements in the element list is completed, performing the traversal operation on the recursive list until the recursive list contains only one target element, and determining that the target element is the target calculation result of the current expression;

[0017] Determine whether the first expression is a calculation error step based on the target calculation result and the calculation result corresponding to the first expression in the answer information.

[0018] Optionally, matching the expression sequence with a standard sequence corresponding to the target question, and determining whether the student has answered correctly according to the matching result includes:

[0019] For a first expression in the expression sequence, determine a second expression in the standard sequence corresponding to the first expression, wherein the first expression is any expression in the expression sequence;

[0020] Comparing the first expression with the second expression, and determining character elements that do not match between the first expression and the second expression;

[0021] The edit distance between the character element and each error type label is calculated to determine the error type corresponding to the first expression.

[0022] Optionally, matching the expression sequence with a standard sequence corresponding to the target question, and determining whether the student has answered correctly according to the matching result includes:

[0023] For the last third expression in the expression sequence, determine a fourth expression in the standard sequence corresponding to the third expression;

[0024] Determine a key string according to the fourth expression;

[0025] For each of the key character strings, if there is a character string matching the key character string in the third expression, it is determined that the third expression is correct.

[0026] Optionally, the preprocessing of the answer information includes:

[0027] Convert the full-width symbols in the answer information into half-width symbols;

[0028] Convert all brackets and curly brackets in the expression to parentheses.

[0029] Optionally, before verifying each expression in the expression sequence based on the binary tree and the traversal operation, the method further includes:

[0030] Based on the regular expression, determine whether the expression corresponding to each step conforms to the mathematical syntax.

[0031] A second aspect of the present disclosure provides a device for correcting application questions, the device comprising:

[0032] An acquisition module is used to obtain the answer information of the students for the target questions;

[0033] A preprocessing module, used to preprocess the answer information and determine the expression sequence corresponding to each step in the answer information;

[0034] A first judgment module is used to check each expression in the expression sequence based on a binary tree and a traversal operation to determine whether there is a calculation error step in the expression sequence;

[0035] The second judgment module is used to match the expression sequence with the standard sequence corresponding to the target question when there is no calculation error step in the expression sequence, and determine whether the student's answer is correct based on the matching result.

[0036] Optionally, the first determination module is specifically configured to:

[0037] For the first expression in the expression sequence, construct a binary tree and perform post-root traversal to obtain a suffix expression, wherein the first expression is any expression in the expression sequence;

[0038] Perform symbol segmentation on the suffix expression to obtain an element list;

[0039] Perform a traversal operation on the element list, the traversal operation comprising:

[0040] In the case where it is determined that the first element currently traversed is an operand, determining whether the last two elements of the first element are the operand and the operator in sequence;

[0041] In the case where it is determined that the last two elements of the first element are not an operand and an operator in sequence, putting the first element into a recursive list;

[0042] When it is determined that the last two elements of the first element are an operand and an operator in sequence, a recursive element is calculated based on the first element and the last two elements, and the recursive element is added to the recursive list, and the traversal index skips the last two elements;

[0043] After determining that the traversal of the elements in the element list is completed, performing the traversal operation on the recursive list until the recursive list contains only one target element, and determining that the target element is the target calculation result of the current expression;

[0044] Determine whether the first expression is a calculation error step based on the target calculation result and the calculation result corresponding to the first expression in the answer information.

[0045] A third aspect of the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect of the present disclosure.

[0046] A fourth aspect of the present disclosure provides an electronic device, including:

[0047] a memory having a computer program stored thereon;

[0048] A processor is used to execute the computer program in the memory to implement the steps of any one of the methods described in the first aspect of the present disclosure.

[0049] Through the above technical solution, by pre-processing the answering process, and then determining whether the expressions in the expression sequence are correct through a binary tree, and comparing them with the key steps of the standard answer, the answer correction results are fed back to achieve automatic correction of mathematical word problems, which effectively improves efficiency and reduces labor costs.

[0050] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0052] Figure 1 is a flow chart showing a method for correcting application questions according to an exemplary embodiment;

[0053] Figure 2 is another flow chart showing a method for correcting application questions according to an exemplary embodiment;

[0054] Figure 3is a flow chart of a method for judging an expression calculation error according to an exemplary embodiment;

[0055] Figure 4 is a block diagram of a device for correcting application questions according to an exemplary embodiment;

[0056] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment;

[0057] Figure 6 is another block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0058] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0059] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0060] Figure 1 is a flow chart of a method for correcting application questions according to an exemplary embodiment. The method can be applied to electronic devices such as computers and mobile phones that have information data processing capabilities, such as Figure 1 As shown, the method includes:

[0061] S101. Obtaining answer information of students for target questions.

[0062] The answer information can be obtained by the student answering the target question on his / her personal computer, uploading the answer to the target server through the network, and then obtaining it through the target server.

[0063] S102: pre-process the answer information to determine an expression sequence corresponding to each step in the answer information.

[0064] In some embodiments, the preprocessing of the answer information includes: converting full-width symbols in the answer information into half-width symbols; and converting square brackets and curly brackets in expressions into small brackets.

[0065] For example, if the answer information includes the step {[1*2+(2*3) / 5}]-3}, then through preprocessing, an expression after preprocessing can be obtained, namely ((1*2+(2*3) / 5)-3).

[0066] Optionally, before executing step S102, the method may further include: determining whether the answer information is empty, and if not, executing step S102. If it is empty, returning a prompt message of "no answer" and stopping the grading process.

[0067] S103, verify each expression in the expression sequence based on the binary tree and traversal operation to determine whether there is a calculation error step in the expression sequence.

[0068] In some possible implementations, before executing step S103, the method further includes: determining whether the expression corresponding to each step conforms to mathematical syntax based on a regular expression.

[0069] For example, if the student's answer information after preprocessing is [120 / 2=60 (meters), 'Answer: The first section of the rope is 60 meters long.'], then the steps "120 / 2=60 (meters)" and "Answer: The first section of the rope is 60 meters long." can be checked by regular expressions. If the expressions corresponding to each step conform to the mathematical syntax, step S103 is executed. If it does not conform to the syntax, the prompt message "The expression in line X does not conform to the syntax" can be returned.

[0070] S104. When there is no calculation error step in the expression sequence, the expression sequence is matched with the standard sequence corresponding to the target question, and whether the student's answer is correct is determined based on the matching result.

[0071] Specifically, in some embodiments, matching the expression sequence with the standard sequence corresponding to the target question, and determining whether the student has answered correctly according to the matching result includes:

[0072] For the last third expression in the expression sequence, determine a fourth expression in the standard sequence corresponding to the third expression;

[0073] Determine a key string according to the fourth expression;

[0074] For each of the key character strings, if there is a character string matching the key character string in the third expression, it is determined that the third expression is correct.

[0075] The standard sequence is a pre-stored standard answer corresponding to the target question. It is understandable that there may be multiple standard sequences for the same target question.

[0076] For example, if the expression sequence is [120 / 2=60 (meters), 'Answer: The first section of the rope is 60 meters long.'], then the third expression "Answer: The first section of the rope is 60 meters long." can be obtained. If the key character strings corresponding to the fourth expression include "Answer:", "first section", "60 meters / 60m", then it can be determined that for each key character string of the fourth expression, there is a character string in the third expression that matches the key character string, and the third expression can be determined to be correct.

[0077] Alternatively, if the third expression is "The first section of rope is 60 meters long.", it cannot match the key string "Answer:", which means that the third expression is incorrect and the prompt message "The answering process is incomplete and the answer is missing" is returned.

[0078] In the disclosed embodiment, by preprocessing the answering process, determining whether the expressions in the expression sequence are correct through a binary tree, and comparing them with the key steps of the standard answer, the answer correction results are fed back to achieve automatic correction of mathematical word problems, which effectively improves efficiency and reduces labor costs.

[0079] In some optional embodiments, the step of checking each expression in the expression sequence based on the binary tree and the traversal operation to determine whether there is a calculation error in the expression sequence includes:

[0080] For the first expression in the expression sequence, construct a binary tree and perform post-root traversal to obtain a suffix expression, wherein the first expression is any expression in the expression sequence;

[0081] Perform symbol segmentation on the suffix expression to obtain an element list;

[0082] Perform a traversal operation on the element list, the traversal operation comprising:

[0083] In the case where it is determined that the first element currently traversed is an operand, determining whether the last two elements of the first element are the operand and the operator in sequence;

[0084] In the case where it is determined that the last two elements of the first element are not an operand and an operator in sequence, putting the first element into a recursive list;

[0085] When it is determined that the last two elements of the first element are an operand and an operator in sequence, a recursive element is calculated based on the first element and the last two elements, and the recursive element is added to the recursive list, and the traversal index skips the last two elements;

[0086] After determining that the traversal of the elements in the element list is completed, performing the traversal operation on the recursive list until the recursive list contains only one target element, and determining that the target element is the target calculation result of the current expression;

[0087] Determine whether the first expression is a calculation error step based on the target calculation result and the calculation result corresponding to the first expression in the answer information.

[0088] For example, if the first expression is "1*(2+3)-(1*2)", the suffix expression obtained by constructing a binary tree and performing postroot traversal is "1#2#3#+#*#1#2*#1#3#*#+#-". After symbol segmentation by "#", the element list can be obtained: ['1','2','3','+','*','1','2','*','1','3','*','+','-']. Based on the element list, a traversal operation is performed. If the traversal index points to the first element '1', '1' is the operand, and the next two elements of the element are '2' and '3' respectively, which do not meet the conditions of being operands and operators in sequence. Therefore, the element '1' can be put into the recursive list as the first element of the recursive list. If the traversal index points to the second element '2' in the element list, '2' is the operand, and the next two elements of the element are '3' and '+', which satisfy the conditions of operand and operator respectively. Therefore, 2+3 is calculated to obtain the recursive element '5', and the recursive element '5' is put into the recursive list as the second element of the recursive list.

[0089] After the traversal of the element list is completed, the recursive list ['1','5','*','2','3','+','-'] can be obtained, and the above traversal operation is performed on the recursive list to obtain the updated recursive list ['5','5','-']. After traversing the recursive list, the recursive list ['0'] containing one element can be obtained. In other words, the calculation result of the expression is 0. By comparing the calculation result with the calculation result in the answer information, if the calculation result of the expression answered by the student in the answer information is 8, it can be determined that the expression is calculated incorrectly. This step is a calculation error step. The prompt message "Calculation error on line x" is returned and the grading process is stopped.

[0090] Those skilled in the art should understand that, in the related art, the calculation of a mathematical expression requires obtaining the calculation result by alternately operating two stacks (an operator stack and an operand stack), firstly obtaining the suffix expression of the expression through an operator stack, and then obtaining the calculation result by operating on the suffix expression through the operand stack.

[0091] With the above scheme, the suffix expression is first obtained by constructing a binary tree of the expression, and then the suffix expression elements are stored in a list, and recursive calculation operations are applied to the list to obtain the calculation results. There is no need to use stack operations multiple times, which improves efficiency.

[0092] In some further optional embodiments, matching the expression sequence with the standard sequence corresponding to the target question, and determining whether the student has answered correctly according to the matching result comprises:

[0093] For a first expression in the expression sequence, determine a second expression in the standard sequence corresponding to the first expression, wherein the first expression is any expression in the expression sequence;

[0094] Comparing the first expression with the second expression, and determining character elements that do not match between the first expression and the second expression;

[0095] The edit distance between the character element and each error type label is calculated to determine the error type corresponding to the first expression.

[0096] Those skilled in the art should know that the edit distance refers to the minimum number of steps required to transform one string into another. The smaller the number of steps, the more similar the two strings are. This solution calculates the edit distance between the unmatched elements and each error annotation. The error annotation corresponding to the minimum edit distance is the most likely error, such as "unit error", "error in understanding the question stem", "error in understanding the concept", etc.

[0097] For example, if the first expression includes "20 meters" and the second expression includes "20 kilometers", it can be obtained that the character element "meter" in the first expression does not match the "kilometer" in the second expression, and based on the edit distance, it is determined that there is an error "unit error" in this step, and a prompt message of "unit error" can be returned to the student. If the first expression includes "30+20" and the second expression includes "30-20", it can be obtained that the character element "+" in the first expression does not match the "-" in the second expression, and it can be determined that the first expression may have a "misunderstanding of the question stem".

[0098] In the disclosed embodiment, by matching strings and calculating the edit distance between two strings, the error type of the steps in the answer information given by the student can be accurately determined based on the edit distance, thereby effectively improving the accuracy of marking.

[0099] For example, based on the steps in the above method, if the question content is "A rope is originally 100 meters long. After being divided into two sections, the first section is 20 meters longer than the second section. How long is the first section of the rope?", the specific judgment and correction can be as follows:

[0100] The students' answer is: [100+20=120 (meters), 120 / 2=60 (meters), 'Answer: The first section of rope is 60 meters long. '].

[0101] The answer process list obtained by analysis, that is, the expression list is: [100+20=120(meters), 120 / 2=60(meters), 'Answer: The first section of rope is 60 meters long.'].

[0102] Judging the answering process:

[0103] (1) After judgment, the answer process list is not empty and there is an answer process;

[0104] (2) After verification, the expression conforms to mathematical grammar;

[0105] (3) After inspection, the calculations of "100+20=120 (meters)" and "120 / 2=60 (meters)" are correct;

[0106] (4) After matching with the standard answer, the expression and units are correct;

[0107] (5) It successfully matches the key contents of the standard answer “Answer:”, “first paragraph”, and “60m / 60 meters”, and returns the correction result: the answer is correct.

[0108] In order to make those skilled in the art more understand the overall concept of the present disclosure, the present disclosure also provides the following Figure 2 The flowchart of a method for correcting application questions according to an exemplary embodiment is shown in FIG. Figure 2 As shown, the method comprises the steps of:

[0109] S201. Determine the content of the student's answer.

[0110] S202: Determine whether the answer content is empty.

[0111] If the answer content is empty, execute step S208; if it is not empty, execute step S203.

[0112] S203, pre-process the answer content to obtain an expression sequence.

[0113] S204: Determine whether the expressions in the expression list are grammatically correct.

[0114] If there is an expression in the expression list that does not conform to the syntax, execute step S209; if all expressions in the expression list conform to the syntax, execute step S205.

[0115] S205: Determine whether there is an expression calculation error in the expression list.

[0116] If there is an expression calculation error in the expression list, execute step S210; if there is no expression calculation error in the expression list, execute step S206.

[0117] S206: Determine whether there is an expression in the expression list that does not match the expression in the standard list.

[0118] If there is an expression in the expression list that does not match the expression in the standard list, execute step S211; if the expression in the expression list matches the expression in the standard list, execute step S207.

[0119] S207. Return the correction result "correct answer".

[0120] S208. Return the correction result "Not answered".

[0121] S209. Return the correction result "The expression in line x does not conform to the syntax".

[0122] S210. Return the correction result "Calculation error in row x".

[0123] S211. Return the correction result "the answering process is incomplete and the answer is missing".

[0124] It should be understood that the above-mentioned x can be determined according to step S209 and step S210, and the correction result "incomplete answering process, missing answer" returned in step S211 only provides an exemplary result, and the specific correction result can be determined according to the matching result in S206, for example, it can also be "unit error", "concept understanding error", "question stem understanding error", etc.

[0125] Further, based on the above step S205, the present disclosure also provides the following Figure 3 The flowchart of a method for judging an expression calculation error according to an exemplary embodiment is shown in FIG. Figure 3 As shown, the method comprises the steps of:

[0126] S301. Construct a binary tree for the first expression and perform post-root traversal to obtain a suffix expression.

[0127] S302. Obtain elements through character segmentation and store them in an element list.

[0128] S303: Determine whether the first element currently traversed is an operand.

[0129] If the currently traversed element is not an operand, execute step S304; if so, execute step S305.

[0130] S304, put into the recursive list.

[0131] S305. Determine whether the last two elements of the first element are an operand and an operator respectively.

[0132] If the last two elements are an operand and an operator in sequence, then execute step S306 and step S303 ; if the last two elements are not an operand and an operator in sequence, then execute step S307 .

[0133] S306 , after calculating the first element and the two elements following the first element, put them into the recursive list, and point the traversal index to the third element following the first element.

[0134] S307: Determine whether the traversal is completed.

[0135] If the traversal is completed, step S308 is executed; if the traversal is not completed, step S309 and step S303 are executed.

[0136] S308. Determine whether the recursive list contains only one element.

[0137] If the recursive list contains only one element, execute step S310; if it contains multiple elements, execute steps S311 and S303.

[0138] S309. Point the traversal index to the first element after the first element.

[0139] That is, after executing step S309, the first element after the first element is the updated first element.

[0140] S310. Determine whether the first expression is a calculation error step based on the values ​​of the elements in the recursive list and the calculation results corresponding to the first expression in the answer information.

[0141] S311. Point the traversal index to the first element in the recursive list.

[0142] At this time, the first element is the first element in the recursive list, and the recursive list is traversed.

[0143] Based on the same inventive concept, Figure 4 is a block diagram of a device 40 for correcting application questions according to an exemplary embodiment. Figure 4 As shown, the device comprises:

[0144] The acquisition module 41 is used to obtain the answer information of the student for the target question;

[0145] A preprocessing module 42, used to preprocess the answer information and determine the expression sequence corresponding to each step in the answer information;

[0146] A first judgment module 43 is used to check each expression in the expression sequence based on a binary tree and a traversal operation to determine whether there is a calculation error step in the expression sequence;

[0147] The second judgment module 44 is used to match the expression sequence with the standard sequence corresponding to the target question when there is no calculation error step in the expression sequence, and determine whether the student's answer is correct based on the matching result.

[0148] Optionally, the first determining module 43 is specifically configured to:

[0149] For the first expression in the expression sequence, construct a binary tree and perform post-root traversal to obtain a suffix expression, wherein the first expression is any expression in the expression sequence;

[0150] Perform symbol segmentation on the suffix expression to obtain an element list;

[0151] Perform a traversal operation on the element list, the traversal operation comprising:

[0152] In the case where it is determined that the first element currently traversed is an operand, determining whether the last two elements of the first element are the operand and the operator in sequence;

[0153] In the case where it is determined that the last two elements of the first element are not an operand and an operator in sequence, putting the first element into a recursive list;

[0154] When it is determined that the last two elements of the first element are an operand and an operator in sequence, a recursive element is calculated based on the first element and the last two elements, and the recursive element is added to the recursive list, and the traversal index skips the last two elements;

[0155] After determining that the traversal of the elements in the element list is completed, performing the traversal operation on the recursive list until the recursive list contains only one target element, and determining that the target element is the target calculation result of the current expression;

[0156] Determine whether the first expression is a calculation error step based on the target calculation result and the calculation result corresponding to the first expression in the answer information.

[0157] Optionally, the second determining module 44 is specifically configured to:

[0158] For a first expression in the expression sequence, determine a second expression in the standard sequence corresponding to the first expression, wherein the first expression is any expression in the expression sequence;

[0159] Comparing the first expression with the second expression, and determining character elements that do not match between the first expression and the second expression;

[0160] The edit distance between the character element and each error type label is calculated to determine the error type corresponding to the first expression.

[0161] Optionally, the second determining module 44 is further configured to:

[0162] For the last third expression in the expression sequence, determine a fourth expression in the standard sequence corresponding to the third expression;

[0163] Determine a key string according to the fourth expression;

[0164] For each of the key character strings, if there is a character string matching the key character string in the third expression, it is determined that the third expression is correct.

[0165] Optionally, the preprocessing module 42 is specifically used for:

[0166] Convert the full-width symbols in the answer information into half-width symbols;

[0167] Convert all brackets and curly brackets in the expression to parentheses.

[0168] Optionally, the device 40 further includes:

[0169] The third judgment module is used to determine whether the expression corresponding to each step conforms to mathematical syntax based on regular expressions.

[0170] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0171] Figure 5 FIG. 5 is a block diagram of an electronic device 500 according to an exemplary embodiment. Figure 5 As shown, the electronic device 500 may include: a processor 501 and a memory 502. The electronic device 500 may also include one or more of a multimedia component 503, an input / output (I / O) interface 504, and a communication component 505.

[0172] The processor 501 is used to control the overall operation of the electronic device 500 to complete all or part of the steps in the above-mentioned application problem correction method. The memory 502 is used to store various types of data to support the operation of the electronic device 500. For example, these data may include instructions for any application or method used to operate on the electronic device 500, and application-related data, such as target questions, answer information of students, etc. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 503 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 502 or sent through the communication component 505. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 504 provides an interface between the processor 501 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 505 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0173] In an exemplary embodiment, the electronic device 500 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned application problem correction method.

[0174] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned word problem correction method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 502 including program instructions, and the above-mentioned program instructions can be executed by the processor 501 of the electronic device 500 to complete the above-mentioned word problem correction method.

[0175] Figure 6 6 is a block diagram of an electronic device 600 according to an exemplary embodiment. For example, the electronic device 600 may be provided as a server. Figure 6 The electronic device 600 includes a processor 622, which may be one or more, and a memory 632 for storing a computer program executable by the processor 622. The computer program stored in the memory 632 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 622 may be configured to execute the computer program to perform the above-mentioned application problem correction method.

[0176] In addition, the electronic device 600 may further include a power supply component 626 and a communication component 650. The power supply component 626 may be configured to perform power management of the electronic device 600, and the communication component 650 may be configured to implement communication of the electronic device 600, for example, wired or wireless communication. In addition, the electronic device 600 may further include an input / output (I / O) interface 658. The electronic device 600 may operate based on an operating system stored in the memory 632, such as Windows Server 2000. TM , Mac OSX TM , Unix TM , Linux TM etc.

[0177] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned word problem correction method are implemented. For example, the non-transitory computer-readable storage medium can be the above-mentioned memory 632 including program instructions, and the above-mentioned program instructions can be executed by the processor 622 of the electronic device 600 to complete the above-mentioned word problem correction method.

[0178] In another exemplary embodiment, a computer program product is provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the above-mentioned word problem correction method when executed by the programmable device.

[0179] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0180] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0181] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for correcting application questions, characterized in that: The method comprises: Obtaining students' answer information for target questions; Preprocessing the answer information to determine an expression sequence corresponding to each step in the answer information; Verify each expression in the expression sequence based on the binary tree and traversal operation to determine whether there is a calculation error step in the expression sequence; In the case where there is no calculation error step in the expression sequence, matching the expression sequence with the standard sequence corresponding to the target question, and determining whether the student's answer is correct according to the matching result; The step of checking each expression in the expression sequence based on the binary tree and the traversal operation to determine whether there is a calculation error in the expression sequence includes: For the first expression in the expression sequence, construct a binary tree and perform post-root traversal to obtain a suffix expression, wherein the first expression is any expression in the expression sequence; Perform symbol segmentation on the suffix expression to obtain an element list; Perform a traversal operation on the element list, the traversal operation comprising: In the case where it is determined that the first element currently traversed is an operand, determining whether the last two elements of the first element are the operand and the operator in sequence; In the case where it is determined that the last two elements of the first element are not an operand and an operator in sequence, putting the first element into a recursive list; When it is determined that the last two elements of the first element are an operand and an operator in sequence, a recursive element is calculated based on the first element and the last two elements, and the recursive element is added to the recursive list, and the traversal index skips the last two elements; After determining that the traversal of the elements in the element list is completed, performing the traversal operation on the recursive list until the recursive list contains only one target element, and determining that the target element is the target calculation result of the current expression; Determine whether the first expression is a calculation error step based on the target calculation result and the calculation result corresponding to the first expression in the answer information.

2. The method according to claim 1, characterized in that The matching of the expression sequence with the standard sequence corresponding to the target question and determining whether the student has answered correctly according to the matching result comprises: For a first expression in the expression sequence, determine a second expression in the standard sequence corresponding to the first expression, wherein the first expression is any expression in the expression sequence; Comparing the first expression with the second expression, and determining character elements that do not match between the first expression and the second expression; The edit distance between the character element and each error type label is calculated to determine the error type corresponding to the first expression.

3. The method according to claim 1, characterized in that: The matching of the expression sequence with the standard sequence corresponding to the target question and determining whether the student has answered correctly according to the matching result comprises: For the last third expression in the expression sequence, determine a fourth expression in the standard sequence corresponding to the third expression; Determine a key string according to the fourth expression; For each of the key character strings, if there is a character string matching the key character string in the third expression, it is determined that the third expression is correct.

4. The method according to any one of claims 1 to 3, characterized in that: The preprocessing of the answer information includes: Convert the full-width symbols in the answer information into half-width symbols; Convert all brackets and curly brackets in the expression to parentheses.

5. The method according to any one of claims 1 to 3, characterized in that: Before verifying each expression in the expression sequence based on the binary tree and the traversal operation, the method further includes: Based on the regular expression, determine whether the expression corresponding to each step conforms to the mathematical syntax.

6. A device for correcting application questions, characterized in that: The device comprises: An acquisition module is used to obtain the answer information of the students for the target questions; A preprocessing module, used to preprocess the answer information and determine the expression sequence corresponding to each step in the answer information; A first judgment module is used to check each expression in the expression sequence based on a binary tree and a traversal operation to determine whether there is a calculation error step in the expression sequence; A second judgment module is used to match the expression sequence with the standard sequence corresponding to the target question when there is no calculation error step in the expression sequence, and determine whether the student's answer is correct according to the matching result; The first judgment module is specifically used for: For the first expression in the expression sequence, construct a binary tree and perform post-root traversal to obtain a suffix expression, wherein the first expression is any expression in the expression sequence; Perform symbol segmentation on the suffix expression to obtain an element list; Perform a traversal operation on the element list, the traversal operation comprising: In the case where it is determined that the first element currently traversed is an operand, determining whether the last two elements of the first element are the operand and the operator in sequence; In the case where it is determined that the last two elements of the first element are not an operand and an operator in sequence, putting the first element into a recursive list; When it is determined that the last two elements of the first element are an operand and an operator in sequence, a recursive element is calculated based on the first element and the last two elements, and the recursive element is added to the recursive list, and the traversal index skips the last two elements; After determining that the traversal of the elements in the element list is completed, performing the traversal operation on the recursive list until the recursive list contains only one target element, and determining that the target element is the target calculation result of the current expression; Determine whether the first expression is a calculation error step based on the target calculation result and the calculation result corresponding to the first expression in the answer information.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 5 are implemented.

8. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 5.