CN111507096A - N L P identification method, device and terminal for teaching system - Google Patents
N L P identification method, device and terminal for teaching system Download PDFInfo
- Publication number
- CN111507096A CN111507096A CN201910088034.3A CN201910088034A CN111507096A CN 111507096 A CN111507096 A CN 111507096A CN 201910088034 A CN201910088034 A CN 201910088034A CN 111507096 A CN111507096 A CN 111507096A
- Authority
- CN
- China
- Prior art keywords
- calculation
- calculation error
- identification
- determining
- recognition
- 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
Images
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The embodiment of the application provides an N L P identification method, an N L P identification device and equipment/a terminal/a server for a teaching system, wherein the method comprises the steps of carrying out N L P identification processing on an obtained identification object once according to a pre-stored mathematical symbol table and an error comparison table, determining the position of a calculation error in the identification object, carrying out N L P identification processing on the position of the calculation error in the identification object twice according to a calculation mode, and determining the type of the calculation error.
Description
Technical Field
The application relates to the technical field of computers, in particular to an N L P identification method, an N L P identification device and a terminal for a teaching system.
Background
Natural language processing (N L P) is an important direction in the fields of computer science and artificial intelligence, which studies various theories and methods that enable efficient communication between a person and a computer using natural language.
The correction method in the existing teaching system can only know the wrong alignment of the questions and cannot know the thought of the wrong questions and where the wrong points are. Therefore, after the correction of the test paper is completed, the correction system in the electronic teaching still needs to evaluate the test paper in a manual mode, and the knowledge point condition which cannot be mastered by the student can be obtained according to the answer state of the student. The existing correction system in electronic teaching still has room for improvement.
Therefore, how to identify the answer to the question by using the N L P algorithm is an urgent technical problem to be solved in the prior art.
Disclosure of Invention
The embodiment of the application provides an N L P identification method and device for a teaching system, and a device/terminal/server, which are used for identifying answers to questions by using an N L P algorithm, acquiring reasons of wrong questions and improving electronic teaching.
According to one aspect of the embodiment of the application, the N L P recognition method for the teaching system is provided, and comprises the steps of carrying out N L P recognition processing on an obtained recognition object once according to a pre-stored mathematical symbol table and an error comparison table to determine the position of a calculation error in the recognition object, and carrying out N L P recognition processing on the position of the calculation error in the recognition object twice according to a calculation mode to determine the type of the calculation error.
According to another aspect of the embodiment of the application, the N L P recognition device for the teaching system comprises a position recognition module and a type recognition module, wherein the position recognition module is configured to perform N L P recognition processing on an acquired recognition object once according to a pre-stored mathematical symbol table and an error comparison table to determine the position of a calculation error in the recognition object, and the type recognition module is configured to perform N L P recognition processing on the position of the calculation error in the recognition object twice according to a calculation mode to determine the type of the calculation error.
According to still another aspect of the embodiments of the present application, there is also provided an apparatus/terminal/server, including one or more processors, and a storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement operations corresponding to the N L P recognition method for a teaching system as described above.
There is also provided, according to yet another aspect of embodiments of the present application, a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements operations corresponding to the N L P recognition method for teaching systems as described above.
According to the technical scheme provided by the embodiment of the application, the acquired identification object is subjected to primary N L P identification processing according to a prestored mathematical symbol table and an error comparison table, the position of a calculation error in the identification object is determined, and then secondary N L P identification processing is performed on the position of the calculation error in the identification object according to a calculation mode, and the type of the calculation error is determined.
Drawings
Fig. 1 is a flowchart illustrating steps of an N L P recognition method for a tutorial system according to a first embodiment of the present application;
FIG. 2a is a flowchart illustrating a step S101 of an N L P recognition method for a tutorial system according to the second embodiment of the present application;
FIG. 2b is a syntax tree of the arithmetic expression 10+5-6 exemplified in step S101 of another N L P recognition method for a tutorial system according to the second embodiment of the present application;
fig. 3 is a flowchart illustrating a step S102 of a further method for identifying N L P for a tutorial system according to a third embodiment of the present application;
fig. 4 is a block diagram of an N L P recognition apparatus for a teaching system according to a fourth embodiment of the present application;
fig. 5 is a block diagram of a location identification module of an N L P identification apparatus for teaching system according to an embodiment of the present application;
fig. 6 is a block diagram illustrating a configuration of a type recognition module of an N L P recognition apparatus for a tutorial system according to a seventh embodiment of the present invention;
fig. 7 is a block diagram of a terminal according to a ninth embodiment of the present application.
Detailed Description
The following detailed description of embodiments of the present application will be made in conjunction with the accompanying drawings (like numerals indicate like elements throughout the several views) and embodiments. The following examples are intended to illustrate the present application but are not intended to limit the scope of the present application.
It will be understood by those within the art that the terms "first", "second", etc. in the embodiments of the present application are used only for distinguishing between different steps, devices or modules, etc., and do not denote any particular technical or logical order therebetween.
Example one
Referring to fig. 1, a flowchart illustrating steps of an N L P identification method for a teaching system according to a first embodiment of the present application is shown.
It should be noted that steps S101 to S102 described in the present application do not represent the execution sequence.
The N L P identification method for the teaching system comprises the following steps:
and S101, carrying out N L P identification processing on the acquired identification object once according to a pre-stored mathematical symbol table and an error comparison table, and determining the position of a calculation error in the identification object.
Specifically, the mathematical symbol table and the error comparison table in the embodiment of the present application are collected manually or obtained by using a machine learning algorithm.
The identification object includes: the test paper, the homework, the practice problem, the answer and other contents of the electronic teaching contain the answer of the student.
The primary N L P identification processing utilizes the prestored mathematical symbol table and the error comparison table to identify student answers and judge the positions where the calculation errors occur compared with target answers.
And S102, performing secondary N L P recognition processing on the position where the calculation error occurs in the recognition object according to a calculation mode, and determining the type of the calculation error.
Specifically, after determining the position where the calculation error occurs, the embodiment of the present application performs secondary N L P recognition processing according to the calculation manner, and determines the type of the calculation error.
Therefore, according to the embodiment of the application, the answer is analyzed by utilizing the N L P algorithm, the wrong answer can be judged, and the reason of the wrong answer can also be judged.
The N L P recognition method for the tutoring system of the present embodiment may be performed by any suitable device having the N L P recognition capability for the tutoring system, including but not limited to various device terminals or servers, including but not limited to PCs, tablets, mobile terminals, etc.
Example two
The N L P recognition method for the tutorial system of the present embodiment includes the above-described steps S101 to S102.
Referring to fig. 2a, a flowchart of a step S101 of an N L P identification method for a tutorial system according to the second embodiment of the present application is shown.
It should be noted that steps S1011 to S1014 described herein do not represent the execution sequence.
Wherein the step S101 includes at least one of:
step S1011: and splitting the sentence in the identification object into a plurality of lexical units, and determining the lexical units with illegal meanings as the positions where the calculation errors occur.
In a specific implementation of the present application, step S1011 in the embodiment of the present application specifically is:
and splitting the sentence in the identification object into a plurality of lexical units, detecting the correctness of the words or/and the arithmetic expressions in the lexical units, and determining the lexical units with incorrect words or/and the arithmetic expressions as the positions where the calculation errors occur.
Therefore, the embodiment of the application determines the position where the calculation error occurs according to whether the word is legal or not by detecting the correctness of the word or/and the arithmetic expression in the lexical unit.
Step S1012: and determining the position where the grammar of the arithmetic expression in the recognition object is incorrect as the position where the calculation error occurs.
Specifically, step S1012 in this application specifically includes:
and generating a syntax tree from the arithmetic expression in the identification object, deducing a non-terminal symbol on a following node of the syntax tree, and determining the position of a calculation error according to a reverse expression.
For example, see FIG. 2b, syntax trees for arithmetic expressions 10+ 5-6. The leaf nodes of the syntax tree form the result of the tree from left to right, i.e. a string of symbols derived from the non-terminal symbols on the root node: 10+5-6.
Therefore, the syntactic analysis focuses on the derivation formula, and combines the words obtained from the lexical analysis according to the syntactic rules, so that the position where the calculation error occurs can be determined according to the derivation formula.
Step S1013: and determining the position where each inverted relation in the identification object is illegal as the position where the calculation error occurs.
Step S1014: and determining the position of the error output by the execution step according to the expression in the identification object as the position where the calculation error occurs.
Therefore, the position of the recognition object with the calculation error can be determined accurately and simply by determining the position of the recognition object with the calculation error through at least one of lexical analysis, syntactic analysis, semantic analysis and step-by-step execution analysis.
The N L P recognition method for the tutoring system of the present embodiment may be performed by any suitable device having the N L P recognition capability for the tutoring system, including but not limited to various device terminals or servers, including but not limited to PCs, tablets, mobile terminals, etc.
EXAMPLE III
The present embodiment includes the above steps S101 to S102. It should be noted that steps S1021 to S1022 described in the present application do not represent the execution sequence.
Referring to fig. 3, the step S102 includes:
step S1021: and determining the type of the possible calculation error according to the calculation mode of the position of the calculation error in the identification object.
The types of the calculation errors can be different due to the calculation mode, such as carry errors in addition, borrow errors in subtraction, and the like. Therefore, the type of the calculation error and the calculation method are associated, and the type of the calculation error can be obtained according to the possible calculation method.
In a specific implementation of the present application, the step S1021 in the embodiment of the present application includes:
and determining the bit number type of the possible calculation error according to the calculation bit number of the calculation formula of the position where the calculation error occurs in the identification object.
Specifically, the calculation error may be determined by using a calculation bit number of a calculation formula, for example, a calculation of multiplying a three-bit number by a one-bit number, and the type of the error should include: tail number error, carry in place causing ten bit error (including forgetting carry and adding error), carry in place causing hundred bit error (including forgetting carry and adding error), carry in place causing thousand bit error (including forgetting carry and adding error).
The step S1021 further includes:
the thinking of inertia and/or the exchange of numbers are taken as the kind of calculation error that may occur.
S1022, referring to the types of the calculation errors that may occur, sequentially determining the types to which the calculation errors belong.
Specifically, for example, a calculation of multiplying a three-digit number by a one-digit number is taken as an example:
the logic to detect the cause of the error is then as follows:
if the question stem conforms to the inertial thinking error mechanism, verifying whether the question stem is a similar group answer, and if so, returning the calculation error type as 'inertial thinking error'. If not, then verify whether there is a carry in the ones bit that results in a ten bit error.
And verifying whether the student answers are products after exchanging a plurality of big multiplying digits with a small multiplying digit, and if yes, returning the calculation error type to be 'digit exchange error'. If not, then verify whether there is a ten-bit carry that results in a hundred-bit error.
The student answers and the correct answers are compared from one place, and if 0 number is wrong, the type of the error is returned to be 'tail number wrong'. If the result is correct, whether the carry with hundreds of bits exists or not is verified to cause the error of thousands of bits.
And comparing the student answers with the correct answers from the units, and if the tens bit is wrong and the question stem conforms to the unit carry to cause the tens bit to be wrong, returning the calculation error type as 'the unit carry causes the tens bit to be wrong'. If the hundred bit is wrong and the question stem conforms to the ten-bit carry to cause the hundred bit to be wrong, returning the calculation error type as 'the ten-bit carry causes the hundred bit to be wrong'. If the thousand bits are wrong and the question stem conforms to the hundred bit carry, the thousand bits are wrong, and the type of the returned calculation error is 'the hundred bit carry causes the thousand bits to be wrong'.
According to the method and the device, the calculation errors are sequentially identified by using an N L P algorithm according to the calculation error types, and the calculation error types are determined.
The N L P recognition method for the tutoring system of the present embodiment may be performed by any suitable device having the N L P recognition capability for the tutoring system, including but not limited to various device terminals or servers, including but not limited to PCs, tablets, mobile terminals, etc.
Example four
Referring to fig. 4, a block diagram of an N L P recognition apparatus for a tutorial system according to a fourth embodiment of the present application is shown.
The N L P recognition device for teaching system of this embodiment includes:
and the position identification module 401 is configured to perform N L P identification processing on the acquired identification object once according to a pre-stored mathematical symbol table and an error comparison table, and determine a position where a calculation error occurs in the identification object.
And the type identification module 402 is configured to perform secondary N L P identification processing on the position where the calculation error occurs in the identification object according to a calculation mode, and determine the type of the calculation error.
Specifically, the mathematical symbol table and the error comparison table in the embodiment of the present application are collected manually or obtained by using a machine learning algorithm.
The identification object includes: the test paper, the homework, the practice problem, the answer and other contents of the electronic teaching contain the answer of the student.
The primary N L P identification processing utilizes the prestored mathematical symbol table and the error comparison table to identify student answers and judge the positions where the calculation errors occur compared with target answers.
Specifically, after determining the position where the calculation error occurs, the embodiment of the present application performs secondary N L P recognition processing according to the calculation manner, and determines the type of the calculation error.
Therefore, according to the embodiment of the application, the answer is analyzed by utilizing the N L P algorithm, the wrong answer can be judged, and the reason of the wrong answer can also be judged.
The N L P recognition method for the tutoring system of the present embodiment may be performed by any suitable device having the N L P recognition capability for the tutoring system, including but not limited to various device terminals or servers, including but not limited to PCs, tablets, mobile terminals, etc.
EXAMPLE five
The N L P identification method for the teaching system of the present embodiment includes the location identification module 401 and the type identification module 402.
Referring to fig. 5, a block diagram of a location identification module 401 of an N L P identification apparatus for a teaching system according to a fifth embodiment of the present application is shown.
Wherein the location identification module 401 includes at least one of the following:
a lexical identification unit 4011 configured to divide the sentence in the identification target into a plurality of lexical units, and determine a lexical unit in which there is an illegal lexical unit as a position where the calculation error occurs.
A syntax recognizing unit 4012 configured to determine a position where the syntax of the arithmetic expression in the recognition object is incorrect as a position where the calculation error occurs.
A semantic recognition unit 4013 configured to determine a position where each of the truncated relations in the recognition object is not legal as a position where the calculation error occurs.
An execution recognition unit 4014 configured to determine a position of the recognition object at which the error is output in accordance with the expression execution step as a position at which the calculation error occurs.
In a specific implementation of the present application, the lexical identification unit 4011 in this embodiment of the present application specifically includes:
and splitting the sentence in the identification object into a plurality of lexical units, detecting the correctness of the words or/and the arithmetic expressions in the lexical units, and determining the lexical units with incorrect words or/and the arithmetic expressions as the positions where the calculation errors occur.
Therefore, the embodiment of the application determines the position where the calculation error occurs according to whether the word is legal or not by detecting the correctness of the word or/and the arithmetic expression in the lexical unit.
Specifically, the grammar recognition unit 4012 in the present application specifically includes:
and generating a syntax tree from the arithmetic expression in the identification object, deducing a non-terminal symbol on a following node of the syntax tree, and determining the position of a calculation error according to a reverse expression.
For example, see FIG. 2b, syntax trees for arithmetic expressions 10+ 5-6. The leaf nodes of the syntax tree form the result of the tree from left to right, i.e. a string of symbols derived from the non-terminal symbols on the root node: 10+5-6.
Therefore, the syntactic analysis focuses on the derivation formula, and combines the words obtained from the lexical analysis according to the syntactic rules, so that the position where the calculation error occurs can be determined according to the derivation formula.
Therefore, the position of the recognition object with the calculation error can be determined accurately and simply by determining the position of the recognition object with the calculation error through at least one of lexical analysis, syntactic analysis, semantic analysis and step-by-step execution analysis.
The N L P recognition method for the tutoring system of the present embodiment may be performed by any suitable device having the N L P recognition capability for the tutoring system, including but not limited to various device terminals or servers, including but not limited to PCs, tablets, mobile terminals, etc.
EXAMPLE six
The embodiment includes the location identification module 401 and the type identification module 402.
Referring to fig. 6, the type identifying module 402 includes:
the category identifying unit 4021 is configured to determine a category of a calculation error that may occur, based on a calculation manner of a position where the calculation error occurs in the identification target.
The error identifying unit 4022 is configured to refer to the types of the calculation errors that may occur, and sequentially determine the types to which the calculation errors belong.
The types of the calculation errors can be different due to the calculation mode, such as carry errors in addition, borrow errors in subtraction, and the like. Therefore, the type of the calculation error and the calculation method are associated, and the type of the calculation error can be obtained according to the possible calculation method.
In a specific implementation of the present application, the category identifying unit 4021 in an embodiment of the present application is specifically configured to:
and determining the bit number type of the possible calculation error according to the calculation bit number of the calculation formula of the position where the calculation error occurs in the identification object.
Specifically, the calculation error may be determined by using a calculation bit number of a calculation formula, for example, a calculation of multiplying a three-bit number by a one-bit number, and the type of the error should include: tail number error, carry in place causing ten bit error (including forgetting carry and adding error), carry in place causing hundred bit error (including forgetting carry and adding error), carry in place causing thousand bit error (including forgetting carry and adding error).
The category identifying unit 4021 is further specifically configured to:
the thinking of inertia and/or the exchange of numbers are taken as the kind of calculation error that may occur.
Specifically, for example, a calculation of multiplying a three-digit number by a one-digit number is taken as an example:
the logic to detect the cause of the error is then as follows:
if the question stem conforms to the inertial thinking error mechanism, verifying whether the question stem is a similar group answer, and if so, returning the calculation error type as 'inertial thinking error'. If not, then verify whether there is a carry in the ones bit that results in a ten bit error.
And verifying whether the student answers are products after exchanging a plurality of big multiplying digits with a small multiplying digit, and if yes, returning the calculation error type to be 'digit exchange error'. If not, then verify whether there is a ten-bit carry that results in a hundred-bit error.
The student answers and the correct answers are compared from one place, and if 0 number is wrong, the type of the error is returned to be 'tail number wrong'. If the result is correct, whether the carry with hundreds of bits exists or not is verified to cause the error of thousands of bits.
And comparing the student answers with the correct answers from the units, and if the tens bit is wrong and the question stem conforms to the unit carry to cause the tens bit to be wrong, returning the calculation error type as 'the unit carry causes the tens bit to be wrong'. If the hundred bit is wrong and the question stem conforms to the ten-bit carry to cause the hundred bit to be wrong, returning the calculation error type as 'the ten-bit carry causes the hundred bit to be wrong'. If the thousand bits are wrong and the question stem conforms to the hundred bit carry, the thousand bits are wrong, and the type of the returned calculation error is 'the hundred bit carry causes the thousand bits to be wrong'.
According to the method and the device, the calculation errors are sequentially identified by using an N L P algorithm according to the calculation error types, and the calculation error types are determined.
The N L P recognition method for the tutoring system of the present embodiment may be performed by any suitable device having the N L P recognition capability for the tutoring system, including but not limited to various device terminals or servers, including but not limited to PCs, tablets, mobile terminals, etc.
EXAMPLE seven
Referring to fig. 7, a block diagram of a terminal according to a seventh embodiment of the present application is shown, where the specific embodiment of the present application does not limit a specific implementation of the terminal.
As shown in fig. 7, the device/terminal/server may include: one or more processors (processors) 702, and a storage device (memory) 704.
Wherein:
the processor 702, configured to execute the program 706, may specifically perform relevant steps in the above-described N L P recognition method embodiment for a teaching system.
In particular, the program 706 may include program code that includes computer operational instructions.
The processor 702 may be a central processing unit CPU, or an application specific Integrated circuit asic, or one or more Integrated circuits configured to implement embodiments of the present application. The one or more processors comprised by the device/terminal/server may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
Storage 704 for storing one or more programs 706. Storage 704 may include high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 706 may be specifically configured to enable the processor 702 to perform N L P recognition processing on the acquired identification object once according to a pre-stored mathematical symbol table and error comparison table to determine a position of the identification object where a calculation error occurs, and perform N L P recognition processing on the position of the identification object where the calculation error occurs twice according to a calculation manner to determine a type of the calculation error.
In an alternative embodiment, program 706 is further operable to perform one of the following: splitting the sentence in the identification object into a plurality of lexical units, and determining the lexical units with illegal meanings as positions where calculation errors occur; determining a position where the syntax of the arithmetic expression in the recognition object is incorrect as a position where a calculation error occurs; determining the position of each inverted relation in the identification object, which is illegal, as the position of the occurrence of the calculation error; and determining the position of the error output by the execution step according to the expression in the identification object as the position where the calculation error occurs.
In an alternative embodiment, the program 706 is further configured to split the sentence in the recognition object into a plurality of lexical units, detect correctness of the word or/and the arithmetic expression in the lexical unit, and determine the lexical unit in which the incorrect word or/and the arithmetic expression exist as the position where the calculation error occurs.
In an alternative embodiment, the program 706 is further configured to generate a syntax tree from the arithmetic expression in the identified object, derive the syntax tree from the non-terminal symbols at the following nodes of the syntax tree, and determine the position where the calculation error occurs according to a reciprocal formula.
In an alternative embodiment, the program 706 is further configured to determine a type of the calculation error that may occur according to a calculation manner of a position where the calculation error occurs in the identification object; and sequentially judging the type of the calculation error by referring to the types of the calculation errors which possibly occur.
In an alternative embodiment, program 706 is further configured to determine the number of bits of the calculation error that may occur according to the number of calculation bits of the calculation formula for identifying the location of the calculation error in the object.
In an alternative embodiment, the program 706 is also used to exchange the thoughts of inertia and/or numbers as the kind of computational error that may occur.
Therefore, according to the embodiment of the application, the answer is analyzed by utilizing the N L P algorithm, the wrong answer can be judged, and the reason of the wrong answer can also be judged.
It should be noted that, according to the implementation requirement, each component/step described in the embodiment of the present application may be divided into more components/steps, and two or more components/steps or partial operations of the components/steps may also be combined into a new component/step to achieve the purpose of the embodiment of the present application.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communication section XXX and/or installed from removable media XXX. The above-described functions defined in the method of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) XXX. It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including AN object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor comprises a receiving unit, an analyzing unit, an information selecting unit and a generating unit. Where the names of these elements do not in some cases constitute a limitation on the elements themselves, for example, a receiving element may also be described as an "element that receives a user's web browsing request".
As another aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method as described in any of the embodiments above.
The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to perform a primary N L P recognition process on the acquired identification object according to a pre-stored mathematical symbol table and error comparison table to determine a location of a calculation error in the identification object, and perform a secondary N L P recognition process on the location of the identification object where the calculation error occurs according to a calculation manner to determine a type of the calculation error.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (16)
1. An N L P recognition method for a tutorial system, the method comprising:
carrying out N L P identification processing on the obtained identification object once according to a pre-stored mathematical symbol table and an error comparison table, and determining the position of a calculation error in the identification object;
and performing secondary N L P recognition processing on the position where the calculation error occurs in the recognition object according to a calculation mode, and determining the type of the calculation error.
2. The method according to claim 1, wherein the N L P recognition process is performed on the obtained recognition object once according to a pre-stored mathematical symbol table and error comparison table, and the determination of the position of the recognition object where the calculation error occurs comprises at least one of the following:
splitting the sentence in the identification object into a plurality of lexical units, and determining the lexical units with illegal meanings as positions where calculation errors occur;
determining a position where the syntax of the arithmetic expression in the recognition object is incorrect as a position where a calculation error occurs;
determining the position of each inverted relation in the identification object, which is illegal, as the position of the occurrence of the calculation error;
and determining the position of the error output by the execution step according to the expression in the identification object as the position where the calculation error occurs.
3. The method according to claim 2, wherein the splitting of the sentence in the recognition object into a plurality of lexical units and the determining of the existence of the illegal lexical unit as the position where the calculation error occurs are specifically:
and splitting the sentence in the identification object into a plurality of lexical units, detecting the correctness of the words or/and the arithmetic expressions in the lexical units, and determining the lexical units with incorrect words or/and the arithmetic expressions as the positions where the calculation errors occur.
4. The method according to claim 2, wherein the determining of the position where the syntax of the arithmetic expression in the recognition object is incorrect as the position where the calculation error occurs is specifically:
and generating a syntax tree from the arithmetic expression in the identification object, deducing a non-terminal symbol on a following node of the syntax tree, and determining the position of a calculation error according to a reverse expression.
5. The method according to claim 1, wherein the performing a quadratic N L P recognition process on the position of the recognition object where the calculation error occurs according to the calculation mode, and the determining the type of the calculation error comprises:
determining the type of the possible calculation error according to the calculation mode of the position of the calculation error in the identification object;
and sequentially judging the type of the calculation error by referring to the types of the calculation errors which possibly occur.
6. The method of claim 5, wherein determining the type of the possible calculation error according to the calculation mode of the position of the calculation error in the identification object comprises:
and determining the bit number type of the possible calculation error according to the calculation bit number of the calculation formula of the position where the calculation error occurs in the identification object.
7. The method of claim 6, wherein determining the type of the possible calculation error according to the calculation mode of the position of the calculation error in the identification object further comprises:
the thinking of inertia and/or the exchange of numbers are taken as the kind of calculation error that may occur.
8. An N L P recognition apparatus for use in a teaching system, the apparatus comprising:
the position identification module is configured to perform N L P identification processing on the acquired identification object once according to a pre-stored mathematical symbol table and an error comparison table, and determine the position of a calculation error in the identification object;
and the type identification module is configured to perform secondary N L P identification processing on the position where the calculation error occurs in the identification object according to a calculation mode, and determine the type of the calculation error.
9. The apparatus of claim 8, wherein the location identification module comprises at least one of:
a lexical identification unit configured to split a sentence in the identification object into a plurality of lexical units, and determine an illegal lexical unit as a position where a calculation error occurs;
a syntax recognition unit configured to determine a position where the syntax of the arithmetic expression in the recognition object is incorrect as a position where a calculation error occurs;
a semantic recognition unit configured to determine a position where each of the truncated relations in the recognition object is not legal as a position where a calculation error occurs;
and the execution identification unit is configured to determine the position of the error output by the execution step according to the expression in the identification object as the position where the calculation error occurs.
10. The apparatus according to claim 9, wherein the lexical identification unit is specifically configured to:
and splitting the sentence in the identification object into a plurality of lexical units, detecting the correctness of the words or/and the arithmetic expressions in the lexical units, and determining the lexical units with incorrect words or/and the arithmetic expressions as the positions where the calculation errors occur.
11. The apparatus according to claim 9, wherein the syntax recognition unit is configured to:
and generating a syntax tree from the arithmetic expression in the identification object, deducing a non-terminal symbol on a following node of the syntax tree, and determining the position of a calculation error according to a reverse expression.
12. The apparatus of claim 8, wherein the type identification module comprises:
a category identification unit configured to determine a category of a calculation error that may occur according to a calculation manner of a position where the calculation error occurs in the identification object;
and the error identification unit is configured to refer to the types of the possible calculation errors and sequentially judge the types of the calculation errors.
13. The apparatus according to claim 12, wherein the category identifying unit is configured to:
and determining the bit number type of the possible calculation error according to the calculation bit number of the calculation formula of the position where the calculation error occurs in the identification object.
14. The apparatus according to claim 13, wherein the category identifying unit is further configured to:
the thinking of inertia and/or the exchange of numbers are taken as the kind of calculation error that may occur.
15. A terminal, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
16. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910088034.3A CN111507096B (en) | 2019-01-29 | 2019-01-29 | NLP (non line segment) identification method, device and terminal for teaching system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910088034.3A CN111507096B (en) | 2019-01-29 | 2019-01-29 | NLP (non line segment) identification method, device and terminal for teaching system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111507096A true CN111507096A (en) | 2020-08-07 |
| CN111507096B CN111507096B (en) | 2022-05-20 |
Family
ID=71877276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910088034.3A Active CN111507096B (en) | 2019-01-29 | 2019-01-29 | NLP (non line segment) identification method, device and terminal for teaching system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507096B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096677A (en) * | 2015-08-19 | 2015-11-25 | 北京京东方多媒体科技有限公司 | Teaching system and work method thereof |
| US20160314106A1 (en) * | 2015-04-27 | 2016-10-27 | International Business Machines Corporation | Automated correction of natural language processing systems |
| CN108416709A (en) * | 2018-02-09 | 2018-08-17 | 深圳市鹰硕技术有限公司 | Automatically generate the method and device of mathematics multiple-choice question answer choice |
| CN108509439A (en) * | 2017-02-24 | 2018-09-07 | 上海莘越软件科技有限公司 | A kind of Algebra Teaching system |
| CN109241364A (en) * | 2018-07-13 | 2019-01-18 | 广州神马移动信息科技有限公司 | Generation method, device and the equipment/terminal/server of reference information |
-
2019
- 2019-01-29 CN CN201910088034.3A patent/CN111507096B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160314106A1 (en) * | 2015-04-27 | 2016-10-27 | International Business Machines Corporation | Automated correction of natural language processing systems |
| CN105096677A (en) * | 2015-08-19 | 2015-11-25 | 北京京东方多媒体科技有限公司 | Teaching system and work method thereof |
| CN108509439A (en) * | 2017-02-24 | 2018-09-07 | 上海莘越软件科技有限公司 | A kind of Algebra Teaching system |
| CN108416709A (en) * | 2018-02-09 | 2018-08-17 | 深圳市鹰硕技术有限公司 | Automatically generate the method and device of mathematics multiple-choice question answer choice |
| CN109241364A (en) * | 2018-07-13 | 2019-01-18 | 广州神马移动信息科技有限公司 | Generation method, device and the equipment/terminal/server of reference information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111507096B (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Beckett et al. | FALCON: a software package for analysis of nestedness in bipartite networks | |
| US11195066B2 (en) | Automatic protocol discovery using text analytics | |
| CN107491536B (en) | Test question checking method, test question checking device and electronic equipment | |
| CN111325031B (en) | Resume analysis method and device | |
| CN114792089A (en) | Method, apparatus and program product for managing computer system | |
| CN109614327B (en) | Method and apparatus for outputting information | |
| CN112599211B (en) | Medical entity relationship extraction method and device | |
| CN112395880B (en) | Error correction method and device for structured triples, computer equipment and storage medium | |
| CN114201756A (en) | Vulnerability detection method and related device for intelligent contract code segment | |
| US20190362291A1 (en) | Generating and publishing a problem ticket | |
| KR20200071413A (en) | Machine learning data generating apparatus, apparatus and method for analyzing errors in source code | |
| CN111563037B (en) | Test optimization method and device based on test questions, storage medium and terminal | |
| CN111506305B (en) | Tool pack generation method, device, computer equipment and readable storage medium | |
| CN111126056B (en) | Method and device for identifying trigger words | |
| CN111507096B (en) | NLP (non line segment) identification method, device and terminal for teaching system | |
| CN109359055B (en) | Data testing method and device | |
| Ďuračík et al. | Issues with the detection of plagiarism in programming courses on a larger scale | |
| CN115328753A (en) | Fault prediction method and device, electronic equipment and storage medium | |
| CN115660083A (en) | Method and equipment for constructing knowledge graph and asking for answering for transmission network fault | |
| CN114416597A (en) | Test case record generation method and device | |
| CN113515705A (en) | Response information generation method, device, equipment and computer readable storage medium | |
| TWI596583B (en) | Weakened knowledge point correcting learning planning system and method thereof | |
| CN112799938A (en) | Automatic evaluation method and system for microbit programming questions based on python | |
| Gupta et al. | Learning Representations on Logs for AIOps | |
| CN117235744B (en) | Source file online method, device, electronic equipment and computer readable medium |
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 |