CN113205084B - English dictation correction method and device and electronic equipment - Google Patents
English dictation correction method and device and electronic equipment Download PDFInfo
- Publication number
- CN113205084B CN113205084B CN202110755966.6A CN202110755966A CN113205084B CN 113205084 B CN113205084 B CN 113205084B CN 202110755966 A CN202110755966 A CN 202110755966A CN 113205084 B CN113205084 B CN 113205084B
- Authority
- CN
- China
- Prior art keywords
- english
- phrase
- words
- word
- dictation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides an English dictation correction method, device and electronic equipment, which are characterized in that words in an English dictation text image are analyzed according to phrase reference answers and word reference answers in the reference answers, words adjacent in position are combined to obtain similar candidate phrases of the phrase reference answers, then the similar candidate phrases of the phrase reference answers are processed to obtain English dictation phrases input by students, and therefore the English dictation text image of the students is corrected, so that the similar English candidate phrases of the phrase reference answers are obtained by combining the words adjacent in position, and the phrase recognition rate and the correction accuracy rate can be improved when the English dictation text is corrected.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for correcting English dictation and electronic equipment.
Background
At present, English is an important subject of current education, words and phrases are the most basic knowledge of English, and the requirements for students must reach the degree that the students can read, write, use and understand Chinese and English meanings, so in the teaching of words and phrases, dictation is an indispensable operation step. However, there are many students in the class, and there is only one teacher, which causes a lot of and heavy tasks for correction.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide a method, an apparatus, and an electronic device for English dictation correction.
In a first aspect, an embodiment of the present invention provides an english dictation correction method, including:
acquiring English dictation text images uploaded by students, wherein the English dictation text images comprise: english dictation words, English dictation phrases and dictation marks;
inquiring a reference answer list of the English dictation text image according to the dictation identification, wherein the reference answer list comprises answers of English dictation;
performing text detection processing and text recognition processing on the English dictation text image to obtain words and position information of the words in the English dictation text image;
analyzing the number of words of each answer in the reference answer list, determining the answer with the number of words being 1 as a word reference answer, placing the word reference answer into the word answer list, determining the answer with the number of words being more than 1 as a phrase reference answer, and placing the phrase reference answer into the phrase answer list;
determining adjacent words of the words in the display direction based on the position information of the words, establishing association relations between the words and the adjacent words of the words, and taking the words without the association relations as candidate similar words of the word reference answers; wherein, the words in an incidence relation form a phrase;
acquiring a first word in word group reference answers in the word group answer list, and calculating the text similarity between the first word in each word group reference answer in the word group answer list and the detected word in the English dictation text image;
determining phrases corresponding to the association relationship between the English dictation text image and the word with the text similarity larger than the similarity threshold value of the first word in each phrase reference answer in the phrase answer list as similar candidate phrases of each phrase reference answer;
calculating first similarity between each similar candidate phrase in the plurality of similar candidate phrases and a phrase reference answer, and determining the similar candidate phrase with the maximum first similarity obtained by calculation as an English dictation phrase input by a student;
calculating a second similarity between each candidate similar word in the plurality of candidate similar words and the word reference answer, and determining the candidate similar word with the maximum second similarity obtained by calculation as an English dictation word input by the student;
and correcting the English dictation text images of the students according to the phrase reference answers, the word reference answers, the English dictation phrases and the English dictation words.
In a second aspect, an embodiment of the present invention further provides an english dictation correction apparatus, including:
the acquisition module is used for acquiring English dictation text images uploaded by students, and the English dictation text images comprise: english dictation words, English dictation phrases and dictation marks;
the query module is used for querying a reference answer list of the English dictation text image according to the dictation identification, wherein the reference answer list comprises answers of English dictation;
the processing module is used for carrying out text detection processing and text recognition processing on the English dictation text image to obtain words in the English dictation text image and position information of the words;
the analysis module is used for analyzing the number of words of each answer in the reference answer list, determining the answer with the number of words being 1 as a word reference answer, placing the word reference answer into the word answer list, determining the answer with the number of words being more than 1 as a phrase reference answer, and placing the phrase reference answer into the phrase answer list;
the first determining module is used for determining adjacent words of the words in the display direction based on the position information of the words, establishing association relations between a plurality of words and the adjacent words of the words, and taking the words without the association relations as candidate similar words of the word reference answers; wherein, the words in an incidence relation form a phrase;
the first calculation module is used for acquiring a first word in the word group reference answers in the word group answer list and calculating the text similarity between the first word in each word group reference answer in the word group answer list and the detected word in the English dictation text image;
a second determining module, configured to determine phrases corresponding to association relationships between words in the english dictation text image and words in the phrase answer list, where text similarity of a first word in each phrase reference answer is greater than a similarity threshold, as similar candidate phrases of each phrase reference answer;
the second calculation module is used for calculating the first similarity between each similar candidate phrase in the plurality of similar candidate phrases and the phrase reference answer, and determining the similar candidate phrase with the maximum first similarity obtained by calculation as an English dictation phrase input by the student;
the third calculation module is used for calculating second similarity between each candidate similar word in the plurality of candidate similar words and the word reference answers and determining the candidate similar word with the maximum second similarity obtained through calculation as an English dictation word input by the student;
and the correcting module is used for correcting the English dictation text images of the students according to the phrase reference answers, the word reference answers, the English dictation phrases and the English dictation words.
In a third aspect, the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the method in the first aspect.
In a fourth aspect, embodiments of the present invention also provide an electronic device, which includes a memory, a processor, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor to perform the steps of the method according to the first aspect.
In the solutions provided in the first to fourth aspects of the embodiments of the present invention, words in the english dictation text image are analyzed according to the phrase reference answers and the word reference answers in the reference answers, words adjacent to each other in position are merged to obtain similar candidate phrases of the phrase reference answers, then the similar candidate phrases of the phrase reference answers are processed to obtain english dictation phrases input by the student, and thus, the english dictation text image of the student is modified, so that the similar candidate phrases of the phrase reference answers are obtained by using the manner of merging words adjacent to each other in position, and when the english dictation text is modified, the recognition rate of the phrases and the accuracy rate of modification can be improved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 shows a flowchart of an english dictation correction method provided in embodiment 1 of the present invention;
fig. 2 is a schematic structural diagram illustrating an english dictation correction device provided in embodiment 2 of the present invention;
fig. 3 shows a schematic structural diagram of an electronic device provided in embodiment 3 of the present invention.
Detailed Description
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like, indicate orientations and positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
At present, as is well known, english is an important subject of education, words and phrases are the most basic components of english, and the requirements of students must meet the requirements of reading, writing, using and understanding the meaning of chinese and english, so in the teaching of words and phrases, dictation is an indispensable operation step. However, the students in class are numerous, but the English teachers are few, and the task of correction is large and heavy.
The application provides an English dictation correction method, an English dictation correction device and electronic equipment, which mainly solve the problem of reducing a large amount of time for correction of the operation of a teacher and automatically process repeated work, such as: the homework of the student is photographed and uploaded to the mobile phone end in batches, and the homework is corrected through comparison with the answer after reaching the server, so that the correction effect of the homework made by the student is returned, the method is simple and efficient, and the error condition is avoided.
Based on this, the following embodiments of the present application provide an english dictation correction method, apparatus, and electronic device, according to a phrase reference answer and a word reference answer in a reference answer, analyze words in an english dictation text image, merge words adjacent in position to obtain similar candidate phrases of the phrase reference answer, then process the similar candidate phrases of the phrase reference answer to obtain an english dictation phrase input by a student, so as to correct an english dictation text image of the student, thereby obtaining the similar candidate phrases of the phrase reference answer by using a manner of merging words adjacent in position, and when correcting an english dictation text, can improve a recognition rate of the phrase and an accuracy rate of correction.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
Example 1
The embodiment provides an English dictation correction method, and an execution main body is a server.
And the server is connected with the image acquisition equipment.
Referring to fig. 1, the present embodiment provides an english dictation correction method, which includes the following specific steps:
In step 100, after the student completes the english dictation job, the student obtains an english dictation text, and then an image capture device connected to the server captures an english dictation text image of the english dictation text. After the English dictation text image is acquired, the image acquisition equipment prompts a student to input a student name and a class of the student, the student name and the class of the student are used as dictation identifiers to be arranged in the English dictation text image, and then the English dictation text image with the dictation identifiers is uploaded to the server, so that the server acquires the English dictation text image uploaded by the student.
And 102, inquiring a reference answer list of the English dictation text image according to the dictation identification, wherein the reference answer list comprises all answers of English dictation.
In step 102, after the teacher uploads the reference answer list, the server inputs the name of the student who listens in english and/or the class of the student as a dictation identifier, and then generates and stores a corresponding relationship between the dictation identifier and the reference answer list.
Then, when the server acquires the english dictation text image uploaded by the image acquisition device, the server traverses the correspondence between the dictation identifier and the reference answer list according to the dictation identifier carried in the english dictation text image, and queries the reference answer list corresponding to the english dictation text image.
And 104, performing text detection processing and text recognition processing on the English dictation text image to obtain words and position information of the words in the English dictation text image.
In step 104, performing text detection processing and text recognition processing on the english dictation text image to obtain the words and the position information of the words in the english dictation text image is the prior art, and is not described here any more.
The position information of the word includes but is not limited to: coordinate information of the upper left corner of the word and coordinate information of the lower right corner.
The position information of the word is coordinates in a two-dimensional system, and includes: the abscissa and the ordinate.
In the step 106, the process of analyzing the number of words of each answer in the reference answer list is the prior art, and is not described herein again.
In the above step 108, when the difference between the ordinate in the coordinate information of the lower right corner of the word a and the ordinate in the coordinate information of the upper left corner in the coordinate information of another word b in the display direction is smaller than the first coordinate threshold value and the difference between the abscissa in the coordinate information of the lower right corner of the word a and the abscissa in the coordinate information of the upper left corner in the coordinate information of another word b is smaller than the second coordinate threshold value, it is determined that the word b is an adjacent word of the word a in the display direction.
The difference value between the ordinate in the coordinate information of the lower right corner of the word a and the ordinate in the coordinate information of the upper left corner of the coordinate information of another word b in the display direction is smaller than a first coordinate threshold value, and the word a and the word b are on the same horizontal line; when the difference between the abscissa in the coordinate information of the lower right corner of the word a and the abscissa in the coordinate information of the upper left corner of the coordinate information of another word b is smaller than the second coordinate threshold, the server may determine that the spacing distance of the word b in the display direction is 1 to 3 widths of the english characters, which indicates that the spacing distance between the word b and the word a is smaller. By combining the two points, the server can determine the adjacent word b of the word a in the display direction, determine that the adjacent word b of the word a and the word a is the word in a phrase, generate the association relationship between the word and the adjacent word of the word, and judge whether the word b has the adjacent word by using the method, thereby obtaining the association relationship between the words forming a phrase.
In one embodiment, if a phrase consists of word a, word b, and word c in the display direction. The association that the server can get is the word a-word b-word c.
The association may be stored in the server in the form of a linked list.
In the step 110, in order to calculate the text similarity between the first word in each phrase reference answer in the phrase answer list and the word in the english dictation text image obtained through detection, the number of english characters included in the first word of each phrase reference answer may be obtained through statistics; then, comparing the English characters in the first word in each phrase reference answer with the English characters of the words in the English dictation text image obtained through detection one by one, and determining the number of the first word in each phrase reference answer to be the same as the number of the characters of the words in the English dictation text image obtained through detection; and finally, calculating the text similarity between the first word in each phrase reference answer in the phrase answer list and the word in the English dictation text image obtained by detection according to the same character number/the English character number.
For example: any phrase reference answer is play the piano; then the first word in the phrase reference answer is play; then, the number of english characters is 4; the word in the English dictation text image needing comparison is plus; then, after comparing English characters one by one, determining that the number of the same characters in the first word play in the phrase reference answer and the word plus in the English dictation text image is 2; then, the text similarity of play to plus =2/4= 50%.
And step 112, determining phrases corresponding to the association relationship between the words in the english dictation text image and the words with the text similarity of the first word in each phrase reference answer being greater than the similarity threshold in the phrase answer list as similar candidate phrases of each phrase reference answer.
In step 112, the similarity threshold may be set to 0.4.
In order to expand the range of similar candidate phrases, a second word adjacent to the first word in the display direction in the phrase reference answers in the phrase answer list can be obtained, then the similarity between the second word in each phrase reference answer in the phrase answer list and the detected second text of the word in the english dictation text image is calculated, and some similar candidate phrases are determined again according to the calculated second text similarity. The specific process is similar to the process described in step 110 to step 112, and is not described herein again.
And step 114, calculating a first similarity between each similar candidate phrase in the plurality of similar candidate phrases and the phrase reference answer, and determining the similar candidate phrase with the maximum first similarity as an English dictation phrase input by the student.
In the step 114, a manner of calculating a first similarity between each similar candidate phrase in the plurality of similar candidate phrases and the phrase reference answer is similar to the process of calculating the text similarity between a first word in each phrase reference answer in the phrase answer list and a word in the english dictation text image obtained by detection, that is, the number of characters included in the phrase reference answer is determined first; then, comparing the English characters in each similar candidate phrase with the English characters in the phrase reference answers one by one, and determining that the similar candidate phrases are respectively the same as the English characters of the phrase reference answers in number; and finally, calculating the first similarity of each similar candidate phrase and the phrase reference answer by the same number of the similar candidate phrases as the English characters of the phrase reference answer or the number of the characters in the phrase reference answer.
And step 116, calculating a second similarity between each candidate similar word in the plurality of candidate similar words and the word reference answer, and determining the candidate similar word with the maximum second similarity obtained by calculation as an English dictation word input by the student.
In the step 116, the process of calculating the second similarity between each candidate similar word in the plurality of candidate similar words and the word reference answer is similar to the process of calculating the text similarity between the first word in each phrase reference answer in the phrase answer list and the detected word in the english dictation text image, and is not repeated here.
Further, the reference answer list carries a case identifier.
In one embodiment, the capital and small case identifier is 0, which indicates that capital English characters in English dictation phrases and English dictation words do not need to be converted into lowercase English characters; the capital and small letters are 1, which means that capital English characters in English dictation phrases and English dictation words do not need to be converted into lowercase English characters.
Before the dictation text is corrected, English dictation word groups and English dictation words need to be preprocessed.
Therefore, before the step of correcting the English dictation text image of the student according to the phrase reference answers, the word reference answers, the English dictation phrases and the English dictation words, the method further comprises the following steps (1) to (5):
(1) acquiring a case identifier carried in the reference answer list;
(2) judging whether the capital and small case marks indicate that capital English characters in English dictation phrases and English dictation words need to be converted into lowercase English characters or not; if yes, executing the step (3), otherwise, executing the step (4);
(3) converting capital English characters in English dictation phrases and English dictation words into lowercase English characters, and jumping to the step (5);
(4) keeping capital English characters in English dictation phrases and English dictation words unchanged;
(5) and removing the number characters and illegal characters in English dictation phrases and English dictation words.
In the step (5), the process of removing the numeric characters and illegal characters in the english dictation phrase and the english dictation word is the prior art, and is not repeated here.
The illegal characters include but are not limited to: "," # "," @ ","! "and English words or phrases as correct answers to repeated writings.
After preprocessing the english dictation phrases and english dictation words, the method continues to modify the english dictation text images of the students according to the phrase reference answers, the word reference answers, the english dictation phrases and the english dictation words in step 118.
And step 118, correcting the English dictation text images of the students according to the phrase reference answers, the word reference answers, the English dictation phrases and the English dictation words.
In the above step 118, in order to modify the english dictation text image of the student, the following steps (1) to (13) may be performed:
(1) traversing each phrase reference answer by using the English dictation phrase, determining the English dictation phrase as a correct answer when the content which is consistent with the English dictation phrase can be inquired from each phrase reference answer, and setting a correction mark for the phrase reference answer which is consistent with the English dictation phrase;
(2) when the content consistent with the English dictation phrases cannot be inquired from the word group reference answers, calculating a third similarity between the English dictation phrases and the word group reference answers;
(3) when the third similarity of the English dictation phrase and the phrase reference answer obtained by calculation is smaller than the correction similarity threshold, determining the English dictation phrase as an irrelevant phrase;
(4) when the third similarity between the English dictation phrase obtained by calculation and the phrase reference answer is greater than or equal to the correction similarity threshold, determining the English dictation phrase with the third similarity to the phrase reference answer greater than or equal to the correction similarity threshold as a phrase to be replaced, and acquiring the corresponding relation of the replaced characters; wherein, the corresponding relation of the replacing characters records the corresponding relation of a plurality of replaced characters and the characters replacing the replaced characters;
(5) when the phrase reference answers are contained in phrases to be replaced, determining the phrases to be replaced as correct answers, and setting correction marks for phrase reference answers consistent with the English dictation phrases;
(6) when the phrase reference answers are not contained in the phrases to be replaced, calculating the editing distance between the phrases to be replaced and the phrase reference answers, and obtaining an editing relation list for converting the phrases to be replaced into the phrase reference answers, wherein an editing process for converting the phrases to be replaced into the phrase reference answers in a mode of adding English characters, a mode of deleting English characters and/or a mode of replacing English characters is recorded in the editing relation list; the method for replacing English characters comprises the following steps: the corresponding relation between the replaced character in the phrase to be replaced and the character replacing the replaced character;
(7) when only English character replacing modes are recorded in the edit relationship list and the number of the English character replacing modes is the same as the number threshold, acquiring the English character replacing modes recorded in the edit relationship list;
(8) when the corresponding relation between the replaced character in the phrase to be replaced and the character replacing the replaced character in the mode of replacing the English character recorded in the edit relation list is recorded in the corresponding relation of the replaced character, determining the phrase to be replaced as a correct answer, and setting a correction mark for a phrase reference answer consistent with the English dictation phrase;
(9) when the mode of adding English characters or the mode of deleting English characters are recorded in the edit relation list, or the number of the modes of replacing English characters recorded in the edit relation list is different from the number threshold, determining the phrase to be replaced as a wrong answer, and setting a correction mark for the phrase reference answer corresponding to the English dictation phrase of which the third similarity of the phrase reference answer is more than or equal to the correction similarity threshold;
(10) determining English dictation words consistent with the word reference answers as correct answers, and setting correction marks for the word reference answers consistent with the English dictation words;
(11) determining English dictation words inconsistent with the word reference answers as wrong answers, and setting correction marks for the word reference answers corresponding to the English dictation words with the fourth similarity of the word reference answers being more than or equal to the correction similarity threshold;
(12) based on the word reference answers with the correction marks, determining the word reference answers without the correction marks from the word reference answers, and determining the word reference answers without the correction marks as the words missed by the students;
(13) and determining the phrase reference answers which are not provided with the correction marks from the phrase reference answers based on the phrase reference answers which are provided with the correction marks, and determining the phrase reference answers which are not provided with the correction marks as the phrases which are missed by the students.
In the step (1), the content consistent with the english dictation phrase can be queried from each of the word group reference answers, that is, the phrase reference answer consistent with the english dictation phrase can be queried from each of the word group reference answers.
In the step (2), the process of calculating the third similarity between the english dictation phrase and the reference answer of each phrase group is similar to the process of calculating the first similarity between each similar candidate phrase in the similar candidate phrases and the reference answer of the phrase in the step 114, and details are not repeated here.
In the step (3) above, in one embodiment, the correction similarity threshold may be set to 0.6.
The irrelevant word group is used for indicating that the English dictation word group written by the student is irrelevant to the subject.
In the step (4), the correspondence relationship between the replacement characters is preset in the server.
The corresponding relation of the replacement characters records the corresponding relation between characters which are easy to be confused and mixed when the students write English characters by hand.
In the step (5), when the phrase reference answer is included in the phrase to be replaced, it is described that a recognition error occurs due to a writing condition such as a handwriting stroke in the recognition process of the phrase to be replaced, and a correct answer is erroneously recognized as a wrong answer. And (5) correcting the situation of wrongly judged English dictation phrases.
In the step (7), in one embodiment, the number threshold may be set to 2.
In the above steps (6) to (9), the explanation can be made by the following example:
for example: if there is a phrase reference answer is make take and the English dictation phrase is rrake take.
And if the third similarity of the English dictation phrase and the phrase reference answer is 0.8, determining that the English dictation phrase rrake cake is a to-be-replaced phrase of the phrase reference answer make cake.
The edit distance between the phrase rrake to be replaced and the phrase reference answer make can be calculated by a get _ codes method of sequence mather, an edit relation list which is converted from the phrase to be replaced and the phrase reference answer make is obtained, a character replacement operation (namely, 'rr' is replaced by'm') is recorded in the edit relation list, and then after the corresponding relation between'm' and 'rr' is found in the preset corresponding relation of the replacement characters, the rrake can be judged to be the correct answer in a character replacement mode within 2 times.
If the English dictation phrase is the make keys, the operation obtained by the get _ opcodes method is to add English characters s, which is not a replacement operation, so that the English dictation phrase make keys can be judged to be wrongly written by the student and be wrong answers.
For another example, the correct answer is you have a coming call, the english dictation phrase is you have g call, and the get _ codes method can be used to obtain an edit relationship list, which includes the following operations: o is replaced by a; g is replaced by a; n is replaced by m; explaining that 3 times of character replacement operations are recorded in the edit relation list, and the number of the character replacement operations exceeds the number threshold value 2, it can be judged that the English dictation phrase you have a come call is wrongly written by the student and is an incorrect answer.
Similarly, if the student writes the word group you have a come letter in english, the edit relationship list obtained by the above get _ codes method includes the following operations: the character replacing operation "n replaces l", but when looking up in the replacing character corresponding relation, the corresponding relation between the replaced character n and the character l replacing the replaced character n cannot be found, so that the situation can also judge that the english dictation phrase you have a come letter writing mistake is an incorrect answer.
Through the process described in the steps (1) to (13), in the process of correcting the English dictation, the wrong answer can be determined, and words or phrases which are not written (neglected writing) by students and written irrelevant phrases which are irrelevant to the dictation content can be identified, so that the explanation of a teacher can be more targeted, and the score of the student can correctly show the dictation condition of the student.
The embodiment provides an english dictation correction method, which includes analyzing words in an english dictation text image according to phrase reference answers and word reference answers in the reference answers, merging words adjacent in position to obtain similar candidate phrases of the phrase reference answers, processing the similar candidate phrases of the phrase reference answers to obtain english dictation phrases input by a student, correcting the english dictation text image of the student according to the similar candidate phrases, and obtaining the similar candidate phrases of the phrase reference answers by utilizing a mode of merging words adjacent in position.
Example 2
This embodiment proposes an english dictation correction apparatus for executing the english dictation correction method proposed in embodiment 1 above.
Referring to fig. 2, a schematic structural diagram of an english dictation correction device is shown, the english dictation correction device provided in this embodiment includes:
the obtaining module 200 is configured to obtain an english dictation text image uploaded by a student, where the english dictation text image includes: english dictation words, English dictation phrases and dictation marks;
the query module 202 is configured to query a reference answer list of the english dictation text image according to the dictation identifier, where the reference answer list includes answers for english dictation;
the processing module 204 is configured to perform text detection processing and text recognition processing on the english dictation text image to obtain a word in the english dictation text image and position information of the word;
an analyzing module 206, configured to analyze the number of words of each answer in the reference answer list, determine an answer with a word number of 1 as a word reference answer, place the word reference answer in the word answer list, determine an answer with a word number greater than 1 as a phrase reference answer, and place the phrase reference answer in the phrase answer list;
a first determining module 208, configured to determine, based on the position information of the word, adjacent words of the word in the display direction, establish association relationships between multiple words and adjacent words of the word, and use a word without an established association relationship as a candidate similar word of the word reference answer; wherein, the words in an incidence relation form a phrase;
a first calculating module 210, configured to obtain a first word in the phrase reference answers in the phrase answer list, and calculate text similarities between the first word in each phrase reference answer in the phrase answer list and the detected word in the english dictation text image;
a second determining module 212, configured to determine phrases corresponding to association relationships between the words in the english dictation text image and the words in the phrase reference answers in the phrase answer list, where the text similarity of the first word is greater than the similarity threshold, as similar candidate phrases of the phrase reference answers, respectively;
the second calculating module 214 is configured to calculate a first similarity between each similar candidate phrase in the multiple similar candidate phrases and the phrase reference answer, and determine the similar candidate phrase with the maximum first similarity obtained through calculation as an english dictation phrase input by the student;
the third calculating module 216 is configured to calculate a second similarity between each candidate similar word in the multiple candidate similar words and the word reference answer, and determine the candidate similar word with the largest second similarity obtained through calculation as an english dictation word input by the student;
and the correcting module 218 is configured to correct the english dictation text image of the student according to the phrase reference answer, the word reference answer, the english dictation phrase, and the english dictation word.
Further, the reference answer list carries a case identifier; the device further comprises:
the obtaining unit is used for obtaining the capital and small case identifiers carried in the reference answer list;
the judging unit is used for judging whether the capital and small case marks indicate that capital English characters in English dictation phrases and English dictation words need to be converted into lowercase English characters or not; if so, executing the function of the conversion unit, otherwise executing the function of the holding unit;
the conversion unit is used for converting uppercase English characters in English dictation phrases and English dictation words into lowercase English characters and skipping to execute the function of the preprocessing unit;
the holding unit is used for holding capital English characters in English dictation phrases and English dictation words unchanged;
and the preprocessing unit is used for removing the digital characters and illegal characters in English dictation phrases and English dictation words.
Specifically, the first calculation module is specifically configured to:
counting to obtain the number of English characters contained in the first word of each phrase reference answer;
comparing English characters in the first words in the phrase reference answers with English characters of the words in the English dictation text image obtained through detection one by one, and determining the number of the first words in the phrase reference answers to be the same as the number of the characters of the words in the English dictation text image obtained through detection;
and calculating the text similarity between the first word in each phrase reference answer in the phrase answer list and the word in the English dictation text image obtained by detection through the same character number/the English character number.
The embodiment provides an english dictation correction device, according to a phrase reference answer and a word reference answer in a reference answer, words in an english dictation text image are analyzed, words adjacent in position are combined to obtain similar candidate phrases of the phrase reference answer, then the similar candidate phrases of the phrase reference answer are processed to obtain english dictation phrases input by a student, and therefore the english dictation text image of the student is corrected, so that the similar candidate phrases of the phrase reference answer are obtained by combining the words adjacent in position, and when the english dictation text is corrected, the phrase recognition rate and the correction accuracy rate are improved.
Example 3
The present embodiment proposes a computer-readable storage medium, which stores thereon a computer program that, when executed by a processor, performs the steps of the english dictation correction method described in embodiment 1 above. For specific implementation, refer to method embodiment 1, which is not described herein again.
In addition, referring to the schematic structural diagram of an electronic device shown in fig. 3, the present embodiment further provides an electronic device, where the electronic device includes a bus 51, a processor 52, a transceiver 53, a bus interface 54, a memory 55, and a user interface 56. The electronic device comprises a memory 55.
In this embodiment, the electronic device further includes: one or more programs stored on the memory 55 and executable on the processor 52, configured to be executed by the processor for performing the following steps (1) to (10):
(1) acquiring English dictation text images uploaded by students, wherein the English dictation text images comprise: english dictation words, English dictation phrases and dictation marks;
(2) inquiring a reference answer list of the English dictation text image according to the dictation identification, wherein the reference answer list comprises answers of English dictation;
(3) performing text detection processing and text recognition processing on the English dictation text image to obtain words and position information of the words in the English dictation text image;
(4) analyzing the number of words of each answer in the reference answer list, determining the answer with the number of words being 1 as a word reference answer, placing the word reference answer into the word answer list, determining the answer with the number of words being more than 1 as a phrase reference answer, and placing the phrase reference answer into the phrase answer list;
(5) determining adjacent words of the words in the display direction based on the position information of the words, establishing association relations between the words and the adjacent words of the words, and taking the words without the association relations as candidate similar words of the word reference answers; wherein, the words in an incidence relation form a phrase;
(6) acquiring a first word in word group reference answers in the word group answer list, and calculating the text similarity between the first word in each word group reference answer in the word group answer list and the detected word in the English dictation text image;
(7) determining phrases corresponding to the association relationship between the English dictation text image and the word with the text similarity larger than the similarity threshold value of the first word in each phrase reference answer in the phrase answer list as similar candidate phrases of each phrase reference answer;
(8) calculating first similarity between each similar candidate phrase in the plurality of similar candidate phrases and a phrase reference answer, and determining the similar candidate phrase with the maximum first similarity obtained by calculation as an English dictation phrase input by a student;
(9) calculating a second similarity between each candidate similar word in the plurality of candidate similar words and the word reference answer, and determining the candidate similar word with the maximum second similarity obtained by calculation as an English dictation word input by the student;
(10) and correcting the English dictation text images of the students according to the phrase reference answers, the word reference answers, the English dictation phrases and the English dictation words.
A transceiver 53 for receiving and transmitting data under the control of the processor 52.
Where a bus architecture (represented by bus 51) is used, bus 51 may include any number of interconnected buses and bridges, with bus 51 linking together various circuits including one or more processors, represented by processor 52, and memory, represented by memory 55. The bus 51 may also link various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further in this embodiment. A bus interface 54 provides an interface between the bus 51 and the transceiver 53. The transceiver 53 may be one element or may be multiple elements, such as multiple receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. For example: the transceiver 53 receives external data from other devices. The transceiver 53 is used for transmitting data processed by the processor 52 to other devices. Depending on the nature of the computing system, a user interface 56, such as a keypad, display, speaker, microphone, joystick, may also be provided.
The processor 52 is responsible for managing the bus 51 and the usual processing, running a general-purpose operating system as described above. And memory 55 may be used to store data used by processor 52 in performing operations.
Alternatively, processor 52 may be, but is not limited to: a central processing unit, a singlechip, a microprocessor or a programmable logic device.
It will be appreciated that the memory 55 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data Rate Synchronous Dynamic random access memory (ddr Data Rate SDRAM, ddr SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 55 of the systems and methods described in this embodiment is intended to comprise, without being limited to, these and any other suitable types of memory.
In some embodiments, memory 55 stores elements, executable modules or data structures, or a subset thereof, or an expanded set thereof as follows: an operating system 551 and application programs 552.
The operating system 551 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application 552 includes various applications, such as a Media Player (Media Player), a Browser (Browser), and the like, for implementing various application services. A program implementing the method of an embodiment of the present invention may be included in the application 552.
The embodiment provides a computer-readable storage medium and an electronic device, wherein words in an english dictation text image are analyzed according to phrase reference answers and word reference answers in the reference answers, words adjacent in position are combined to obtain similar candidate phrases of the phrase reference answers, then the similar candidate phrases of the phrase reference answers are processed to obtain english dictation phrases input by a student, and therefore, correction is performed on the english dictation text image of the student, so that the similar candidate phrases of the phrase reference answers are obtained by combining the words adjacent in position, and when an english dictation text is corrected, the recognition rate of the phrases and the accuracy of correction can be improved.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. An English dictation correction method is characterized by comprising the following steps:
acquiring English dictation text images uploaded by students, wherein the English dictation text images comprise: english dictation words, English dictation phrases and dictation marks;
inquiring a reference answer list of the English dictation text image according to the dictation identification, wherein the reference answer list comprises answers of English dictation;
performing text detection processing and text recognition processing on the English dictation text image to obtain words and position information of the words in the English dictation text image;
analyzing the number of words of each answer in the reference answer list, determining the answer with the number of words being 1 as a word reference answer, placing the word reference answer into the word answer list, determining the answer with the number of words being more than 1 as a phrase reference answer, and placing the phrase reference answer into the phrase answer list;
determining adjacent words of the words in the display direction based on the position information of the words, establishing association relations between the words and the adjacent words of the words, and taking the words without the association relations as candidate similar words of the word reference answers; wherein, the words in an incidence relation form a phrase;
acquiring a first word in word group reference answers in the word group answer list, and calculating the text similarity between the first word in each word group reference answer in the word group answer list and the detected word in the English dictation text image;
determining phrases corresponding to the association relationship between the English dictation text image and the word with the text similarity larger than the similarity threshold value of the first word in each phrase reference answer in the phrase answer list as similar candidate phrases of each phrase reference answer;
calculating first similarity between each similar candidate phrase in the plurality of similar candidate phrases and a phrase reference answer, and determining the similar candidate phrase with the maximum first similarity obtained by calculation as an English dictation phrase input by a student;
calculating a second similarity between each candidate similar word in the plurality of candidate similar words and the word reference answer, and determining the candidate similar word with the maximum second similarity obtained by calculation as an English dictation word input by the student;
and correcting the English dictation text images of the students according to the phrase reference answers, the word reference answers, the English dictation phrases and the English dictation words.
2. The method according to claim 1, wherein the reference answer list carries case identification; before the step of correcting the English dictation text image of the student according to the phrase reference answers, the word reference answers, the English dictation phrases and the English dictation words, the method further comprises the following steps:
acquiring a case identifier carried in the reference answer list;
judging whether the capital and small case marks indicate that capital English characters in English dictation phrases and English dictation words need to be converted into lowercase English characters or not;
if yes, converting uppercase English characters in English dictation phrases and English dictation words into lowercase English characters, and skipping to the step of removing digital characters and illegal characters in the English dictation phrases and English dictation words;
if not, keeping capital English characters in English dictation phrases and English dictation words unchanged;
and removing the number characters and illegal characters in English dictation phrases and English dictation words.
3. The method according to claim 1, wherein calculating the text similarity between the first word in each phrase reference answer in the phrase answer list and the first word in each incidence relation in the display direction in the plurality of incidence relations comprises:
counting to obtain the number of English characters contained in the first word of each phrase reference answer;
comparing English characters in the first words in the phrase reference answers with English characters of the words in the English dictation text image obtained through detection one by one, and determining the number of the first words in the phrase reference answers to be the same as the number of the characters of the words in the English dictation text image obtained through detection;
and calculating the text similarity between the first word in each phrase reference answer in the phrase answer list and the word in the English dictation text image obtained by detection through the same character number/the English character number.
4. The method of claim 1, wherein correcting the english dictation text image of the student based on the phrase reference answers, the word reference answers, the english dictation phrases, and the english dictation words comprises:
traversing each phrase reference answer by using the English dictation phrase, determining the English dictation phrase as a correct answer when the content which is consistent with the English dictation phrase can be inquired from each phrase reference answer, and setting a correction mark for the phrase reference answer which is consistent with the English dictation phrase;
when the content consistent with the English dictation phrases cannot be inquired from the word group reference answers, calculating a third similarity between the English dictation phrases and the word group reference answers;
when the third similarity of the English dictation phrase and the phrase reference answer obtained by calculation is smaller than the correction similarity threshold, determining the English dictation phrase as an irrelevant phrase;
when the third similarity between the English dictation phrase obtained by calculation and the phrase reference answer is greater than or equal to the correction similarity threshold, determining the English dictation phrase with the third similarity to the phrase reference answer greater than or equal to the correction similarity threshold as a phrase to be replaced, and acquiring the corresponding relation of the replaced characters; wherein, the corresponding relation of the replacing characters records the corresponding relation of a plurality of replaced characters and the characters replacing the replaced characters;
when the phrase reference answers are contained in phrases to be replaced, determining the phrases to be replaced as correct answers, and setting correction marks for phrase reference answers consistent with the English dictation phrases; when the phrase reference answers are not contained in the phrases to be replaced, calculating the editing distance between the phrases to be replaced and the phrase reference answers, and obtaining an editing relation list for converting the phrases to be replaced into the phrase reference answers, wherein an editing process for converting the phrases to be replaced into the phrase reference answers in a mode of adding English characters, a mode of deleting English characters and/or a mode of replacing English characters is recorded in the editing relation list; the method for replacing English characters comprises the following steps: the corresponding relation between the replaced character in the phrase to be replaced and the character replacing the replaced character;
when only English character replacing modes are recorded in the edit relationship list and the number of the English character replacing modes is the same as the number threshold, acquiring the English character replacing modes recorded in the edit relationship list; when the corresponding relation between the replaced character in the phrase to be replaced and the character replacing the replaced character in the mode of replacing the English character recorded in the edit relation list is recorded in the corresponding relation of the replaced character, determining the phrase to be replaced as a correct answer, and setting a correction mark for a phrase reference answer consistent with the English dictation phrase;
when the mode of adding English characters or the mode of deleting English characters are recorded in the edit relation list, or the number of the modes of replacing English characters recorded in the edit relation list is different from the number threshold, determining the phrase to be replaced as a wrong answer, and setting a correction mark for the phrase reference answer corresponding to the English dictation phrase of which the third similarity of the phrase reference answer is more than or equal to the correction similarity threshold;
determining English dictation words consistent with the word reference answers as correct answers, and setting correction marks for the word reference answers consistent with the English dictation words;
and determining English dictation words inconsistent with the word reference answers as wrong answers, and setting correction marks for the word reference answers corresponding to the English dictation words with the fourth similarity of the word reference answers being more than or equal to the correction similarity threshold.
5. The method of claim 1, further comprising:
based on the word reference answers with the correction marks, determining the word reference answers without the correction marks from the word reference answers, and determining the word reference answers without the correction marks as the words missed by the students;
and determining the phrase reference answers which are not provided with the correction marks from the phrase reference answers based on the phrase reference answers which are provided with the correction marks, and determining the phrase reference answers which are not provided with the correction marks as the phrases which are missed by the students.
6. An English dictation correcting device, comprising:
the acquisition module is used for acquiring English dictation text images uploaded by students, and the English dictation text images comprise: english dictation words, English dictation phrases and dictation marks;
the query module is used for querying a reference answer list of the English dictation text image according to the dictation identification, wherein the reference answer list comprises answers of English dictation;
the processing module is used for carrying out text detection processing and text recognition processing on the English dictation text image to obtain words in the English dictation text image and position information of the words;
the analysis module is used for analyzing the number of words of each answer in the reference answer list, determining the answer with the number of words being 1 as a word reference answer, placing the word reference answer into the word answer list, determining the answer with the number of words being more than 1 as a phrase reference answer, and placing the phrase reference answer into the phrase answer list;
the first determining module is used for determining adjacent words of the words in the display direction based on the position information of the words, establishing association relations between a plurality of words and the adjacent words of the words, and taking the words without the association relations as candidate similar words of the word reference answers; wherein, the words in an incidence relation form a phrase;
the first calculation module is used for acquiring a first word in the word group reference answers in the word group answer list and calculating the text similarity between the first word in each word group reference answer in the word group answer list and the detected word in the English dictation text image;
a second determining module, configured to determine phrases corresponding to association relationships between words in the english dictation text image and words in the phrase answer list, where text similarity of a first word in each phrase reference answer is greater than a similarity threshold, as similar candidate phrases of each phrase reference answer;
the second calculation module is used for calculating the first similarity between each similar candidate phrase in the plurality of similar candidate phrases and the phrase reference answer, and determining the similar candidate phrase with the maximum first similarity obtained by calculation as an English dictation phrase input by the student;
the third calculation module is used for calculating second similarity between each candidate similar word in the plurality of candidate similar words and the word reference answers and determining the candidate similar word with the maximum second similarity obtained through calculation as an English dictation word input by the student;
and the correcting module is used for correcting the English dictation text images of the students according to the phrase reference answers, the word reference answers, the English dictation phrases and the English dictation words.
7. The apparatus according to claim 6, wherein the list of reference answers carries a case identifier; the device further comprises:
the obtaining unit is used for obtaining the capital and small case identifiers carried in the reference answer list;
the judging unit is used for judging whether the capital and small case marks indicate that capital English characters in English dictation phrases and English dictation words need to be converted into lowercase English characters or not; if so, executing the function of the conversion unit, otherwise executing the function of the holding unit;
the conversion unit is used for converting uppercase English characters in English dictation phrases and English dictation words into lowercase English characters and skipping to execute the function of the preprocessing unit;
the holding unit is used for holding capital English characters in English dictation phrases and English dictation words unchanged;
and the preprocessing unit is used for removing the digital characters and illegal characters in English dictation phrases and English dictation words.
8. The apparatus of claim 6, wherein the first computing module is specifically configured to:
counting to obtain the number of English characters contained in the first word of each phrase reference answer;
comparing English characters in the first words in the phrase reference answers with English characters of the words in the English dictation text image obtained through detection one by one, and determining the number of the first words in the phrase reference answers to be the same as the number of the characters of the words in the English dictation text image obtained through detection;
and calculating the text similarity between the first word in each phrase reference answer in the phrase answer list and the word in the English dictation text image obtained by detection through the same character number/the English character number.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of the claims 1 to 5.
10. An electronic device comprising a memory, a processor, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor to perform the steps of the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110755966.6A CN113205084B (en) | 2021-07-05 | 2021-07-05 | English dictation correction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110755966.6A CN113205084B (en) | 2021-07-05 | 2021-07-05 | English dictation correction method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113205084A CN113205084A (en) | 2021-08-03 |
| CN113205084B true CN113205084B (en) | 2021-10-08 |
Family
ID=77022702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110755966.6A Active CN113205084B (en) | 2021-07-05 | 2021-07-05 | English dictation correction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113205084B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201818A (en) * | 2006-12-13 | 2008-06-18 | 李萍 | Method for calculating language structure, executing participle, machine translation and speech recognition using HMM |
| CN104021111A (en) * | 2014-06-23 | 2014-09-03 | 上海埃威航空电子有限公司 | Lexicon-based message word correcting method and system |
| CN104345896A (en) * | 2013-07-31 | 2015-02-11 | 淘宝（中国）软件有限公司 | Alphabetic writing word group inputting method and alphabetic writing word group inputting system |
| CN105760356A (en) * | 2016-03-17 | 2016-07-13 | 广东小天才科技有限公司 | Automatic generation method and system for English word dictation question alternative options |
| CN108121702A (en) * | 2017-12-26 | 2018-06-05 | 科大讯飞股份有限公司 | Mathematics subjective item reads and appraises method and system |
| CN108536708A (en) * | 2017-03-03 | 2018-09-14 | 腾讯科技（深圳）有限公司 | A kind of automatic question answering processing method and automatically request-answering system |
| CN108734153A (en) * | 2018-07-18 | 2018-11-02 | 深圳迪普乐宁科技有限公司 | A kind of method and system of efficient computer marking |
| CN109271945A (en) * | 2018-09-27 | 2019-01-25 | 广东小天才科技有限公司 | Method and system for realizing job correction on line |
| CN109376355A (en) * | 2018-10-08 | 2019-02-22 | 上海起作业信息科技有限公司 | English word and sentence screening technique, device, storage medium and electronic equipment |
| CN111767709A (en) * | 2019-03-27 | 2020-10-13 | 武汉慧人信息科技有限公司 | Logic method for carrying out error correction and syntactic analysis on English text |
| CN111797610A (en) * | 2020-07-13 | 2020-10-20 | 郑州玛源网络科技有限公司 | Font and key sentence analysis method based on image processing |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110249905A1 (en) * | 2010-01-15 | 2011-10-13 | Copanion, Inc. | Systems and methods for automatically extracting data from electronic documents including tables |
| CN109190131B (en) * | 2018-09-18 | 2023-04-14 | 北京工业大学 | Neural machine translation-based English word and case joint prediction method thereof |
| CN111081103B (en) * | 2019-05-17 | 2022-03-01 | 广东小天才科技有限公司 | Dictation answer obtaining method, family education equipment and storage medium |
| CN112580503A (en) * | 2020-12-17 | 2021-03-30 | 深圳市元德教育科技有限公司 | Operation correction method, device, equipment and storage medium |
| CN112749257A (en) * | 2021-01-11 | 2021-05-04 | 徐州金林人工智能科技有限公司 | Intelligent marking system based on machine learning algorithm |
-
2021
- 2021-07-05 CN CN202110755966.6A patent/CN113205084B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201818A (en) * | 2006-12-13 | 2008-06-18 | 李萍 | Method for calculating language structure, executing participle, machine translation and speech recognition using HMM |
| CN104345896A (en) * | 2013-07-31 | 2015-02-11 | 淘宝（中国）软件有限公司 | Alphabetic writing word group inputting method and alphabetic writing word group inputting system |
| CN104021111A (en) * | 2014-06-23 | 2014-09-03 | 上海埃威航空电子有限公司 | Lexicon-based message word correcting method and system |
| CN105760356A (en) * | 2016-03-17 | 2016-07-13 | 广东小天才科技有限公司 | Automatic generation method and system for English word dictation question alternative options |
| CN108536708A (en) * | 2017-03-03 | 2018-09-14 | 腾讯科技（深圳）有限公司 | A kind of automatic question answering processing method and automatically request-answering system |
| CN108121702A (en) * | 2017-12-26 | 2018-06-05 | 科大讯飞股份有限公司 | Mathematics subjective item reads and appraises method and system |
| CN108734153A (en) * | 2018-07-18 | 2018-11-02 | 深圳迪普乐宁科技有限公司 | A kind of method and system of efficient computer marking |
| CN109271945A (en) * | 2018-09-27 | 2019-01-25 | 广东小天才科技有限公司 | Method and system for realizing job correction on line |
| CN109376355A (en) * | 2018-10-08 | 2019-02-22 | 上海起作业信息科技有限公司 | English word and sentence screening technique, device, storage medium and electronic equipment |
| CN111767709A (en) * | 2019-03-27 | 2020-10-13 | 武汉慧人信息科技有限公司 | Logic method for carrying out error correction and syntactic analysis on English text |
| CN111797610A (en) * | 2020-07-13 | 2020-10-20 | 郑州玛源网络科技有限公司 | Font and key sentence analysis method based on image processing |
Non-Patent Citations (4)
| Title |
|---|
| Automatic scoring of scene question-answer in English spoken test;Li Wang等;《2014 International Conference on Information Science, Electronics and Electrical Engineering》;20141106;第712-715页 * |
| 基于分词匹配的主观题自动评阅技术研究;冯光等;《计算机与现代化》;20131231;第212-219页 * |
| 基于语句相似度的主观试题自动阅卷模型研究;陈贤武等;《武汉大学学报（工学版）》;20180731;第51卷(第7期);第654-658页 * |
| 智能批改***的研究与设计;贾硕;《中国优秀硕士学位论文全文数据库 信息科技辑》;20081015;第2008年卷(第10期);I138-82 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113205084A (en) | 2021-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271401B (en) | Topic searching and correcting method and device, electronic equipment and storage medium | |
| CN109710590B (en) | Error problem book generation method and device | |
| CN109815932B (en) | Test paper correcting method and device, electronic equipment and storage medium | |
| CN109583429B (en) | Method and device for correcting application questions in test paper in batches | |
| CN111753767A (en) | Method and device for automatically correcting operation, electronic equipment and storage medium | |
| CN112507806B (en) | Intelligent classroom information interaction method and device and electronic equipment | |
| CN112990180B (en) | Question judging method, device, equipment and storage medium | |
| CN113010707A (en) | Homework correcting method and device and electronic equipment | |
| CN111144079B (en) | Method and device for intelligently acquiring learning resources, printer and storage medium | |
| CN116543404A (en) | Table semantic information extraction method, system, equipment and medium based on cell coordinate optimization | |
| CN111382798A (en) | Sample picture label correction method, device, equipment and storage medium | |
| CN109086336A (en) | Paper date storage method, device and electronic equipment | |
| CN112580503A (en) | Operation correction method, device, equipment and storage medium | |
| CN116758786A (en) | Handwriting evaluation method and device, computer equipment and medium | |
| CN108121987B (en) | Information processing method and electronic equipment | |
| CN112149680A (en) | Wrong word detection and identification method and device, electronic equipment and storage medium | |
| DE102016105584A1 (en) | IMPROVED SEARCH IN HANDWRITTEN DATA | |
| CN113505786A (en) | Test question photographing and judging method and device and electronic equipment | |
| CN113205084B (en) | English dictation correction method and device and electronic equipment | |
| CN110929514B (en) | Text collation method, text collation apparatus, computer-readable storage medium, and electronic device | |
| CN111832550B (en) | Data set manufacturing method and device, electronic equipment and storage medium | |
| CN111090989B (en) | Prompting method based on character recognition and electronic equipment | |
| CN113050933A (en) | Brain graph data processing method, device, equipment and storage medium | |
| CN109902724B (en) | Text recognition method and device based on support vector machine and computer equipment | |
| CN112487897A (en) | Handwriting content evaluation method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |