CN108241847A - Lateh format formula processing method and device in text recognition - Google Patents

Abstract

The embodiment of the application provides a processing method and a device for Lateh format formula in text recognition, wherein the method comprises the following steps: obtaining the formula interval symbol number of a formula in text recognition, and judging whether the formula interval symbol number is an even number; if the number is even, determining the position of the head of the formula according to the character type before the first formula interval symbol in each formula fragment; determining the position of the tail of the formula according to the character type after the last formula interval symbol in each formula fragment; and deleting redundant formula interval symbols to obtain a complete Latah format formula. According to the embodiment of the application, the fragments of the Lathy format formula can be automatically synthesized into the Lathy format formula, the labor cost of image recognition is saved, and the recognition efficiency is improved.

Description

Method and device for processing Rateh format formulas in text recognition

technical field

The present application belongs to the technical field of image recognition, and in particular relates to a method and a device for processing Latek format formulas in text recognition.

Background technique

LATEX (LATEX, transliterated "LATEH") is a typesetting system based on TEX, developed by American computer scientist Leslie Lamport in the early 1980s, using this format , Even if the user has no knowledge of typesetting and programming, he can give full play to the powerful functions provided by TeX, and can generate many book-quality prints in a few days or even a few hours. This is especially true for generating complex tables and mathematical formulas. It is therefore ideal for producing scientific and mathematical documents of high print quality. This system is equally suitable for generating all other kinds of documents from simple letters to complete books.

In the traditional computer-aided instruction system, teachers often need to enter a large number of test paper questions and exercise books into the computer system to facilitate online contact with students and online tutoring by teachers. The process of entering test questions often consumes a lot of manpower and material resources, and the progress is often very slow. Image recognition technology can be used to complete the entry of most of the questions very conveniently and quickly, but because the formulas contained in the question cannot be recognized by the whole at one time, the result of image recognition still needs manual secondary intervention, which leads to inefficiency. The improvement is very limited. If the formula fragments of the Rateh format for image recognition (a part of the Rateh format formula separated by the formula separator) can be merged together in an automated manner, the labor cost of image recognition will be saved and the recognition efficiency will be improved.

Therefore, how to automatically process the Rateh scheme formula in image recognition has become a technical problem that needs to be solved urgently in the prior art.

Contents of the invention

One of the technical problems to be solved by the embodiments of the present application is to provide a method and device for processing Rateh format formulas in text recognition, which can automatically synthesize Rateh format formula fragments into Rateh format formulas, saving image recognition Lower labor costs and improve recognition efficiency.

An embodiment of the present application provides a method for processing Latek format formulas in text recognition, including:

Obtaining the number of formula interval symbols of the formula in the text recognition, and judging whether the number of formula interval symbols is an even number;

If it is an even number, the position of the head of the formula fragment is determined according to the character type before the first formula interval symbol of each formula fragment;

Determine the position of the tail of the formula fragment according to the character type after the last formula interval symbol of each formula fragment;

Remove redundant formula spacers to obtain complete formulas in Rateh format.

In the specific implementation of the present application, the method also includes:

If it is an odd number, search for a character or a formula spacer that is not included in the formula fragment before each formula spacer, and insert a formula spacer after the character or formula spacer.

In the specific implementation of the present application, if it is an even number, determining the position of the head of the formula fragment according to the character type before the first formula interval symbol of each formula fragment includes:

Detecting the type of the first character before the first formula break symbol of each formula fragment;

If described first character is any one in Chinese, formula interval symbol, punctuation mark, then finish searching forward, determine that the character after described formula interval symbol is the position of the head of formula fragment;

If the first character is a number, a letter or a mathematical symbol, then exchange the position of the formula interval symbol and the first character, and continue to detect and determine the position of the formula fragment head;

If the first character is a right parenthesis, determine the position of the head of the formula fragment according to whether the forward search obtains a left parenthesis.

In the specific implementation of the present application, if the first character is a right parenthesis, then according to whether the forward search obtains a left parenthesis, determining the position of the head of the formula fragment includes:

If the first character is a right parenthesis, then determine whether the forward search obtains a left parenthesis;

If the search does not obtain the left parenthesis, then end the forward search, and determine that the character after the formula interval symbol is the position of the head of the formula fragment;

If the search obtains a left parenthesis, and the characters between the right parenthesis and the left parenthesis are letters and/or mathematical symbols and letters and/or mathematical symbols and numbers, the formula spacer is inserted in front of the left parenthesis.

In the specific implementation of the present application, the determination of the position of the tail of the formula fragment according to the character type after the last formula interval symbol of each formula fragment includes:

detecting the type of the second character after the last formula break symbol of each formula fragment;

If the second character is any one of Chinese, formula interval symbols, and punctuation marks, then end the backward search, and determine that the character before the formula interval symbols is the position of the tail of the formula fragment;

If the second character is a letter, a number or a mathematical symbol, then exchange the position of the formula interval symbol and the second character, and continue to detect backwards to determine the position of the tail of the formula fragment;

If the second character is a left parenthesis, determine the position of the tail of the formula fragment according to whether the backward search obtains a right parenthesis.

In the specific implementation of the present application, if the second character is a left parenthesis, then according to whether the backward search obtains a right parenthesis, determining the position of the tail of the formula fragment includes:

If the second character is a left parenthesis, then determine whether the backward search obtains a right parenthesis;

If searching does not obtain closing parentheses, then end the backward search, and determine that the character after the formula interval symbol is the position of the tail of the formula fragment;

If the search obtains a closing bracket, and the characters between the closing bracket and the left bracket are letters and/or mathematical symbols and letters and/or mathematical symbols and numbers, the formula spacer is inserted behind the closing bracket.

In a specific implementation of the present application, the redundant formula interval symbols are specifically: two consecutive formula interval symbols.

Corresponding to the above method, the present application also provides a Ratek format formula processing device in text recognition, including:

Quantity judging module, is used for obtaining the formula interval symbol quantity of formula in text recognition, and judges whether described formula interval symbol quantity is an even number;

The head determination module is used to determine the position of the head of the formula fragment according to the character type before the first formula interval symbol of each formula fragment if it is an even number;

Tail determination module, used to determine the position of the tail of the formula fragment according to the character type after the last formula interval symbol of each formula fragment;

The symbol removal module is used to remove redundant formula space symbols to obtain complete formulas in Rateh format.

In the specific implementation of the present application, the device also includes:

The symbol inserting module is used to find a character or a formula spacer that is not included in the formula fragment before each formula spacer if the number is odd, and insert a formula spacer after the character or formula spacer.

In the specific implementation of the present application, the header determination module includes:

A first character judging unit, configured to detect the type of the first character before the first formula interval symbol of each formula fragment;

The first search end unit is used for if the first character is any one of Chinese, formula interval symbols, and punctuation marks, then ends the forward search, and determines that the character after the formula interval symbol is the head of the formula fragment Location;

The first character exchange unit is used to exchange the position of the formula interval symbol and the first character if the first character is a number, letter or mathematical symbol, and continue to detect and determine the position of the formula fragment head. ;

The left parenthesis search unit is configured to determine the position of the head of the formula fragment according to whether the forward search obtains a left parenthesis if the first character is a right parenthesis.

In the specific implementation of the present application, the left bracket search unit includes:

The first judging subunit is used to judge whether the forward search obtains a left bracket if the first character is a right bracket;

The first obtaining subunit is used to end the forward search if the search does not obtain the left parenthesis, and determine that the character after the formula interval symbol is the position of the head of the formula fragment;

The first unobtained subunit is used to divide the formula into an interval symbol if the left parenthesis is obtained from the search, and the characters between the right parenthesis and the left parenthesis are letters and/or mathematical symbols and letters and/or mathematical symbols and numbers Inserted before said opening parenthesis.

In the specific implementation of the present application, the tail determination module includes:

The second character judging unit is used to detect the type of the second character after the last formula interval symbol of each formula fragment;

The second search end unit is used to end the backward search if the second character is any one of Chinese, formula spacer and punctuation, and determine that the character before the formula spacer is the position of the tail of the formula fragment ;

The second character exchange unit is used to exchange the position of the formula interval symbol and the second character if the second character is a letter, a number or a mathematical symbol, and continue to detect and determine the position of the tail of the formula fragment;

A right bracket lookup unit, configured to determine the position of the tail of the formula fragment according to whether the backward search obtains a right bracket if the second character is a left bracket.

In the specific implementation of the present application, the right bracket search unit includes:

The second judging subunit is used to judge whether the backward search obtains a right bracket if the second character is a left bracket;

The second obtaining subunit is used to end the backward search if the search does not obtain a right parenthesis, and determine that the character after the formula interval symbol is the position of the tail of the formula fragment;

The second unobtained subunit is used to divide the formula into an interval symbol if the search obtains a closing bracket, and the characters between the closing bracket and the left bracket are letters and/or mathematical symbols and letters and/or mathematical symbols and numbers Inserted after the closing parenthesis.

In a specific implementation of the present application, the redundant formula interval symbols are specifically: two consecutive formula interval symbols.

When the embodiment of the present application determines that the number of formula interval symbols is an even number, determine the position of the formula head in the formula fragment according to the character type before the first formula interval symbol in each formula fragment, and determine the position of the formula header in each formula fragment according to the last formula interval in each formula fragment The type of character following the symbol determines the position of the tail of the formula in the formula fragment. Furthermore, the redundant formula interval symbols are deleted to obtain a complete Latek format formula. The application can automatically synthesize fragments of the Rateh format formula into Rateh format formulas, save labor costs for image recognition, and improve recognition efficiency.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments described in this application, and those skilled in the art can also obtain other drawings based on these drawings.

Fig. 1 is a flow chart of an embodiment of a method for processing Latek format formulas in a text recognition provided by the present application;

FIG. 2 is a flow chart of another embodiment of a method for processing Latek format formulas in text recognition provided by the present application;

Fig. 3 is a flow chart of an embodiment of step S2 in a method for processing Latek format formulas in text recognition provided by the present application;

FIG. 4 is a flow chart of an embodiment of step S24 in a method for processing Latek format formulas in text recognition provided by the present application;

Fig. 5 is a flow chart of an embodiment of step S3 in a method for processing Latek format formulas in text recognition provided by the present application;

FIG. 6 is a flow chart of an embodiment of step S34 in a method for processing Latek format formulas in text recognition provided by the present application;

FIG. 7 is a structural diagram of an embodiment of a Ratek format formula processing device in text recognition provided by the present application;

Fig. 8 is a structure diagram of another embodiment of a Ratek format formula processing device in text recognition provided by the present application;

Fig. 9 is a structural diagram of an embodiment of a head determination module in a Ratek formula processing device for text recognition provided by the present application;

Fig. 10 is a structure diagram of an embodiment of the left bracket search unit in the head determination module in the Ratek format formula processing device in a text recognition provided by the present application;

Fig. 11 is a structural diagram of an embodiment of a tail determination module in a Latek format formula processing device in a text recognition provided by the present application;

Fig. 12 is a structural diagram of an embodiment of a right bracket search unit in a tail determination module in a Latek format formula processing device provided by the present application;

Fig. 13 is a schematic diagram of the hardware structure of the electronic device of the Latek format formula processing method in the text recognition provided by the present application;

Fig. 14 is a flowchart of a specific application scenario of the present application.

Detailed ways

When the embodiment of the present application determines that the number of formula interval symbols is an even number, determine the position of the formula head in the formula fragment according to the character type before the first formula interval symbol in each formula fragment, and determine the position of the formula header in each formula fragment according to the last formula interval in each formula fragment The type of character following the symbol determines the position of the tail of the formula in the formula fragment. Furthermore, the redundant formula interval symbols are deleted to obtain a complete Latek format formula. The application can automatically synthesize fragments of the Rateh format formula into Rateh format formulas, save labor costs for image recognition, and improve recognition efficiency.

While the present application is capable of embodiments in many different forms, certain embodiments have been shown in the drawings and will be described in detail herein, it being understood that the disclosure of such embodiments should be considered as an illustration of principles and is not intended to be The application is limited to the specific embodiments shown and described. In the following description, the same reference numerals are used to describe the same, similar or corresponding parts in the several views of the drawings.

As used herein, the term "a" or "an" is defined as one or more than one. As used herein, the term "plurality" is defined as two or more than two. As used herein, the term "other" is defined as at least one more or more. As used herein, the terms "comprising" and/or "having" are defined as comprising (ie, open language). As used herein, the term "coupled" is defined as connected, although not necessarily directly, and not necessarily mechanically. As used herein, the term "program" or "computer program" or similar terms is defined as a sequence of instructions designed for execution on a computer system. A "program" or "computer program" may include subroutines, functions, procedures, object methods, object implementations, executable applications, applets, servlets, source code, object code, shared/dynamically loaded libraries, and/or Other sequences of instructions designed for execution on a computer system.

Reference throughout this document to "one embodiment," "certain embodiments," "an embodiment," or similar terms means that a particular feature, structure, or characteristic described in connection with the embodiments is included in at least one implementation of the invention. example. Thus, the appearances of such words in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments, without limitation.

As used herein, the term "or" should be interpreted as being inclusive or meaning any one or any combination. Thus, "A, B or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". An exception to this definition will only occur when a combination of elements, functions, steps or acts is in some way inherently mutually exclusive.

In order to enable those skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described implementation Examples are only some of the embodiments of the present application, but not all of them. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in this application shall fall within the protection scope of this application.

The specific implementation of the present application will be further described below in conjunction with the drawings of the present application.

Referring to Fig. 1, an embodiment of the present application provides a method for processing Latek format formulas in text recognition, including:

S1. Obtain the number of formula interval symbols of the formula in the text recognition, and judge whether the number of formula interval symbols is an even number.

For the Rateh format formula, all mathematical formulas should be placed between the formula interval symbols $$, but the Rateh format formula crawled from the website usually divides a complete formula into multiple formula fragments.

For example, the crawled Rateh format formula "Title 1:|-$$\frac{1}{2}$$|+$$\sqrt{12}$$-2$$^{-1}$$ ", including formula fragments: $$\frac{1}{2}$$, $$\sqrt{12}$$, $$^{-1}$$. And this complete formula should be $$|-\frac{1}{2}|+\sqrt{12}-2^{-1}$$.

Since the crawled Rateh format formula contains some formula fragments, the title that was originally one formula now displays three formulas. For example, "Title 1: |-$$\frac{1}{2}$$|+$$\sqrt{12}$$-2$$^{-1}$$", there are 6 formula interval symbols $$, these 6 formula interval symbols $$ are in pairs, and the part in the middle is the formula fragment in latex format. Calculate whether the number of formula fragments in it is an even number, such as "|-$$\frac{1}{2}$$|+$$\sqrt{12}$$-2$$^{-1}$$" The number of formula fragments in is 3.

S2. If it is an even number, determine the position of the head of the formula fragment according to the character type before the first formula interval symbol of each formula fragment.

If the number of formula spacers is even, the head position of the formula fragment can be determined according to the character type before the first formula space symbol of each formula fragment.

S3. Determine the position of the tail of the formula fragment according to the character type after the last formula interval symbol of each formula fragment.

If the number of formula spacers is an even number, the position of the tail of the formula fragment can be determined according to the character type after the last formula space symbol of each formula fragment.

S4. Deleting redundant formula interval symbols to obtain a complete formula in Rateh format.

Delete the redundant formula space symbols in multiple formula fragments, so that the formulas on both sides can be opened, and a complete formula in Rateh format can be obtained.

Therefore, the present application can automatically synthesize fragments of the Rateh format formula into Rateh format formulas, save labor costs for image recognition, and improve recognition efficiency.

In another specific embodiment of the present application, referring to FIG. 2, the method further includes:

S5. If it is an odd number, search for a character or a formula spacer that is not included in the formula fragment before each formula spacer, and insert a formula spacer after the character or formula spacer.

If the number of formula interval symbols is odd, for each formula interval symbol $$, find the first character that is not in the formula or formula interval symbol $$ from before it, and insert the formula interval symbol $$ after the character.

For example, the following topic 2:

Calculation: |-$$\frac{1}{2}$$|+$$ (question 2)

For the first pair of formula interval symbols $$, the first character before it that is not in the formula is a colon ":", then after the first processing, the title becomes:

Calculate: $$|-$$\frac{1}{2}$$|+$$

In the same way, after the entire formula is processed, it becomes:

Calculate: $$|-$$$$\frac{1}{2}$$$$|+$$

After processing in this way, the number of interval symbols $$ in the formula in the title becomes an even number, and then step S2 is executed.

In another specific embodiment of the present application, referring to FIG. 3, the step S2 includes:

S21. Detect the type of the first character before the first formula space symbol of each formula fragment.

S22. If the first character is any one of Chinese, formula spacer, and punctuation mark, then end the forward search, and determine that the character after the formula spacer is the head position of the formula fragment.

Specifically, if the first character is any one of Chinese, formula interval symbols, and punctuation marks, it indicates that the first character is not a part of the formula fragment. For example, if the first character before the first formula interval symbol $$ in "(1), $$a+b$$" is ",", then it is determined that the character "a" after the formula interval symbol $$ is The position of the head of the formula fragment.

S23. If the first character is a number, a letter or a mathematical symbol, exchange the position of the formula interval symbol and the first character, and continue to detect and determine the position of the head of the formula fragment.

Specifically, if the first character is a number, letter or mathematical symbol, it indicates that the first character is a part of a formula fragment. For example, if the first character before the first formula space symbol $$ in "6+$$5+9$$" is "+", then exchange the positions of the formula space symbol and the first character to obtain "6$ $+5+9$$". Continue to detect and determine the position of the head of the formula fragment, exchange the positions of the formula interval symbol and the first character to obtain "$$6+5+9$$".

S24. If the first character is a right parenthesis, determine the position of the head of the formula fragment according to whether the forward search obtains a left parenthesis.

Specifically, referring to FIG. 4, the step S24 includes:

S241. If the first character is a right bracket, judge whether the forward search obtains a left bracket.

S242. If the search does not obtain a left parenthesis, end the forward search, and determine that the character after the formula space symbol is the head position of the formula fragment.

S243. If the search obtains the left parenthesis, and the characters between the right parenthesis and the left parenthesis are letters and/or mathematical symbols and letters and/or mathematical symbols and numbers, insert the formula interval symbol into the left parenthesis Front.

In the embodiment of the present application, when the first character is a right bracket, it is necessary to search forward whether the formula interval symbol needs to be moved forward to the front of the left bracket in front of the right bracket, that is, it needs to be based on whether the left bracket can be found , to determine the position of the head of the formula fragment.

In another specific embodiment of the present application, referring to FIG. 5, the step S3 includes:

S31. Detect the type of the second character after the last formula space symbol of each formula fragment.

S32. If the second character is any one of Chinese, formula spacer, and punctuation mark, then end the backward search, and determine that the character before the formula spacer is the position of the tail of the formula fragment.

Specifically, if the second character is any one of Chinese, formula interval symbols, and punctuation marks, it indicates that the second character is not a part of the formula fragment. For example, if the second character after the first formula space symbol $$ in "$$a+b$$," is ",", it is determined that the character "b" before the formula space symbol $$ is the formula fragment The position of the tail.

S33. If the second character is a letter, a number or a mathematical symbol, exchange the position of the formula interval symbol and the second character, and continue to detect backward to determine the position of the tail of the formula fragment.

Specifically, if the second character is a number, letter or mathematical symbol, it indicates that the second character is a part of a formula fragment. For example, if the second character after the last formula space symbol $$ in "$$5+9$$-2" is "-", then exchange the positions of the formula space symbol and the second character to obtain "$$5 +9-$$2". Continue to detect backwards to determine the position of the tail of the formula fragment, exchange the positions of the formula space symbol and the second character to obtain "$$5+9-2$$".

S34. If the second character is a left parenthesis, determine the position of the tail of the formula fragment according to whether the backward search obtains a right parenthesis.

Specifically, referring to FIG. 6, the step S34 includes:

S341. If the second character is a left parenthesis, judge whether the backward search obtains a right parenthesis;

S342. If the search does not obtain a right parenthesis, then end the backward search, and determine that the character after the formula space symbol is the position of the tail of the formula fragment.

S343. If the search obtains a right bracket, and the characters between the right bracket and the left bracket are letters and/or mathematical symbols and letters and/or mathematical symbols and numbers, insert the formula interval symbol into the right bracket Behind.

In the embodiment of the present application, when the second character is a left parenthesis, it is necessary to find out whether the formula interval symbol needs to be moved backward to the right parenthesis behind the left parenthesis, that is, it needs to be based on whether the right parenthesis can be found , to determine the position of the tail of the formula fragment.

In another specific embodiment of the present application, the redundant formula interval symbols are specifically: two consecutive formula interval symbols.

After processing according to steps S1 to S3, there will be a situation where two formula space symbols $$ are connected together, that is, "$$$$", which indicates that the front and back of "$$$$" are real formulas , so you can directly delete "$$$$" at this time, so that the formulas on both sides can be opened.

Referring to FIG. 7 , corresponding to the above method, another embodiment of the present application provides a device for processing Latek format formulas in text recognition, including:

The number judging module 71 is configured to obtain the number of formula interval symbols of the formula in the text recognition, and judge whether the number of formula interval symbols is an even number.

The head determination module 72 is configured to determine the position of the head of the formula fragment according to the character type before the first formula interval symbol of each formula fragment if it is an even number.

The tail determining module 73 is configured to determine the position of the tail of the formula fragment according to the character type after the last formula space symbol of each formula fragment.

The symbol deletion module 74 is used to delete redundant formula interval symbols to obtain a complete formula in Latek format.

For the Rateh format formula, all mathematical formulas should be placed between the formula interval symbols $$, but the Rateh format formula crawled from the website usually divides a complete formula into multiple formula fragments.

For example, the crawled Rateh format formula "Title 1:|-$$\frac{1}{2}$$|+$$\sqrt{12}$$-2$$^{-1}$$ ", including formula fragments: $$\frac{1}{2}$$, $$\sqrt{12}$$, $$^{-1}$$. And this complete formula should be $$|-\frac{1}{2}|+\sqrt{12}-2^{-1}$$.

Since the crawled Rateh format formula contains some formula fragments, the title that was originally one formula now displays three formulas. For example, "Title 1: |-$$\frac{1}{2}$$|+$$\sqrt{12}$$-2$$^{-1}$$", there are 6 formula interval symbols $$, these 6 formula interval symbols $$ are in pairs, and the part in the middle is the formula fragment in latex format. Calculate whether the number of formula fragments in it is an even number, such as "|-$$\frac{1}{2}$$|+$$\sqrt{12}$$-2$$^{-1}$$" The number of formula fragments in is 3.

If the number of formula spacers is even, the head position of the formula fragment can be determined according to the character type before the first formula space symbol of each formula fragment.

If the number of formula fragments is an even number, the position of the tail of the formula fragment can be determined according to the character type after the last formula space symbol of each formula fragment.

Delete the redundant formula space symbols in the formula fragments, so that the formulas on both sides can be opened up, and the complete formulas in the Rateh format can be obtained.

Therefore, the present application can automatically synthesize fragments of the Rateh format formula into Rateh format formulas, save labor costs for image recognition, and improve recognition efficiency.

In another specific embodiment of the present application, referring to FIG. 8, the device further includes:

The symbol insertion module 75 is configured to, if the number is odd, search for a character or a formula space symbol that is not included in the formula fragment before each formula space symbol, and insert a formula space symbol after the character or formula space symbol.

If the number of formula interval symbols is odd, for each formula interval symbol $$, find the first character that is not in the formula or formula interval symbol $$ from before it, and insert the formula interval symbol $$ after the character.

For example, the following topic 2:

Calculation: |-$$\frac{1}{2}$$|+$$ (question 2)

For the first pair of formula interval symbols $$, the first character before it that is not in the formula is a colon ":", then after the first processing, the title becomes:

Calculate: $$|-$$\frac{1}{2}$$|+$$

In the same way, after the entire formula is processed, it becomes:

Calculate: $$|-$$$$\frac{1}{2}$$$$|+$$

After processing in this way, the number of the formula interval symbols $$ in the question becomes an even number, and then the header determination module 72 is executed.

In another specific embodiment of the present application, referring to FIG. 9, the head determination module 72 includes:

The first character judging unit 721 is configured to detect the type of the first character before the first formula interval symbol of each formula fragment.

The first search end unit 722 is used to end the forward search if the first character is any one of Chinese, formula space symbol and punctuation mark, and determine that the character after the formula space symbol is the head of the formula fragment s position.

The first character exchange unit 723 is used to exchange the position of the formula interval symbol and the first character if the first character is a number, letter or mathematical symbol, and continue to detect and determine the position of the formula fragment head Location.

The left parenthesis search unit 724 is configured to determine the position of the head of the formula fragment according to whether the forward search obtains a left parenthesis if the first character is a right parenthesis.

Specifically, if the first character is any one of Chinese, formula interval symbols, and punctuation marks, it indicates that the first character is not a part of the formula fragment. For example, if the first character before the first formula interval symbol $$ in "(1), $$a+b$$" is ",", then it is determined that the character "a" after the formula interval symbol $$ is The position of the head of the formula fragment.

Specifically, if the first character is a number, letter or mathematical symbol, it indicates that the first character is a part of a formula fragment. For example, if the first character before the first formula space symbol $$ in "6+$$5+9$$" is "+", then exchange the positions of the formula space symbol and the first character to obtain "6$ $+5+9$$". Continue to detect and determine the position of the head of the formula fragment, exchange the positions of the formula interval symbol and the first character to obtain "$$6+5+9$$".

Specifically, referring to FIG. 10, the left bracket search unit 724 includes:

The first judging subunit 724a is configured to judge whether the forward search obtains a left bracket if the first character is a right bracket.

The first obtaining subunit 724b is configured to end the forward search and determine that the character after the space symbol of the formula is the head position of the formula fragment if the search does not obtain the left parenthesis.

The first unobtained subunit 724c is used to space the formula if the left parenthesis is obtained from the search, and the characters between the right parenthesis and the left parenthesis are letters and/or mathematical symbols and letters and/or mathematical symbols and numbers symbol is inserted in front of the opening parenthesis.

In the embodiment of the present application, when the first character is a right bracket, it is necessary to search forward whether the formula interval symbol needs to be moved forward to the front of the left bracket in front of the right bracket, that is, it needs to be based on whether the left bracket can be found , to determine the position of the head of the formula fragment.

In another specific embodiment of the present application, referring to FIG. 11 , the tail determination module 73 includes:

The second character judging unit 731 is configured to detect the type of the second character after the last formula space symbol of each formula fragment.

The second search end unit 732 is used for if the second character is any one of Chinese, formula interval symbols, and punctuation marks, then ends the backward search, and determines that the character before the formula interval symbol is the tail of the formula fragment Location.

The second character exchange unit 733 is used to exchange the position of the formula interval symbol and the second character if the second character is a letter, a numeral or a mathematical symbol, and continue to detect backwards to determine the position of the tail of the formula fragment .

The right bracket search unit 734 is configured to determine the position of the tail of the formula fragment according to whether the backward search obtains a right bracket if the second character is a left bracket.

Specifically, if the second character is any one of Chinese, formula interval symbols, and punctuation marks, it indicates that the second character is not a part of the formula fragment. For example, if the second character after the first formula space symbol $$ in "$$a+b$$," is ",", it is determined that the character "b" before the formula space symbol $$ is the formula fragment The position of the tail.

Specifically, if the second character is a number, letter or mathematical symbol, it indicates that the second character is a part of a formula fragment. For example, if the second character after the last formula space symbol $$ in "$$5+9$$-2" is "-", then exchange the positions of the formula space symbol and the second character to obtain "$$5 +9-$$2". Continue to detect backwards to determine the position of the tail of the formula fragment, exchange the positions of the formula space symbol and the second character to obtain "$$5+9-2$$".

Specifically, referring to FIG. 12, the right bracket search unit 734 includes:

The second judging subunit 734a is configured to judge whether the backward search obtains a right bracket if the second character is a left bracket;

The second obtaining subunit 734b is configured to end the backward search and determine that the character after the space symbol of the formula is the tail position of the formula fragment if the search does not obtain a right parenthesis.

The second unobtained subunit 734c is used to space the formula if the search obtains a right parenthesis, and the characters between the right parenthesis and the left parenthesis are letters and/or mathematical symbols and letters and/or mathematical symbols and numbers symbols are inserted after the closing parenthesis.

In the embodiment of the present application, when the second character is a left parenthesis, it is necessary to find out whether the formula interval symbol needs to be moved backward to the right parenthesis behind the left parenthesis, that is, it needs to be based on whether the right parenthesis can be found , to determine the position of the tail of the formula fragment.

In another specific embodiment of the present application, the redundant formula interval symbols are specifically: two consecutive formula interval symbols.

After completing the processing according to the above modules, there will be a situation where two formula interval symbols $$ are connected together, that is, "$$$$". This situation indicates that the front and back of "$$$$" are real formulas, so At this point, you can directly delete "$$$$" to open up the formulas on both sides.

FIG. 13 is a schematic diagram of the hardware structure of the electronic device used in the processing method of the Ratek format formula in the text recognition of the present application. According to Figure 13, the device includes:

One or more processors 1310 and memory 1320 , one processor 1310 is taken as an example in FIG. 13 .

The device of the method for processing Latek format formulas in text recognition may further include: an input device 1330 and an output device 1330 .

The processor 1310, the memory 1320, the input device 1330, and the output device 1330 may be connected via a bus or in other ways, and connection via a bus is taken as an example in FIG. 13 .

The memory 1320, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the Ratek in the text recognition in the embodiment of the present application Program instructions/modules corresponding to the format formula processing method (for example, the list setting module 131 and the poster insertion module 132 shown in FIG. 13 ). The processor 1310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 1320, that is, realizes the Latek format formula processing in the text recognition of the above-mentioned method embodiments method.

The memory 1320 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required by a function; created data, etc. In addition, the memory 1320 may include a high-speed random access memory 1320 , and may also include a non-volatile memory 1320 , such as at least one disk storage 1320 , a flash memory device, or other non-volatile solid-state memory 1320 . In some embodiments, the memory 1320 may optionally include memory 1320 remotely located relative to the processor 1310, and these remote memory 1320 may be connected to the sound effect mode selection device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 1330 can receive input number or character information, and generate key signal input related to user setting and function control of the Ratek format formula processing device in text recognition. The output device 1330 may include devices such as speakers.

The one or more modules are stored in the memory 1320, and when executed by the one or more processors 1310, execute the Latek format formula processing method in text recognition in any of the above method embodiments.

The above-mentioned products can execute the method provided by the embodiment of the present application, and have corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, refer to the method provided in the embodiment of this application.

The electronic equipment of the embodiment of the present application exists in various forms, including but not limited to:

(1) Mobile communication equipment: This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communication. Such terminals include: smart phones (such as iPhone), multimedia phones, feature phones, and low-end phones.

(2) Ultra-mobile personal computer equipment: This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has the characteristics of mobile Internet access. Such terminals include: PDA, MID and UMPC equipment, such as iPad.

(3) Portable entertainment equipment: This type of equipment can display and play multimedia content. Such devices include: audio and video players (such as iPod), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

(4) Server: A device that provides computing services. The composition of a server includes a processor, hard disk, memory, system bus, etc. The server is similar to a general-purpose computer architecture, but due to the need to provide high-reliability services, it is important in terms of processing power and stability. , Reliability, security, scalability, manageability and other aspects have high requirements.

(13) Other electronic devices with data interaction function.

The implementation of this application will be further described below through a specific application scenario of this application.

Referring to Figure 14, the method includes:

1401. Receive a question for character recognition.

1402. Determine whether the question contains the formula interval symbol $$.

1403. If the formula interval symbol $$ is not included, no processing is required.

1404. If the formula interval symbol $$ is included, calculate the number N of formula interval symbols.

1405. Determine whether the number N of interval symbols in the formula is an even number.

1406. If it is not an even number, find the position of the first character that is not in the formula before each formula space symbol $$, insert a formula space symbol $$ after it, and execute step 1407.

1407. If it is an even number, group the formula interval symbols in pairs to obtain formula fragments in the formula.

1408. Determine whether all formula fragments have been processed.

1409. If all formula fragments are processed, retrieve and delete repeated formula space symbols $$$$.

1410. If not all formula fragments have been processed, determine whether the formula interval symbol $$ in each formula fragment is at the beginning of the formula fragment.

1411. If it is at the beginning of the formula fragment, judge whether the character before the formula space symbol $$ is contained in the formula, if not, return to step 1408.

1412 . If the character before the formula separator $$ is contained in the formula, exchange the positions of the formula separator $$ and the preceding character, and return to step 1411 .

1413 . If it is not at the beginning of the formula fragment, judge whether the character behind the formula separator $$ is contained in the formula, and if not, return to step 1408 . .

1414. If the character behind the formula separator $$ is contained in the formula, exchange the positions of the formula separator $$ and the character behind, and return to step 1413.

For example, topic 1 "Calculation: |-$$\frac{1}{2}$$|+$$\sqrt{12}$$-2$$^{-1}$$;", after a series of processing Then it becomes:

Calculation: $$|-\frac{1}{2}$$|+$$\sqrt{12}$$-2$$^{-1}$$;

Calculate: $$|-\frac{1}{2}$$$$|+\sqrt{12}$$-2$$^{-1}$$;

Calculate: $$|-\frac{1}{2}$$$$|+\sqrt{12}$$$$-2^{-1}$$;

Calculation: $$|-\frac{1}{2}|+\sqrt{12}-2^{-1}$$;

For example, question 2 "$$\frac{1}{4}$$a$$^{2}$$-9(b-c)$$^{2}$$ is a factor of $$\frac{1 }{2}$$a-3b+3c, the other factor is ()", after a series of processing, it becomes:

A factor of $$\frac{1}{4}$$a$$^{2}$$-9(b-c)$$^{2}$$ is $$\frac{1}{2}$ $a-3b+3c, another factor is ()

A factor of $$\frac{1}{4}$$$$a^{2}$$-9(b-c)$$^{2}$$ is $$\frac{1}{2}$ $a-3b+3c, another factor is ()

A factor of $$\frac{1}{4}$$$$a^{2}$$$$-9(b-c)^{2}$$ is $$\frac{1}{2}$ $a-3b+3c, another factor is ()

A factor of $$\frac{1}{4}$$$$a^{2}$$$$-9(b-c)^{2}$$ is $$\frac{1}{2}$ $a-3b+3c, another factor is ()

A factor of $$\frac{1}{4}$$$$a^{2}$$$$-9(b-c)^{2}$$ is $$\frac{1}{2}$ $a-3b+3c, another factor is ()

A factor of $$\frac{1}{4}$$$$a^{2}$$$$-9(b-c)^{2}$$ is $$\frac{1}{2}a -3b+3c$$, another factor is ()

One factor of $$\frac{1}{4}a^{2}-9(b-c)^{2}$$ is $$\frac{1}{2}a-3b+3c$$, and the other A factor is ()

The device embodiments described above are only illustrative, and the modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in One place, or it can be distributed to multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative efforts.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, devices (devices), or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices) and computer program products of the embodiments. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

While preferred embodiments of the present application have been described, additional changes and modifications to these embodiments can be made by those skilled in the art once the basic inventive concept is appreciated. Therefore, the appended claims are intended to be construed to cover the preferred embodiment and all changes and modifications which fall within the scope of the application. Obviously, those skilled in the art can make various changes and modifications to the application without departing from the spirit and scope of the application. In this way, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims (14)

1. a kind of La Taihe form formula processing methods in text identification, which is characterized in that including：

The formula space character quantity of formula in text identification is obtained, and judges whether the formula space character quantity is even Number；

It is such as even number, the head of formula fragment is determined according to the character types before the first formula space character of each formula fragment The position in portion；

The position of the tail portion of formula fragment is determined according to the character types after the last formula space character of each formula fragment It puts；

Extra formula space character is deleted, obtains complete La Taihe forms formula.

2. the method as described in claim 1, which is characterized in that the method further includes：

It is such as odd number, the character or formula blank character being not included in before searching each formula space character in formula fragment Number, and a formula space character is inserted into after the character or formula space character.

3. the method as described in claim 1, which is characterized in that it is described as being even number, according to the first public affairs of each formula fragment Character types before formula space character determine that the position on the head of formula fragment includes：

Detect the type of the first character before the first formula space character of each formula fragment；

If first character is Chinese, any in formula space character, punctuation mark, terminate Look-ahead, determine Position of the character for the head of formula fragment after the formula space character；

If first character is number, alphabetical or mathematic sign, the formula space character and described first are exchanged The position of character, and continue to detect the position for determining formula fragment head forward；

If first character is right parenthesis, whether left bracket is obtained according to Look-ahead, determines the formula fragment The position on head.

4. method as claimed in claim 3, which is characterized in that if first character be right parenthesis, according to Before search whether obtain left bracket, determine that the position on the head of the formula fragment includes：

If first character is right parenthesis, judge whether Look-ahead obtains left bracket；

If lookup does not obtain left bracket, terminate Look-ahead, determine that the character after the formula space character is formula The position on the head of fragment；

If search obtain left bracket, and the character between the right parenthesis and left bracket for letter and/or mathematic sign and Letter and/or mathematic sign and number, the formula space character is inserted into before the left bracket.

5. method as described in claim 1, which is characterized in that the last formula space character of each formula fragment of basis Character types later determine that the position of the tail portion of formula fragment includes：

Detect the type of the second character after the last formula space character of each formula fragment；

If second character is Chinese, any in formula space character, punctuation mark, terminate to search backward, determine Position of the character for the tail portion of formula fragment before the formula space character；

If second character is letter, digital or mathematic sign, the formula space character and described second are exchanged The position of character, and continue to detect the position for determining formula fragment tail portion backward；

If second character is left bracket, according to acquisition right parenthesis is searched whether backward, the formula fragment is determined The position of tail portion.

6. method as claimed in claim 5, which is characterized in that if second character be left bracket, according to After search whether obtain right parenthesis, determine that the position of the tail portion of the formula fragment includes：

If second character is left bracket, judge to search whether to obtain right parenthesis backward；

If lookup does not obtain right parenthesis, terminate to search backward, determine that the character after the formula space character is formula The position of the tail portion of fragment；

If search obtain right parenthesis, and the character between the right parenthesis and left bracket for letter and/or mathematic sign and Letter and/or mathematic sign and number, the formula space character is inserted into behind the right parenthesis.

7. method as claimed in claim 6, which is characterized in that the extra formula space character is specially：Two continuous Formula space character.

8. a kind of La Taihe form formula manipulation devices in text identification, which is characterized in that including：

Quantity judgment module for obtaining the formula space character quantity of formula in text identification, and judges the formula interval Whether symbol quantity is even number；

Head determining module, for being such as even number, according to the character type before the first formula space character of each formula fragment Type determines the position on the head of formula fragment；

Tail portion determining module determines public affairs for the character types after the last formula space character according to each formula fragment The position of the tail portion of formula fragment；

Puncture module for deleting extra formula space character, obtains complete La Taihe forms formula.

9. device as claimed in claim 8, which is characterized in that described device further includes：

Symbol is inserted into module, for being such as odd number, the word being not included in before searching each formula space character in formula fragment It accords with either formula space character and a formula space character is inserted into after the character or formula space character.

10. device as claimed in claim 9, which is characterized in that the head determining module includes：

First character judging unit, for detecting the first character before the first formula space character of each formula fragment Type；

First searches end unit, if being Chinese for first character, any in formula space character, punctuation mark Kind, then terminate Look-ahead, determine position of the character for the head of formula fragment after the formula space character；

First character crosspoint if being number for first character, alphabetical or mathematic sign, exchanges the public affairs The position of formula space character and first character, and continue to detect the position for determining formula fragment head forward；

Whether left bracket searching unit if being right parenthesis for first character, left bracket is obtained according to Look-ahead, Determine the position on the head of the formula fragment.

11. device as claimed in claim 10, which is characterized in that the left bracket searching unit includes：

First judgment sub-unit if being right parenthesis for first character, judges whether Look-ahead obtains left bracket；

First obtains subelement, if if not obtaining left bracket for searching, terminates Look-ahead, determines between the formula Position of the character for the head of formula fragment after symbol；

First does not obtain subelement, if obtaining left bracket for searching, and the character between the right parenthesis and left bracket is Letter and/or mathematic sign and letter and/or mathematic sign and number, are inserted into the left side by the formula space character and include Before number.

12. device as claimed in claim 11, which is characterized in that the tail portion determining module includes：

Second character judging unit, for detecting the second word after the last formula space character of each formula fragment The type of symbol；

Second searches end unit, if being Chinese for second character, any in formula space character, punctuation mark Kind, then terminate to search backward, the character before determining the formula space character is the position of the tail portion of formula fragment；

Second character crosspoint if being letter for second character, digital or mathematic sign, exchanges the public affairs The position of formula space character and second character, and continue to detect the position for determining formula fragment tail portion backward；

Right parenthesis searching unit, if being left bracket for second character, basis searches whether to obtain right parenthesis backward, Determine the position of the tail portion of the formula fragment.

13. device as claimed in claim 12, which is characterized in that the right parenthesis searching unit includes：

Second judgment sub-unit if being left bracket for second character, judges to search whether to obtain right parenthesis backward；

Second obtains subelement, if not obtaining right parenthesis for searching, terminates to search backward, determines the formula blank character Position of the character for the tail portion of formula fragment after number；

Second does not obtain subelement, if obtaining right parenthesis for searching, and the character between the right parenthesis and left bracket is Letter and/or mathematic sign and letter and/or mathematic sign and number, are inserted into the right side by the formula space character and include Behind number.

14. device as claimed in claim 13, which is characterized in that the extra formula space character is specially：Two companies Continuous formula space character.