CN111079725B - Method for distinguishing English from pinyin and electronic equipment - Google Patents

Abstract

The embodiment of the invention relates to the technical field of education, and discloses a method and electronic equipment for distinguishing English from pinyin, wherein the method comprises the following steps: acquiring a dictation image corresponding to dictation content, segmenting the dictation content in the dictation image into a plurality of independent characters, traversing each independent character, identifying whether preset tone symbols exist in a preset range of the independent character, and if so, combining the independent characters and surrounding characters of the independent characters according to a pinyin composition rule, thereby obtaining pinyin which accords with the pinyin composition rule and serving as pinyin dictation content; and combining the content except all the pinyin dictation content in the dictation content as English dictation content. Therefore, the invention can distinguish English from pinyin in dictation content, and realize accurate identification of dictation content, thereby improving accuracy of dictation correction.

Description

Method for distinguishing English from pinyin and electronic equipment

Technical Field

The invention relates to the technical field of education, in particular to a method for distinguishing English from pinyin and electronic equipment.

Background

The existing home teaching machine has a dictation correcting function widely, and can recognize dictation contents on a dictation book and correct the dictation contents. In practical use, when the pinyin and the English exist in the dictation content at the same time, the family education machine cannot distinguish the pinyin from the English because the pinyin and the English have similarity, so that the family education machine generates misjudgment in the dictation correction process, and the dictation correction cannot be accurately performed.

Disclosure of Invention

Aiming at the defects, the embodiment of the invention discloses a method for distinguishing English from pinyin and electronic equipment, which can distinguish English from pinyin in dictation content, thereby improving the accuracy of dictation correction.

The first aspect of the embodiment of the invention discloses a method for distinguishing English from pinyin, which comprises the following steps:

acquiring dictation images corresponding to dictation contents;

dividing dictation content in the dictation image into a plurality of independent characters; the dictation content comprises English and Pinyin;

traversing each independent character, and identifying whether preset tone marks exist in a preset range of the independent character; the tone-symbol belongs to one of the plurality of independent characters;

if the independent characters exist, combining the independent characters and surrounding characters of the independent characters according to the pinyin formation rule, so as to obtain pinyin which accords with the pinyin formation rule and serve as pinyin dictation content;

and combining the contents except all the pinyin dictation contents in the dictation contents to serve as English dictation contents.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the combining, as english dictation content, contents other than all of the pinyin dictation content, the method further includes:

Comparing the Pinyin dictation content with the correct dictation content to obtain first error dictation content, and comparing the English dictation content with the correct dictation content to obtain second error dictation content, wherein the first error dictation content and the second error dictation content form error dictation content;

determining synonymous error content from the second error dictation content, wherein the Chinese paraphrasing of the synonymous error content is matched with the Chinese paraphrasing of the correct dictation content corresponding to the synonymous error content;

outputting the error dictation content and the correct dictation content corresponding to the error dictation content, and annotating the synonymous error content included in the error dictation content to help a user to distinguish the synonymous error content and the correct dictation content corresponding to the synonymous error content.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the outputting the error dictation content and the correct dictation content corresponding to the error dictation content, the method further includes:

outputting prompt information to prompt a user to read the correct dictation content corresponding to the first error dictation content, and collecting pinyin audio generated by the user;

Analyzing the audio matching degree of the pinyin audio and the standard pinyin audio corresponding to the pinyin audio;

if the audio matching degree is smaller than the preset audio matching degree, dividing the first error dictation content into an initial consonant part, a vowel part and a tone part, and determining that the error part of the first error dictation content is the initial consonant part, the vowel part or the tone part according to the pinyin audio;

outputting a correct pronunciation course of the error part, wherein the correct pronunciation course comprises a pronunciation mouth shape graph, a text annotation and pronunciation example audio.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, the method further includes:

counting first error dictation contents of the user and error parts of each first error dictation content, and analyzing to obtain error pronunciation habits of the user;

searching a dialect type matched with the wrong pronunciation habit of the user in a dialect database, wherein the dialect database stores the wrong pronunciation habit and pronunciation correction methods corresponding to a plurality of dialect types;

and outputting a pronunciation correction method corresponding to the dialect type of the user so as to help the user correct the wrong pronunciation habit of the user.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, the method further includes:

generating a pronunciation detection statement according to the incorrect pronunciation habit of the user;

when detecting that the user does not execute any operation on the electronic equipment within the preset time, outputting the pronunciation detection statement and prompting the user to read the pronunciation detection statement;

collecting detection audio generated by the user reading the pronunciation detection statement;

analyzing whether the user has wrong pronunciation habit of the user when reading the pronunciation detection statement according to the detection audio;

and if the user appears, executing the pronunciation correction method corresponding to the dialect type of the user so as to help the user to correct the wrong pronunciation habit.

A second aspect of an embodiment of the present invention discloses an electronic device, including:

the image acquisition unit is used for acquiring dictation images corresponding to the dictation content;

the character segmentation unit is used for segmenting dictation content in the dictation image into a plurality of independent characters; the dictation content comprises English and Pinyin;

a tone recognition unit for traversing each of the independent characters and recognizing whether a preset tone symbol exists in a preset range of the independent character; the tone-symbol belongs to one of the plurality of independent characters;

The pinyin combination unit is used for combining the independent characters and surrounding characters of the independent characters according to a pinyin composition rule when the preset tone symbols exist in the preset range of the independent characters, so that pinyin which accords with the pinyin composition rule is obtained and used as pinyin dictation content;

and the English combination unit is used for combining the contents except all the pinyin dictation contents in the dictation contents as English dictation contents.

As an optional implementation manner, in a second aspect of the embodiment of the present invention, the electronic device further includes:

the content correcting unit is used for combining the content except all the pinyin dictation content in the dictation content by the English combining unit to serve as English dictation content, comparing the pinyin dictation content with correct dictation content to obtain first error dictation content, and comparing the English dictation content with the correct dictation content to obtain second error dictation content, wherein the first error dictation content and the second error dictation content form error dictation content;

the synonym identification unit is used for determining synonym error content from the second error dictation content, and the Chinese paraphrasing of the synonym error content is matched with the Chinese paraphrasing of the correct dictation content corresponding to the synonym error content;

The first output unit is used for outputting the error dictation content and the correct dictation content corresponding to the error dictation content, and annotating the synonymous error content included in the error dictation content so as to help a user to distinguish the synonymous error content and the correct dictation content corresponding to the synonymous error content.

As an optional implementation manner, in a second aspect of the embodiment of the present invention, the electronic device further includes:

the first acquisition unit is used for outputting prompt information to prompt a user to read the correct dictation content corresponding to the first error dictation content after the first output unit outputs the error dictation content and the correct dictation content corresponding to the error dictation content, and acquiring pinyin audio generated by the user;

the audio analysis unit is used for analyzing the audio matching degree of the pinyin audio and the standard pinyin audio corresponding to the pinyin audio;

the error determining unit is used for dividing the first error dictation content into an initial consonant part, a final sound part and a tone part when the audio matching degree is smaller than a preset audio matching degree, and determining that the error part of the first error dictation content is the initial consonant part, the final sound part or the tone part according to the pinyin audio;

And the second output unit is used for outputting the correct pronunciation course of the error part, wherein the correct pronunciation course comprises a pronunciation mouth shape graph, a text annotation and pronunciation example audio.

As an optional implementation manner, in a second aspect of the embodiment of the present invention, the electronic device further includes:

the error statistics unit is used for counting the first error dictation content of the user and the error part of each first error dictation content, and analyzing and obtaining the error pronunciation habit of the user;

the dialect matching unit is used for searching a dialect type matched with the wrong pronunciation habit of the user in a dialect database, and the dialect database stores the wrong pronunciation habit and pronunciation correction methods corresponding to a plurality of dialect types;

and the third output unit is used for outputting a pronunciation correction method corresponding to the dialect type of the user so as to help the user correct the wrong pronunciation habit.

As an optional implementation manner, in a second aspect of the embodiment of the present invention, the electronic device further includes:

a sentence generating unit, configured to generate a pronunciation detection sentence according to the incorrect pronunciation habit of the user;

the reading prompting unit is used for outputting the pronunciation detection statement and prompting the user to read the pronunciation detection statement when detecting that the user does not execute any operation on the electronic equipment within a preset time period;

The second acquisition unit is used for acquiring detection audio generated by the user reading the pronunciation detection statement;

the pronunciation analysis unit is used for analyzing whether the user has wrong pronunciation habit of the user when reading the pronunciation detection statement according to the detection audio;

the third output unit is further configured to output a pronunciation correction method corresponding to the dialect type of the user when the user is analyzed to have the incorrect pronunciation habit of the user when the user reads the pronunciation detection sentence, so as to help the user correct the incorrect pronunciation habit.

A third aspect of an embodiment of the present invention discloses an electronic device, including:

a memory storing executable program code;

a processor coupled to the memory;

the processor invokes the executable program code stored in the memory to execute a method for distinguishing between english and pinyin as disclosed in the first aspect of the embodiment of the invention.

A fourth aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute a method for distinguishing english from pinyin disclosed in the first aspect of the embodiments of the present invention.

A fifth aspect of the embodiments of the present invention discloses a computer program product which, when run on a computer, causes the computer to perform part or all of the steps of any one of the methods of the first aspect.

A sixth aspect of the embodiments of the present invention discloses an application publishing platform for publishing a computer program product, wherein the computer program product, when run on a computer, causes the computer to perform part or all of the steps of any one of the methods of the first aspect.

Compared with the prior art, the embodiment of the invention has the following beneficial effects:

in the embodiment of the invention, the electronic equipment acquires the dictation image corresponding to the dictation content, segments the dictation content in the dictation image into a plurality of independent characters, traverses each independent character, recognizes whether preset tone symbols exist in the preset range of the independent character, and if so, combines the independent character and surrounding characters of the independent character according to the pinyin formation rule, thereby obtaining pinyin which accords with the pinyin formation rule and is used as pinyin dictation content; and combining the content except all the pinyin dictation content in the dictation content as English dictation content. Therefore, the invention can distinguish English from pinyin in dictation content, and realize accurate identification of dictation content, thereby improving accuracy of dictation correction.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for distinguishing English from Pinyin according to an embodiment of the present invention;

FIG. 2 is a flow chart of another method for distinguishing English from Pinyin according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of another electronic device according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of another electronic device according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the invention discloses a method and electronic equipment for distinguishing English from pinyin, which can improve the accuracy of identifying subjects of a subject image and improve the use experience of a user. The following detailed description is made in connection with the accompanying drawings from the perspective of an electronic device.

Example 1

Referring to fig. 1, fig. 1 is a flowchart of a method for distinguishing between english and pinyin according to an embodiment of the invention. The method for distinguishing English from pinyin described in fig. 1 is applicable to electronic devices such as home teaching machines, smart phones, tablet computers and personal computers. The embodiment of the invention takes the electronic equipment as an example to describe a method for distinguishing English from pinyin, and the method is not limited. As shown in fig. 1, the method for distinguishing english from pinyin may include the following steps.

101. And acquiring a dictation image corresponding to the dictation content.

In the embodiment of the invention, a user plays the dictation audio corresponding to the dictation content by using the electronic device when dictating, and writes the dictation content on the dictation book according to the indication of the dictation audio, for example, the electronic device can play the Chinese audio when dictating and instruct the user to write English corresponding to the Chinese or pinyin corresponding to the Chinese in the audio, and after the user finishes dictation according to the indication, the user places the dictation book in the effective shooting area of the camera of the electronic device, and the electronic device controls the camera to shoot so as to acquire the dictation image containing the dictation content.

102. And cutting the dictation content in the dictation image into a plurality of independent characters.

In the embodiment of the invention, the dictation content comprises English and pinyin, the English characters composing English and the pinyin characters composing pinyin have similarity, and when the English and the pinyin in the dictation content cannot be distinguished, each English character and the pinyin characters included in the dictation content are firstly segmented to obtain a plurality of independent characters, such as the dictation contentSegmentation into independent characters->The dictation content "h hao" is split into separate characters "h, a, ˇ, o".

103. Each independent character is traversed and whether preset tone marks exist in a preset range of the independent character or not is recognized.

In the embodiment of the present invention, the tone symbol belongs to one of a plurality of independent characters, and the pinyin is composed of a plurality of pinyin characters and tone symbols, so that the pinyin characters can be identified according to the tone symbols, and if the preset tone symbols exist in the preset range of the independent characters, the step 104 is shifted; if not, go to step 105.

As an alternative embodiment, traversing each independent character and identifying whether a preset tone-symbol exists within a preset range of the independent character may be implemented by: the preset tone marks may be "— -, a-, ˇ -, and" b ", which are used to indicate the first, second, third, and fourth sounds of the pinyin tone, respectively, and the preset range is set according to the average length of the plurality of independent characters obtained by the segmentation in step 102, and whether the preset tone mark exists in the preset range of each independent character is detected, and if the preset tone mark" ˇ "exists in the preset range of the independent character" a "is detected for the independent character" h, a, ˇ, and o "obtained by the segmentation in step 102, the tone mark" ˇ "is determined to be the tone indicating the pinyin composed of the independent characters" a ", so that the pinyin character corresponding to the tone mark is accurately identified, and the step 104 is further performed.

As an alternative embodiment, since part of the english word is noted during writing, the english word may also be identified from the phonetic symbols in the individual words. Specifically, it is assumed that for the independent character segmented in step 102Detecting the presence of a preset phonetic symbol +.>Then determine phonetic symbol +.>English is present around and phonetic symbols +.>And phonetic symbols composed of a plurality of independent characters are used for phonetic notation of the English, and can accurately identify the phonetic characters with tone symbols and the English characters with phonetic symbols by detecting the characteristic symbols of the English and the phonetic symbols.

104. And combining the independent characters and surrounding characters of the independent characters according to the pinyin composition rule, thereby obtaining pinyin which accords with the pinyin composition rule and taking the pinyin as pinyin dictation content.

In the embodiment of the invention, only one independent character usually has tone symbols in a plurality of independent characters included in each pinyin, so after the pinyin characters with tone coincidence are identified in the independent characters, the pinyin characters and surrounding independent characters are combined to obtain the complete pinyin.

As an alternative implementation manner, the independent characters and surrounding characters of the independent characters are combined according to the pinyin formation rule, so as to obtain the pinyin which accords with the pinyin formation rule, and the pinyin dictation can be realized by the following ways: the pinyin is generally composed of an initial consonant, a final and a phonetic symbol corresponding to a certain final, after the phonetic symbol and its corresponding pinyin character are identified in step 103, the pinyin character is combined with the phonetic symbol, and then the characters around the pinyin character are detected according to the pinyin formation rule of (the initial consonant+the final), so that a plurality of characters conforming to the pinyin formation rule are identified and combined to obtain a complete pinyin, for example, the pinyin character "a" and the tone symbol "ˇ" identified in step 103 are combined to obtain a character "x", at this time, the character "x" and the characters around the character "x" are identified according to the pinyin formation rule, and the characters conforming to the pinyin formation rule are combined to obtain the pinyin "h o"; the method can identify and obtain a plurality of complete pinyins in the dictation content as the pinyins dictation content. Therefore, under the condition that the pinyin characters and the corresponding tone symbols are identified, the complete pinyin dictation content can be quickly and accurately obtained by combining the disordered dictation content according to the pinyin composition rules.

105. And combining the contents except all the pinyin dictation contents in the dictation contents to serve as English dictation contents.

In the embodiment of the invention, after the pinyin dictation content is obtained according to the pinyin formation rule combination, the rest of the uncombined content does not accord with the pinyin formation rule, the rest of the content can be considered to be English, and the English dictation content can be obtained by combining the rest of the content.

As an alternative embodiment, the combination of the dictation content except for all the pinyin dictation content, as the english dictation content, may be achieved by: based on the detected phonetic symbols and English construction rules, contents other than phonetic transcription content, such as the rest, can be combinedThen according to the construction rules of English, it can be known that +.>Phonetic symbols capable of forming English->Then according to the phonetic symbolsCan be combined to obtain English "eat" so as to obtain complete English dictation content +.>By the method, a plurality of complete English words are identified from the dictation contents to serve as English dictation contents. Therefore, by combining the contents except the pinyin dictation contents, the complete English dictation contents can be simply combined.

As another alternative embodiment, since part of the english dictation content is an english word without phonetic symbols, in the case that the english can not be combined by phonetic symbols, a certain independent character may be selected as a starting character from the content other than all the pinyin dictation content, the starting character and the characters around the starting character are combined, and whether the combined content is a complete english word is detected in the english dictionary database, if not, the combined content and the next independent character are continuously combined until the complete english word is obtained by combining, at this time, the starting character is selected again, the english words are continuously combined, and the combined english words are used as the english dictation content. It can be seen that the English dictation content can be combined in the absence of phonetic symbols by recognizing English words.

In the embodiment of the invention, the electronic device acquires the dictation image corresponding to the dictation content, segments the dictation content in the dictation image into a plurality of independent characters, traverses each independent character, and recognizes whether preset tone symbols exist in the preset range of the independent character, if so, combines the independent character and surrounding characters of the independent character according to the pinyin composition rule, thereby obtaining pinyin which accords with the pinyin composition rule as pinyin dictation content; and combining the content except all the pinyin dictation content in the dictation content as English dictation content. Therefore, the invention can distinguish English from pinyin in dictation content, and realize accurate identification of dictation content, thereby improving accuracy of dictation correction.

Example two

Referring to fig. 2, fig. 2 is a flowchart illustrating a method for distinguishing between english and pinyin according to another embodiment of the invention. As shown in fig. 2, the method for distinguishing english from pinyin may include the following steps.

201. And acquiring a dictation image corresponding to the dictation content.

202. And cutting the dictation content in the dictation image into a plurality of independent characters.

203. Each independent character is traversed and whether preset tone marks exist in a preset range of the independent character or not is recognized.

204. And combining the independent characters and surrounding characters of the independent characters according to the pinyin composition rule, thereby obtaining pinyin which accords with the pinyin composition rule and taking the pinyin as pinyin dictation content.

205. And combining the contents except all the pinyin dictation contents in the dictation contents to serve as English dictation contents.

206. And correcting the pinyin dictation content and the English dictation content to obtain the error dictation content.

In the embodiment of the invention, the recognized pinyin dictation content and English dictation content are modified according to the correct dictation content, so that the error dictation content is obtained and output to the user.

As an optional implementation manner, in step 205, the contents except all the pinyin dictation contents in the dictation contents are combined, after being the english dictation contents, the pinyin dictation contents and the correct dictation contents are compared to obtain a first error dictation content, and the english dictation contents and the correct dictation contents are compared to obtain a second error dictation content, where the first error dictation content and the second error dictation content form an error dictation content; determining synonymous error content from the second error dictation content, wherein the Chinese paraphrasing of the synonymous error content is matched with the Chinese paraphrasing of the correct dictation content corresponding to the synonymous error content; outputting the error dictation content and the correct dictation content corresponding to the error dictation content, and annotating the synonymous error content included in the error dictation content to help a user identify the synonymous error content and the correct dictation content corresponding to the synonymous error content. Specifically, the electronic device compares the identified pinyin dictation content and the identified english dictation content with the correct dictation content, and further obtains the incorrect pinyin dictation content as a first error dictation content and obtains the incorrect english dictation content as a second error dictation content; in addition, in the case of playing the chinese audio and instructing the user to write the english dictation content, there is a phenomenon that the english dictation content written by the user is different from the corresponding correct dictation content, but the chinese paraphrasing is the same, so after the second error dictation content is obtained, it is also detected whether there is a second error dictation content matching with the chinese paraphrasing of the corresponding correct dictation content, for example, when the chinese audio is played and the user is instructed to write the english of "good", the english of the correct dictation content is "good", the dictation content written by the user is "nice" and "nice" is determined as the second error dictation content, and the electronic device detects that "nice" matches with the chinese paraphrasing of "good", and determines that "nice" in the second error dictation content is synonymous error content; after the correction of the dictation content is completed, the electronic equipment outputs the error dictation content formed by the first error dictation content and the second error dictation content and the corresponding correct dictation content so as to enable a user to learn the error dictation content in real time; in addition, the synonymous dictation content in the error dictation content is annotated, and the annotation comprises the paraphrasing and example sentences of the synonymous dictation content and the corresponding correct dictation content, so that a user can distinguish the synonymous dictation content and the correct dictation content according to the annotation, and the user can be helped to correctly use the synonymous dictation content and the correct dictation content. Therefore, by carrying out dictation correction and outputting error dictation content and annotating synonymous error content, a user can be better helped to grasp the error dictation content.

207. And analyzing the mispronounced content of the user to obtain mispronounced habits, and helping the user to correct the mispronounced habits.

In the embodiment of the invention, the pronunciation habit of the user can be obtained by analyzing according to the wrong pinyin content generated when the user listens to pinyin.

As an optional implementation manner, after outputting the error dictation content and the correct dictation content corresponding to the error dictation content in step 206, outputting a prompt message to prompt the user to read the correct dictation content corresponding to the first error dictation content, and collecting pinyin audio generated by the user reading; analyzing the audio matching degree of the standard pinyin audio corresponding to the pinyin audio; if the audio matching degree is smaller than the preset audio matching degree, dividing the first error dictation content into an initial consonant part, a vowel part and a tone part, and determining that the error part of the first error dictation content is the initial consonant part, the vowel part or the tone part according to the pinyin audio; outputting a correct pronunciation course of the error part, wherein the correct pronunciation course comprises a pronunciation mouth shape chart, a text annotation and pronunciation example audio. Specifically, after the wrong dictation content is output, prompt information is output on a screen to prompt a user to read the correct dictation content corresponding to the first wrong dictation content, after the pinyin audio generated by the user reading is acquired, the audio matching degree of the pinyin audio and the standard audio is analyzed, if the pronunciation of the user when reading 'h' o 'is' h 'and' o ', the audio matching degree of' h 'is smaller than the preset audio matching degree, at the moment, the analysis is performed from the angles of tones and the like according to the pinyin audio of' h 'o', the error part of 'h' is known to be a tone part, a correct pronunciation course aiming at the error part is output, the correct pronunciation course comprises a pronunciation mouth shape graph and a character annotation of the pinyin, and the pronunciation example audio of the pinyin, and the user can correct the error pronunciation course according to the correct pronunciation.

As another optional implementation manner, counting the first error dictation content of the user and the error part of each first error dictation content, and analyzing to obtain the error pronunciation habit of the user; searching a dialect database for the type of the dialect matched with the wrong pronunciation habit of the user, wherein the dialect database stores the wrong pronunciation habit and pronunciation correction method corresponding to a plurality of dialect types; and outputting a pronunciation correction method corresponding to the dialect type of the user so as to help the user correct the wrong pronunciation habit of the user. Specifically, the mispronounced habit of the user is generally influenced by the native language and the dialect of the user, so that the type of the dialect of the user can be judged through the mispronounced habit; after the user performs dictation for a plurality of times and generates a large number of first error dictation contents, the error pronunciation habit of the user can be analyzed according to the first error dictation contents, if the error pronunciation habit of the user is confusing with the pronunciation of n and l, the dialect type of the user is found to be Hunan dialect in the dialect database, and a pronunciation correction method aiming at the Hunan dialect is output at the moment, and comprises example audio and pronunciation teaching so as to help the user get rid of the error pronunciation habit brought by the dialect during pronunciation.

As yet another alternative embodiment, the pronunciation detection statement is generated according to the incorrect pronunciation habit of the user; outputting a pronunciation detection statement when detecting that the user does not execute any operation on the electronic equipment within a preset time period, and prompting the user to read the pronunciation detection statement; collecting detection audio generated by a user reading the pronunciation detection statement; analyzing whether the user has wrong pronunciation habit when reading the pronunciation detection statement according to the detection audio; if the user appears, executing a pronunciation correction method corresponding to the dialect type of the output user so as to help the user correct the wrong pronunciation habit. Specifically, after the above-mentioned pronunciation correction method is outputted according to the incorrect pronunciation habit of the user, a pronunciation detection sentence generated for the incorrect pronunciation habit of the user is outputted during the idle period of the electronic device, for example, the incorrect pronunciation habit of the user confusing the pronunciation of "n, l" is generated, the pronunciation detection sentence "you are there, i'll" is generated, the detection audio of the pronunciation detection sentence is collected, if the incorrect pronunciation habit still appears in the detection audio, the steps in the previous embodiment are executed again, so as to help the user to master the correct pronunciation method.

Therefore, in the embodiment of the invention, the user is helped to timely master the error dictation content by correcting and outputting the error dictation content; in addition, the wrong pronunciation habit of the user can be accurately analyzed through the wrong dictation content, the corresponding pronunciation correction method is output to help the user to realize correct pronunciation, and the user experience is good.

Example III

Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the invention. As shown in fig. 3, the electronic device may include:

an image acquisition unit 301, configured to acquire a dictation image corresponding to the dictation content;

the character segmentation unit 302 is configured to segment dictation content in the dictation image into a plurality of independent characters; dictation content includes English and Pinyin;

a tone recognition unit 303, configured to traverse each independent character and recognize whether a preset tone symbol exists within a preset range of the independent character; tone-symbols belong to one of several independent characters;

the pinyin combination unit 304 is configured to, when it is recognized that a preset tone symbol exists in a preset range of the independent character, combine the independent character and surrounding characters of the independent character according to a pinyin formation rule, thereby obtaining a pinyin that meets the pinyin formation rule, and use the pinyin as pinyin dictation content;

The english combination unit 305 is configured to combine, as english dictation contents, contents other than all pinyin dictation contents among dictation contents.

In the embodiment of the present invention, the character segmentation unit 302 segments the dictation content existing on the dictation image acquired by the image acquisition unit 301 to obtain a plurality of independent characters, the tone recognition unit 303 recognizes the tone symbols in the independent characters, the pinyin combination unit 304 obtains the pinyin dictation content according to the combination of the tone symbols, and the english combination unit 305 combines the remaining content to obtain the english dictation content.

As an alternative embodiment, the tone recognition unit 303 traverses each independent character and recognizes whether a preset tone symbol exists within a preset range of the independent character, which may be achieved by: the preset tone symbols may be "—first, second, third and fourth sounds, respectively, for indicating pinyin tones, and the preset range is set according to the average lengths of the individual characters obtained by the segmentation by the character segmentation unit 302, and whether or not a preset tone symbol exists in the preset range of each individual character is detected, and if the individual characters" h, a, ˇ, o "obtained by the segmentation by the character segmentation unit 302 are detected to exist in the preset range of the individual character" a ", the tone recognition unit 303 determines that the tone symbol" ˇ "is a tone for indicating pinyin composed of the individual characters" a ", thereby accurately recognizing the pinyin character corresponding to the tone symbol, and triggering the pinyin combining unit 304.

As an alternative embodiment, since a part of english is noted as a phonetic symbol when writing, the tone recognition unit 303 may also recognize an english character from phonetic symbols in the independent character. Specifically, it is assumed that the individual characters obtained by segmentation are segmented by the character segmentation unit 302Detecting the presence of a preset phonetic symbol +.>The tone recognition unit 303 determines the phonetic symbol +.>English is present around and phonetic symbols +.>And phonetic symbols composed of a plurality of independent characters are used for phonetic notation of the English, and can accurately identify the phonetic characters with tone symbols and the English characters with phonetic symbols by detecting the characteristic symbols of the English and the phonetic symbols.

As an alternative embodiment, the pinyin combining unit 304 combines the independent characters and surrounding characters of the independent characters according to the pinyin formation rule, so as to obtain the pinyin conforming to the pinyin formation rule, and as the pinyin dictation content, the following manner may be implemented: the pinyin is generally composed of an initial consonant, a final and a phonetic symbol corresponding to a certain final, after the tone recognition unit 303 recognizes the phonetic symbol and its corresponding pinyin character, the pinyin combination unit 304 combines the pinyin character with the phonetic symbol, and detects the characters around the pinyin character according to the pinyin formation rule (initial consonant+final), thereby recognizing and obtaining a plurality of characters conforming to the pinyin formation rule, and combining to obtain a complete pinyin, for example, for the pinyin character "a" and the tone symbol "ˇ" recognized by the tone recognition unit 303, the pinyin combination unit 304 combines to obtain the character "me", at this time, recognizes the character "k" and the characters around the same according to the pinyin formation rule, and combines the characters conforming to the pinyin formation rule to obtain the pinyin "h, o"; the method can identify and obtain a plurality of complete pinyins in the dictation content as the pinyins dictation content. Therefore, under the condition that the pinyin characters and the corresponding tone symbols are identified, the complete pinyin dictation content can be quickly and accurately obtained by combining the disordered dictation content according to the pinyin composition rules.

As an alternative embodiment, the english combining unit 305 combines the contents other than all the pinyin dictation contents among the dictation contents, as the english dictation contents, may be realized by: based on the detected phonetic symbols and English construction rules, the English combination unit 305 may combine contents other than the Pinyin dictation contents, such as the rest of the contents Then according to the construction rules of English, it can be known that +.>Phonetic symbols capable of forming English->Based on phonetic symbols->English "eat" can be combined so that English combination unit 305 combines to obtain the complete English dictation content +.>By the method, a plurality of complete English words are identified from the dictation contents to serve as English dictation contents. Therefore, by combining the contents except the pinyin dictation contents, the complete English dictation contents can be simply combined.

As another alternative embodiment, since part of the english dictation content is an english word without phonetic symbols, in the case where the english word cannot be combined by phonetic symbols, the english combining unit 305 may select a certain independent character as a starting character from the content other than all the pinyin dictation content, combine the starting character and the characters around the starting character, and detect whether the combined content is a complete english word in the english dictionary database, if not, continue to combine the combined content and the next independent character until the complete english word is combined, at this time, reselect the starting character, continue to combine the english word, and use the combined several english words as the english dictation content. It can be seen that the English dictation content can be combined in the absence of phonetic symbols by recognizing English words.

It can be seen that, in the embodiment of the present invention, the image obtaining unit 301 obtains the dictation image corresponding to the dictation content, the character segmentation unit 302 segments the dictation content in the dictation image into a plurality of independent characters, the tone recognition unit 303 traverses each independent character and recognizes whether a preset tone symbol exists in a preset range of the independent character, and if so, the pinyin combination unit 304 combines the independent character and surrounding characters of the independent character according to the pinyin formation rule, thereby obtaining pinyin according with the pinyin formation rule as pinyin dictation content; and the english combining unit 305 combines the contents other than all the pinyin dictation contents among the dictation contents as english dictation contents. Therefore, the invention can distinguish English from pinyin in dictation content, and realize accurate identification of dictation content, thereby improving accuracy of dictation correction.

Example IV

Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to another embodiment of the invention; the electronic device shown in fig. 4 is optimized based on the electronic device shown in fig. 3, and the electronic device shown in fig. 4 may further include:

a content correcting unit 306, configured to combine, in the english combining unit 305, the content other than all the pinyin dictation content in the dictation content, and after the content is used as the english dictation content, compare the pinyin dictation content with the correct dictation content to obtain a first error dictation content, and compare the english dictation content with the correct dictation content to obtain a second error dictation content, where the first error dictation content and the second error dictation content form an error dictation content;

A synonym identifying unit 307, configured to determine a synonym error content from the second error dictation content, where the chinese paraphrasing of the synonym error content matches the chinese paraphrasing of the correct dictation content corresponding to the synonym error content;

the first output unit 308 is configured to output the error dictation content and correct dictation content corresponding to the error dictation content, and annotate synonymous error content included in the error dictation content, so as to help a user identify the synonymous error content and correct dictation content corresponding to the synonymous error content;

the first collecting unit 309 is configured to output a prompt message to prompt a user to read the correct dictation content corresponding to the first error dictation content after the first output unit 308 outputs the error dictation content and the correct dictation content corresponding to the error dictation content, and collect pinyin audio generated by the user reading;

an audio analysis unit 310, configured to analyze an audio matching degree of the pinyin audio and the standard pinyin audio corresponding to the pinyin audio;

an error determining unit 311, configured to segment the first error dictation content into an initial part, a final part, and a tone part when the audio matching degree is smaller than a preset audio matching degree, and determine that the error part of the first error dictation content is the initial part, the final part, or the tone part according to the pinyin audio;

A second output unit 312 for outputting a correct pronunciation course of the error part, the correct pronunciation course including a pronunciation mouth shape, text notes, and pronunciation example audio;

an error statistics unit 313, configured to count first error dictation contents of the user and error parts of each first error dictation content, and analyze to obtain error pronunciation habits of the user;

a dialect matching unit 314, configured to find a dialect type matching with the incorrect pronunciation habit of the user in a dialect database, where the dialect database stores incorrect pronunciation habits and pronunciation correction methods corresponding to a plurality of dialect types;

a third output unit 315, configured to output a pronunciation correction method corresponding to the dialect type of the user, so as to help the user correct the incorrect pronunciation habit of the user;

a sentence generation unit 316 for generating a pronunciation detection sentence according to the incorrect pronunciation habit of the user;

a reading prompting unit 317, configured to output a pronunciation detection sentence when it is detected that the user does not perform any operation on the electronic device within a preset duration, and prompt the user to read the pronunciation detection sentence;

a second collection unit 318, configured to collect detection audio generated by the user reading the pronunciation detection sentence;

A pronunciation analysis unit 319 for analyzing whether a user's wrong pronunciation habit occurs when the user reads a pronunciation detection sentence according to the detection audio;

in addition, the third output unit 315 is further configured to output a pronunciation correction method corresponding to the dialect type of the user when the pronunciation analysis unit 319 analyzes that the user has a wrong pronunciation habit when reading the pronunciation detection sentence, so as to help the user correct the wrong pronunciation habit.

In the embodiment of the present invention, the content modifying unit 306 modifies the dictation content of the user to obtain the error dictation content, and the first output unit 308 outputs the modification result; further, the error determination unit 311 will determine that the user speaks such that the error portion, and the correct pronunciation course is output by the second output unit 312; the error statistics unit 313 may analyze the error pronunciation habit of the user after counting the first error dictation content of the user, and output a pronunciation correction method by the third output unit 315.

As an alternative embodiment, after the english combination unit 305 combines the contents other than all the pinyin dictation contents in the dictation contents as the english dictation contents, the content correcting unit 306 compares the pinyin dictation contents with the correct dictation contents to obtain a first error dictation content, and compares the english dictation contents with the correct dictation contents to obtain a second error dictation content, where the first error dictation content and the second error dictation content constitute an error dictation content; the synonym identifying unit 307 determines a synonym error content from the second error dictation content, the chinese paraphrasing of the synonym error content matching the chinese paraphrasing of the correct dictation content corresponding to the synonym error content; the first output unit 308 outputs the error dictation content and the correct dictation content corresponding to the error dictation content, and annotates the synonymous error content included in the error dictation content to help the user identify the synonymous error content and the correct dictation content corresponding to the synonymous error content. Specifically, the content correcting unit 306 compares the identified pinyin dictation content and the identified english dictation content with the correct dictation content, thereby obtaining an erroneous pinyin dictation content as a first error dictation content and an erroneous english dictation content as a second error dictation content; in addition, in the case of playing chinese audio and instructing the user to write english dictation content, there is a phenomenon that the english dictation content written by the user is different from the corresponding correct dictation content, but the chinese paraphrasing is the same, so after obtaining the second error dictation content, the synonym recognition unit 307 will also detect whether there is a second error dictation content that matches the chinese paraphrasing of the corresponding correct dictation content, for example, playing "good" chinese audio and instructing the user to write "good" english in the dictation, where "good" corresponds to english as "good", and the dictation content written by the user as "nice" and "nice" is determined as the second error dictation content, and the electronic device detects that "nice" matches the chinese paraphrasing of "good", the synonym recognition unit 307 determines "nice" in the second error dictation content as the error content; after the correction of the dictation content is completed, the first output unit 308 outputs the error dictation content composed of the first error dictation content and the second error dictation content and the corresponding correct dictation content, so that the user learns the error dictation content in real time; in addition, the synonymous dictation content in the error dictation content is annotated, and the annotation comprises the paraphrasing and example sentences of the synonymous dictation content and the corresponding correct dictation content, so that a user can distinguish the synonymous dictation content and the correct dictation content according to the annotation, and the user can be helped to correctly use the synonymous dictation content and the correct dictation content. Therefore, by carrying out dictation correction and outputting error dictation content and annotating synonymous error content, a user can be better helped to grasp the error dictation content.

As an alternative implementation manner, after the first output unit 308 outputs the error dictation content and the correct dictation content corresponding to the error dictation content, the first collecting unit 309 outputs a prompt message to prompt the user to read the correct dictation content corresponding to the first error dictation content, and collect pinyin audio generated by the user reading; the audio analysis unit 310 analyzes the audio matching degree of the pinyin audio and the standard pinyin audio corresponding to the pinyin audio; if the audio matching degree is smaller than the preset audio matching degree, the error determining unit 311 divides the first error dictation content into an initial part, a final part and a tone part, and determines that the error part of the first error dictation content is the initial part, the final part or the tone part according to the pinyin audio; the second output unit 312 outputs a correct pronunciation course of the error part, which includes a pronunciation mouth shape, text notes, and pronunciation example audio. Specifically, after the first output unit 308 outputs the error dictation content, the first collecting unit 309 will further output a prompt message on the screen to prompt the user to read the correct dictation content corresponding to the first error dictation content, after collecting the pinyin audio generated by the user reading, the audio analyzing unit 310 will analyze the audio matching degree of the pinyin audio and the standard audio, and if the pronunciation of the user when reading "h x o" is "h o", the audio matching degree of the user when reading "h x o" is assumed to be "h x o", and the analysis results in "h x o" is less than the preset audio matching degree, at this time, the error determining unit 311 analyzes from the pitch and other angles according to the pinyin audio of "h x o", and knows that the error portion of "h x o" is the pitch portion, and the second output unit 312 outputs the correct pronunciation course for the error portion, where the correct pronunciation mouth shape chart and the text annotation of the pinyin, and the pronunciation example audio of the pinyin, and the user can correct the error pronunciation of the user according to the correct pronunciation course.

As another alternative embodiment, the error statistics unit 313 counts the first error dictation contents of the user and the error portion of each first error dictation content, and analyzes to obtain the error pronunciation habit of the user; the dialect matching unit 314 searches a dialect database for the type of the dialect matched with the wrong pronunciation habit of the user, and the dialect database stores the wrong pronunciation habit and pronunciation correction method corresponding to a plurality of dialect types; the third output unit 315 outputs a pronunciation correction method corresponding to the dialect type of the user to help the user correct his own wrong pronunciation habit. Specifically, the mispronounced habit of the user is generally influenced by the native language and the dialect of the user, so that the type of the dialect of the user can be judged through the mispronounced habit; after the user performs dictation multiple times and generates a large amount of first error dictation content, the error statistics unit 313 may analyze the error pronunciation habit of the user according to the first error dictation content, and if the error pronunciation habit of the user is confusing the pronunciation of "n and l", the dialect matching unit 314 searches the dialect database that the dialect type of the user is a hunan dialect, and at this time, the third output unit 315 outputs a pronunciation correction method for the hunan dialect, including example audio and pronunciation teaching, so as to help the user get rid of the error pronunciation habit caused by the dialect when making a pronunciation.

As yet another alternative embodiment, the sentence generating unit 316 generates the pronunciation detection sentence according to the wrong pronunciation habit of the user; when it is detected that the user does not perform any operation on the electronic device within the preset time period, the reading prompting unit 317 outputs a pronunciation detection sentence and prompts the user to read the pronunciation detection sentence; the second acquisition unit 318 acquires detection audio generated by the user reading the pronunciation detection sentence; the pronunciation analysis unit 319 analyzes whether or not a user's wrong pronunciation habit occurs when the user reads a pronunciation detection sentence according to the detection audio; if so, the third output unit 315 performs a step of outputting a pronunciation correction method corresponding to the dialect type of the user to help the user correct the wrong pronunciation habit. Specifically, after the above-mentioned pronunciation correction method is outputted according to the incorrect pronunciation habit of the user, a pronunciation detection sentence generated for the incorrect pronunciation habit of the user is outputted during the idle period of the electronic device, for example, the incorrect pronunciation habit of the user confusing the pronunciation of "n, l" is generated, the pronunciation detection sentence "you are there, i'll" is generated, the detection audio of the pronunciation detection sentence is collected, if the incorrect pronunciation habit still appears in the detection audio, the steps in the previous embodiment are executed again, so as to help the user to master the correct pronunciation method.

Therefore, in the embodiment of the invention, the user is helped to timely master the error dictation content by correcting and outputting the error dictation content; in addition, the wrong pronunciation habit of the user can be accurately analyzed through the wrong dictation content, the corresponding pronunciation correction method is output to help the user to realize correct pronunciation, and the user experience is good.

Example five

Referring to fig. 5, fig. 5 is a schematic structural diagram of another electronic device according to another embodiment of the present invention. As shown in fig. 5, the electronically controllable device may include:

a memory 401 storing executable program codes;

a processor 402 coupled with the memory 401;

wherein the processor 402 invokes executable program code stored in the memory 401 to perform any one of the methods of fig. 1 and 2 for distinguishing between english and pinyin.

The embodiment of the invention discloses a computer readable storage medium storing a computer program, wherein the computer program causes a computer to execute any one of the methods for distinguishing English from Pinyin shown in FIG. 1 and FIG. 2.

The embodiments of the present invention also disclose a computer program product, wherein the computer program product, when run on a computer, causes the computer to perform some or all of the steps of the method as in the method embodiments above.

Those of ordinary skill in the art will appreciate that all or part of the steps of the various methods of the above embodiments may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (RandomAccess Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), or other optical disk Memory, magnetic disk Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.

The above describes in detail a method and an electronic device for distinguishing english from pinyin, which are disclosed in the embodiments of the present invention, and specific examples are applied herein to illustrate the principles and embodiments of the present invention, and the above description of the embodiments is only for helping to understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims (10)

1. A method for distinguishing between english and pinyin comprising:

acquiring dictation images corresponding to dictation contents;

dividing dictation content in the dictation image into a plurality of independent characters; the dictation content comprises English and Pinyin;

traversing each independent character, and identifying whether preset tone marks exist in a preset range of the independent character; the tone-symbol belongs to one of the plurality of independent characters;

if the independent characters exist, combining the independent characters and surrounding characters of the independent characters according to the pinyin formation rule, so as to obtain pinyin which accords with the pinyin formation rule and serve as pinyin dictation content;

and combining the contents except all the pinyin dictation contents in the dictation contents to serve as English dictation contents.

2. The method of claim 1, wherein after said combining of said dictation content other than all of said pinyin dictation content as english dictation content, said method further comprises:

comparing the Pinyin dictation content with the correct dictation content to obtain first error dictation content, and comparing the English dictation content with the correct dictation content to obtain second error dictation content, wherein the first error dictation content and the second error dictation content form error dictation content;

Determining synonymous error content from the second error dictation content, wherein the Chinese paraphrasing of the synonymous error content is matched with the Chinese paraphrasing of the correct dictation content corresponding to the synonymous error content;

outputting the error dictation content and the correct dictation content corresponding to the error dictation content, and annotating the synonymous error content included in the error dictation content to help a user to distinguish the synonymous error content and the correct dictation content corresponding to the synonymous error content.

3. The method of claim 2, wherein after said outputting said error dictation content and said correct dictation content corresponding to said error dictation content, said method further comprises:

outputting prompt information to prompt a user to read the correct dictation content corresponding to the first error dictation content, and collecting pinyin audio generated by the user;

analyzing the audio matching degree of the pinyin audio and the standard pinyin audio corresponding to the pinyin audio;

if the audio matching degree is smaller than the preset audio matching degree, dividing the first error dictation content into an initial consonant part, a vowel part and a tone part, and determining that the error part of the first error dictation content is the initial consonant part, the vowel part or the tone part according to the pinyin audio;

Outputting a correct pronunciation course of the error part, wherein the correct pronunciation course comprises a pronunciation mouth shape graph, a text annotation and pronunciation example audio.

4. A method according to claim 3, characterized in that the method further comprises:

counting first error dictation contents of the user and error parts of each first error dictation content, and analyzing to obtain error pronunciation habits of the user;

searching a dialect type matched with the wrong pronunciation habit of the user in a dialect database, wherein the dialect database stores the wrong pronunciation habit and pronunciation correction methods corresponding to a plurality of dialect types;

and outputting a pronunciation correction method corresponding to the dialect type of the user so as to help the user correct the wrong pronunciation habit of the user.

5. The method according to claim 4, wherein the method further comprises:

generating a pronunciation detection statement according to the incorrect pronunciation habit of the user;

when detecting that the user does not execute any operation on the electronic equipment within the preset time, outputting the pronunciation detection statement and prompting the user to read the pronunciation detection statement;

collecting detection audio generated by the user reading the pronunciation detection statement;

Analyzing whether the user has wrong pronunciation habit of the user when reading the pronunciation detection statement according to the detection audio;

and if the user appears, executing the pronunciation correction method corresponding to the dialect type of the user so as to help the user to correct the wrong pronunciation habit.

6. An electronic device, comprising:

the image acquisition unit is used for acquiring dictation images corresponding to the dictation content;

the character segmentation unit is used for segmenting dictation content in the dictation image into a plurality of independent characters; the dictation content comprises English and Pinyin;

a tone recognition unit for traversing each of the independent characters and recognizing whether a preset tone symbol exists in a preset range of the independent character; the tone-symbol belongs to one of the plurality of independent characters;

the pinyin combination unit is used for combining the independent characters and surrounding characters of the independent characters according to a pinyin composition rule when the preset tone symbols exist in the preset range of the independent characters, so that pinyin which accords with the pinyin composition rule is obtained and used as pinyin dictation content;

And the English combination unit is used for combining the contents except all the pinyin dictation contents in the dictation contents as English dictation contents.

7. The electronic device of claim 6, wherein the electronic device further comprises:

the content correcting unit is used for combining the content except all the pinyin dictation content in the dictation content by the English combining unit to serve as English dictation content, comparing the pinyin dictation content with correct dictation content to obtain first error dictation content, and comparing the English dictation content with the correct dictation content to obtain second error dictation content, wherein the first error dictation content and the second error dictation content form error dictation content;

the synonym identification unit is used for determining synonym error content from the second error dictation content, and the Chinese paraphrasing of the synonym error content is matched with the Chinese paraphrasing of the correct dictation content corresponding to the synonym error content;

the first output unit is used for outputting the error dictation content and the correct dictation content corresponding to the error dictation content, and annotating the synonymous error content included in the error dictation content so as to help a user to distinguish the synonymous error content and the correct dictation content corresponding to the synonymous error content.

8. The electronic device of claim 7, wherein the electronic device further comprises:

the first acquisition unit is used for outputting prompt information to prompt a user to read the correct dictation content corresponding to the first error dictation content after the first output unit outputs the error dictation content and the correct dictation content corresponding to the error dictation content, and acquiring pinyin audio generated by the user;

the audio analysis unit is used for analyzing the audio matching degree of the pinyin audio and the standard pinyin audio corresponding to the pinyin audio;

the error determining unit is used for dividing the first error dictation content into an initial consonant part, a final sound part and a tone part when the audio matching degree is smaller than a preset audio matching degree, and determining that the error part of the first error dictation content is the initial consonant part, the final sound part or the tone part according to the pinyin audio;

and the second output unit is used for outputting the correct pronunciation course of the error part, wherein the correct pronunciation course comprises a pronunciation mouth shape graph, a text annotation and pronunciation example audio.

9. The electronic device of claim 8, wherein the electronic device further comprises:

The error statistics unit is used for counting the first error dictation content of the user and the error part of each first error dictation content, and analyzing and obtaining the error pronunciation habit of the user;

the dialect matching unit is used for searching a dialect type matched with the wrong pronunciation habit of the user in a dialect database, and the dialect database stores the wrong pronunciation habit and pronunciation correction methods corresponding to a plurality of dialect types;

and the third output unit is used for outputting a pronunciation correction method corresponding to the dialect type of the user so as to help the user correct the wrong pronunciation habit.

10. The electronic device of claim 9, wherein the electronic device further comprises:

a sentence generating unit, configured to generate a pronunciation detection sentence according to the incorrect pronunciation habit of the user;

the reading prompting unit is used for outputting the pronunciation detection statement and prompting the user to read the pronunciation detection statement when detecting that the user does not execute any operation on the electronic equipment within a preset time period;

the second acquisition unit is used for acquiring detection audio generated by the user reading the pronunciation detection statement;

The pronunciation analysis unit is used for analyzing whether the user has wrong pronunciation habit of the user when reading the pronunciation detection statement according to the detection audio;

the third output unit is further configured to output a pronunciation correction method corresponding to the dialect type of the user when the user is analyzed to have the incorrect pronunciation habit of the user when the user reads the pronunciation detection sentence, so as to help the user correct the incorrect pronunciation habit.