CN113743102A

CN113743102A - Method and device for recognizing characters and electronic equipment

Info

Publication number: CN113743102A
Application number: CN202110950635.8A
Authority: CN
Inventors: 张铭阳; 蒋峰; 张志达; 胡晓雨; 张国鹏; 陈轶博; 高丰; 谢卓
Original assignee: Baidu Online Network Technology Beijing Co Ltd
Current assignee: Baidu Online Network Technology Beijing Co Ltd
Priority date: 2021-08-18
Filing date: 2021-08-18
Publication date: 2021-12-03
Anticipated expiration: 2041-08-18
Also published as: CN113743102B

Abstract

The disclosure provides a method and a device for recognizing characters and electronic equipment, and relates to the field of data processing, in particular to the field of word processing. The specific implementation scheme is as follows: acquiring at least one character to be recognized obtained after scanning a text to be recognized; displaying an initial recognition result of character error correction on at least one character to be recognized; responding to a selection instruction of at least one character to be recognized contained in the initial recognition result, and determining a target character from the at least one character to be recognized; and identifying the target character to obtain an identification result. Through the method and the device, the problem of low accuracy rate of character recognition in the prior art is at least solved.

Description

Method and device for recognizing characters and electronic equipment

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a method and an apparatus for recognizing characters, and an electronic device.

Background

With the development of internet technology, various text recognition devices have entered into people's daily life, and these text recognition devices can help people to perform quick scanning query of chinese and english, including: word searching, sentence searching and translation are beneficial to improving the working efficiency of people.

In the existing various common text recognition devices, when performing character recognition in a text, a user is first required to perform stroke scanning on the text by using a pen point, so that text contents shot by a camera on the pen point are spliced and subjected to OCR (optical character recognition), and then processes such as word searching, retrieving and translating are performed on OCR results, and a final recognition result is obtained.

However, the OCR result can only be recognized at a character level, that is, OCR follows the principle of what you see is what you get in the text recognition process, and does not perform any semantic correction and prediction of the real intention of the user.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The present disclosure provides a method, an apparatus, and an electronic device for recognizing characters, so as to at least solve the problem of low character recognition accuracy in the prior art.

According to an aspect of the present disclosure, there is provided a method of recognizing a character, including: acquiring at least one character to be recognized obtained after scanning a text to be recognized; displaying an initial recognition result of character error correction on at least one character to be recognized; and responding to a selection instruction of at least one character to be recognized contained in the initial recognition result, determining a target character from the at least one character to be recognized, and recognizing the target character to obtain a recognition result.

Further, the method for recognizing characters further comprises: and acquiring at least one character to be recognized obtained after the text scanning unit scans the file to be recognized, wherein the text recognition device at least comprises the text scanning unit and a text display unit, and the text display unit is at least used for displaying the initial recognition result, the target character and the recognition result.

Further, the method for recognizing characters further comprises: and identifying the target character to obtain an identification result, acquiring the semantic meaning of the target character in the text to be identified, and identifying the target character according to the semantic meaning to obtain the identification result.

Further, the method for recognizing characters further comprises: and displaying an initial recognition result obtained by performing natural language processing on at least one character to be recognized in a text display unit.

Further, the method for recognizing characters further comprises: before at least one character to be recognized obtained after a text to be recognized is scanned is acquired, when the text scanning unit scans abnormally, prompt information is displayed on a text display unit; and when the display duration of the prompt message is longer than the second preset duration, hiding the prompt message in the text display unit.

Further, the method for recognizing characters further comprises: detecting a character type corresponding to at least one character to be recognized before determining a target character from the at least one character to be recognized in response to a selection instruction of the at least one character to be recognized included in an initial recognition result; and responding to the splitting instruction of the at least one character to be recognized, and displaying the at least one split character after the splitting operation is carried out on the at least one character to be recognized according to the character type on the text display unit.

Further, the method for recognizing characters further comprises: splitting at least one character to be recognized according to any one or more of the following modes; splitting at least one character to be recognized based on characters contained in a preset word stock; splitting at least one character to be recognized according to the number of units contained in each character to be recognized, wherein each character to be recognized is composed of at least one unit; and splitting the at least one character to be recognized according to the word frequency of the at least one character to be recognized.

Further, the method for recognizing characters further comprises: detecting whether the semantics corresponding to the target characters exist in a preset word bank or not; when no semantics corresponding to the target character exist in the preset word bank, performing character adding operation and/or character deleting operation on the target character to obtain a first target character; and querying the semantic corresponding to the first target character in a preset word bank, and displaying the semantic corresponding to the first target character in a text display unit.

Further, the method for recognizing characters further comprises: detecting whether the semantics corresponding to the target characters exist in a preset word bank or not; when the semantics corresponding to the target characters exist in the preset word bank, highlighting the semantics corresponding to the target characters in the text display unit; performing character adding operation and/or character deleting operation on the target character to obtain a second target character; and querying the semantic meaning corresponding to the second target character in a preset word bank, and displaying the second target character and the semantic meaning corresponding to the second target character in a text display unit.

Further, the method for recognizing characters further comprises: and responding to the touch operation of the voice playing unit in the text recognition equipment, and playing the target character and/or the recognition result of the target character.

Further, the method for recognizing characters further comprises: and after detecting that the text scanning unit scans the at least one character, displaying the at least one character on the text display unit.

Further, the method for recognizing characters further comprises: acquiring the distance between a scanning unit of text recognition equipment and a text to be recognized; recording a first duration when the distance is greater than a preset distance; when the first time length is less than a first preset time length, acquiring a first character scanned by the text recognition device before the first time length and a second character scanned after the first time length; performing continuing processing on the first character and the second character to obtain at least one character to be recognized; at least one character to be recognized is displayed on the text display unit.

According to an aspect of the present disclosure, there is also provided an apparatus for recognizing a character, including: the acquisition module is used for acquiring at least one character to be recognized obtained after the text to be recognized is scanned; the display module is used for displaying an initial recognition result of character error correction of at least one character to be recognized; the response module is used for responding to a selection instruction of at least one character to be recognized contained in the initial recognition result and determining a target character from the at least one character to be recognized; and the identification module is used for identifying the target character to obtain the identification result.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for recognizing characters.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the above-described method of recognizing characters.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the above-described method of recognizing characters.

According to another aspect of the present disclosure, there is provided a text recognition apparatus including: the text scanning unit is used for scanning the text to be recognized to obtain at least one character to be recognized; the text recognition unit is used for performing character error correction processing on at least one character to be recognized, determining a target character from the character to be recognized after the character error correction processing, and recognizing the target character according to the semantic meaning of the target character in the text to be recognized to obtain a recognition result; and the text display unit is used for displaying at least one character to be recognized and a recognition result.

In the method, a mode of identifying a target character according to the semantic meaning of the target character in a text to be identified is adopted, and finally an identification result is displayed, at least one character to be identified obtained after the text to be identified is scanned is obtained, and an initial identification result of character error correction is displayed on the at least one character to be identified, so that a selection instruction of the at least one character to be identified contained in the initial identification result is responded, the target character is determined from the at least one character to be identified, and the target character is identified to obtain the identification result.

In the process, the text to be recognized is firstly scanned to obtain the characters to be recognized, the characters are corrected to obtain the target characters, the target characters are recognized again on the basis of the target characters according to the semantics of the target characters in the text to be recognized, so that the semantic correction is performed on the target characters, the real intention of a user is more accurately predicted, the corresponding display recognition result is given, the problem of low character recognition accuracy rate caused by the fact that the characters in the text to be recognized cannot be subjected to semantic recognition in the prior art is solved, and the effect of improving the use experience of the user is achieved.

Therefore, the scheme provided by the disclosure achieves the purpose of improving the character recognition accuracy rate, thereby realizing the technical effect of improving the user experience and further solving the problem of low character recognition accuracy rate in the prior art.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a flow chart of a method of recognizing characters according to embodiment 1 of the present disclosure;

FIG. 2 is a flow chart of a method of recognizing characters according to embodiment 1 of the present disclosure;

FIG. 3 is a flow chart of a method of recognizing characters according to embodiment 1 of the present disclosure;

FIG. 4 is a flow chart of a method of recognizing characters according to embodiment 1 of the present disclosure;

FIG. 5 is a flow chart of a method of recognizing characters according to embodiment 1 of the present disclosure;

FIG. 6 is a flow chart of a method of recognizing characters according to embodiment 1 of the present disclosure;

FIG. 7 is a schematic diagram of a method for recognizing characters according to embodiment 1 of the present disclosure;

FIG. 8 is a schematic diagram of a method for recognizing characters according to embodiment 1 of the present disclosure;

fig. 9 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

fig. 10 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

fig. 11 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

fig. 12 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

fig. 13 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

fig. 14 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

FIG. 15 is a schematic diagram of a method for recognizing characters according to embodiment 1 of the present disclosure;

fig. 16 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

fig. 17 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

fig. 18 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

fig. 19 is a schematic diagram of a method of recognizing characters according to embodiment 1 of the present disclosure;

fig. 20 is a schematic diagram of a character recognition prediction apparatus according to embodiment 2 of the present disclosure;

fig. 21 is a block diagram of an electronic device for implementing a method of recognizing characters according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and 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, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

In accordance with an embodiment of the present disclosure, there is provided an embodiment of a character recognition method, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.

In addition, it should be further noted that the method provided by the embodiment of the present disclosure may be applied to a text recognition device, where the text recognition device at least includes a text scanning unit and a text display unit.

Fig. 1 is a flowchart of a text recognition method according to an embodiment of the present disclosure, as shown in fig. 1, the method including the steps of:

step S102, at least one character to be recognized obtained after the text to be recognized is scanned is obtained.

In an alternative embodiment, the text to be recognized may be scanned by a text scanning device in the text recognition device, and the at least one character to be recognized is obtained, where the text scanning device may be a miniature camera, the text recognition device may be a dictionary pen, and the miniature camera is embedded in a pen point of the dictionary pen.

Optionally, as shown in fig. 2, a spring support is mounted on the pen head of the dictionary pen, and is used for fixing the pen head to prevent shaking. In addition, as shown in fig. 3, a pen point alignment line is further disposed on the pen point of the dictionary pen for approving the text content during the text recognition process. The user can use the dictionary pen to input the contents to be queried or translated in a click-press, single-line scanning, multi-line scanning mode and the like, obtain the corresponding content result, that is, read the character to be recognized, after reading the character to be recognized, the dictionary pen can further view or operate the character to be recognized, for example, the user clicks a pronunciation button on the dictionary pen to make a sentence pronounce, clicks a follow-up button to enter follow-up reading and the like, at this time, the process of reading the character to be recognized once can be called a user session control, and further, no matter the user performs the click-press operation, or performs the single-line scanning, the multi-line scanning and the like, the input of one user session control represents the user to perform a complete operation of inputting the text contents desired to be circled.

In addition, after one session control of the user is generated, the system of the dictionary pen can perform caching, and when the next session control is generated or the user clicks an entry such as a history record to enter a display interface of another session control, the previous session control caching is cleared. When the conversation control cache exists, operations such as searching or translation are carried out, and the dictionary pen reads the conversation control content in the cache and displays the conversation control content.

And step S104, displaying an initial recognition result of character error correction on at least one character to be recognized.

In an alternative embodiment, the user uses the dictionary pen to select the desired query/translation content on the physical material by way of dot-pressing, single-line scanning and multi-line scanning, wherein the physical material includes but is not limited to: books, newspapers, magazines, computer screens, etc. When a user wants to translate a section of words in a book, a dictionary pen is used for pressing the pen on the book to start scanning of a text, a pen point directrix is aligned to a starting center line of the text to be recognized on a solid material, a spring support leg of the pen point is pressed down, the pressing is kept and the pen point slides rightwards, in the sliding process, the center line of the text to be recognized of the pen point directrix slides to the right side of the last word of the text to be recognized, and then the pen is lifted to start scanning and reading of the text to be recognized until the reading is finished. Wherein a text display unit, e.g. a screen, is arranged on the dictionary pen. As shown in fig. 4, after the stylus is activated, a cursor in an initial state is displayed on the screen, and the cursor keeps flickering all the time during the scanning process. In addition, during the scanning process, the result of the scanning process may appear on the screen, and as shown in fig. 5, the cursor with the middle result may flash behind the last character.

Optionally, the text recognition device may perform character error correction on the character to be recognized, and perform character error correction of OCR on the character to be recognized during the sliding process of the text device to obtain an initial recognition result, for example, during the recognition process, a single word some is recognized as s0me (a letter o is recognized as a number 0), and the error correction is performed on the single word some into a correct english spelling some, so that the correct initial recognition result some is displayed on the text display unit.

It should be noted that, in step S104, the character to be recognized is subjected to character error correction to obtain an initial recognition result, so that the problem of character recognition errors is effectively avoided, and the character recognition accuracy is improved.

And step S106, responding to a selection instruction of at least one character to be recognized contained in the initial recognition result, and determining a target character from the at least one character to be recognized.

In an optional embodiment, the user may select the initial recognition result, and the text recognition device responds to a selection instruction, where the character to be recognized in the initial recognition result is subjected to character error correction, and the text recognition device may continue to select at least one character to be recognized included in the initial recognition result, where the selection process includes that the text recognition device performs error correction processing on the at least one character to be recognized through NLP (Neuro-linear Programming), and the user actively performs selection such as splitting on the at least one character to be recognized through the character recognition device, that is, the at least one character to be recognized included in the initial recognition result is reselected according to the user's intention to obtain a target character, and the target character is displayed in the text display unit.

Through the process, the character to be recognized is selected again on the basis of the initial recognition result, so that the target character is determined according to the predicted user intention, the true intention of the user is predicted more accurately, the corresponding displayed recognition result is given, and the effect of improving the character recognition accuracy is achieved.

And step S108, identifying the target character to obtain an identification result.

In an alternative embodiment, the text display unit may be configured to display the recognition result, where the text display unit may be a screen on the text recognition device, or may be another display device connected to the text recognition device, for example, a display screen with a projection function, where a target character is recognized according to the semantic meaning of the target character in the text to be recognized, and a recognition result is obtained, for example, when the target character is "after the mountain is whited", the target character is an ancient poetry sentence in the text to be recognized, and from the semantic point of view, the target character is split and recognized, and the interpretation is inaccurate, so that the embodiment of the present disclosure may follow the semantic meaning of the target character in the text to be recognized, interpret the target character as a sentence, and display the interpretation.

In the process, the target character is identified again according to the semantics of the target character in the text to be identified on the basis of the target character, so that the target character is corrected according to the voice, and the effect of improving the accuracy of corresponding paraphrasing of the character is realized.

Based on the schemes defined in steps S102 to S108, it can be known that, in the embodiment of the present disclosure, a manner of recognizing characters according to semantics of the characters in a text to be recognized is adopted, at least one character to be recognized obtained after scanning the text to be recognized is obtained, and an initial recognition result of performing character error correction on the at least one character to be recognized is displayed in a text display unit, so that a selection instruction of the at least one character to be recognized included in the initial recognition result is responded, a target character is determined from the at least one character to be recognized, and the target character is recognized, so that a recognition result is obtained.

It is easy to notice that, in the above process, the present disclosure scans the text to be recognized to obtain the character to be recognized, obtains the target character after correcting the error of the character, and recognizes the target character again according to the semantic meaning of the target character in the text to be recognized on the basis of the target character, thereby performing semantic error correction on the target character, predicting the real intention of the user more accurately and giving a corresponding display recognition result, and further solving the problem of low accuracy of character recognition in the prior art, and achieving the effect of improving the user experience.

In an alternative embodiment, the text recognition device displays at least one character on the text display unit after detecting that the at least one character is scanned by the text scanning unit.

Optionally, the text recognition device may detect the text by way of single line scanning, for example, the user holds the dictionary pen in the right hand, aligns the pen point directrix with the beginning central line of the text to be recognized on the solid material, presses down the pen point spring support, keeps pressing down and slides to the right, and the sliding process aligns the pen point with the central line of the text to be recognized, slides to the right of the last character of the text to be recognized, and lifts the pen. The user can inevitably hand tremble at the slip in-process and carry out the fluctuation, can effectively avoid trembling through the spring stabilizer blade on the nib.

In the process, the text recognition device can display the characters on the text display unit, so that the user can visually see the characters recognized by the text recognition device, the user can actively correct the characters, and the use experience of the user is improved.

In an optional embodiment, the text recognition device obtains at least one character to be recognized obtained after the text scanning unit scans the file to be recognized, where the text recognition device at least includes a text scanning unit and a text display unit, and the text display unit is at least used for displaying an initial recognition result, a target character, and a recognition result.

Optionally, the text scanning unit may be a miniature camera installed on the text recognition device, the miniature camera is used for photographing and scanning a text, and the text display unit may be a display screen installed on the text recognition device, or may be another display device connected to the text recognition device, for example, a display screen with a projection function.

The effect of intuitively displaying the initial recognition result, the target character and the recognition result is achieved through the text scanning unit and the text display unit.

In an optional embodiment, the text recognition device obtains semantics of the target characters in the text to be recognized, and recognizes the target characters according to the semantics to obtain a recognition result.

Optionally, the text recognition device may recognize the target character according to the semantic meaning of the target character in the text to be recognized, so as to obtain a recognition result, for example, when the target character is "as long as the mountain on a white day", the target character is an ancient poetry sentence in the text to be recognized, and from the semantic point of view, the target character is split, recognized and interpreted inaccurately, so that the embodiment of the present disclosure may interpret the target character as a sentence following the semantic meaning of the target character in the text to be recognized, and display the interpreted meaning.

In an optional embodiment, the text recognition device obtains a distance between a scanning unit of the text recognition device and the text to be recognized; recording a first duration when the distance is greater than a preset distance; when the first time length is less than a first preset time length, acquiring a first character scanned by the text recognition device before the first time length and a second character scanned after the first time length; performing continuing processing on the first character and the second character to obtain at least one character to be recognized; at least one character to be recognized is displayed on the text display unit.

Optionally, the text recognition device may detect the text by a multi-line scanning manner, as shown in fig. 6, when the text recognition device detects that the user has lifted the pen in the last scanning, a user session control is formed once, and a content of the first character "take" scanned by the user within a preset time period, for example, within 2 seconds, and a second character "away" is obtained, and then the recognition content and the content scanned last time are subjected to character continuation, as shown in fig. 7, so as to obtain at least one character "take" to be recognized, and the character "take" is displayed on the text display unit, and the condition of the multi-line text may also be determined whether to connect the characters according to the preset time period.

In addition, different from multi-line scanning, during the use of the text recognition device, there is often a click operation, that is, the pen is not slid after being pressed, and at this time, the text scanning device on the text recognition device, for example, a camera, may shoot a text to be recognized, where the shooting range is the preset distance, as shown in fig. 8, the preset distance may be set to 1.6 centimeters, and the camera may transmit recognition results of all characters in the shooting range to the text recognition device.

It should be noted that in the above process, the character to be recognized obtained after the multi-line scanning and the dot pressing operation can be displayed on the text display unit, and the multi-line scanning can improve the character recognition efficiency, and can be visually displayed to the user, thereby achieving the effect of improving the text detection efficiency.

In an alternative embodiment, the text recognition apparatus displays an initial recognition result obtained by natural language processing of at least one character to be recognized in the text display unit.

Alternatively, the initial recognition result displayed in the text display unit by the text recognition apparatus is obtained by natural language processing, wherein the natural language processing may be error correction processing by NLP (Neuro-linear Programming). For example, when the text recognition device gives the character to be recognized to the NLP, the predicted location of the user's intention can be performed twice, and the first presentation that appears after the user lifts the pen in a user session is the predicted location of the NLP on the user's first intention. When a user clicks a label or text word segmentation and word segmentation contents in a user session, the secondary intention of the NLP to the user is autonomously positioned.

Alternatively, as shown in fig. 9, the character recognition apparatus may add "dot-difference" marks to all characters to be recognized, so that the contents of the characters to be recognized may be referred to, for example, by looking up the characters to be recognized in a dictionary. If there is a query result, the query result is highlighted by default and interpreted, the specific process is as shown in fig. 10, the letter of the query result can be selected by the character recognition device, and sorted by calculating the length of the letter, if there is no result, the interpretation is directly performed, the sorting is performed, the most probable interpretation is placed at the forefront, the highlight is defaulted, and the guessing process of the user's intention can be guessed according to a word frequency system. In addition, the interpreted results should all be available for dictionary lookup or translation in a software development kit. And sorting according to word frequency. If the translation cannot be found or is not translated, a bottom-of-pocket page as shown in fig. 11 appears.

Optionally, as shown in fig. 12, the character recognition device may autonomously locate the secondary intention of the user through the NLP, for example, when the character to be recognized is "take off", the NLP queries in the dictionary, the character can be directly found, the character and the paraphrase in the dictionary are displayed, that is, the explanation, at this time, the user clicks the text area again, the text is participled as take off, and the label of "word" is added in front of the text area. When the character to be recognized is "s family d", the NLP queries in the dictionary, s, family and d can be found, the family is defaulted to be in a highlight mode (because the word frequency is highest), at this time, the user clicks the text area again, the text is participled to be s/family/d, the user clicks the label of the "sentence", the whole sentence can be translated, and thus, the NLP can autonomously position the secondary intention of the user, for example, judge whether the user wants to translate the whole sentence or the word.

It should be noted that, in the above process, natural language processing is performed on at least one character to be recognized, so that the real intention of the user is predicted more accurately, and a corresponding display recognition result is given, thereby solving the problem in the prior art that the accuracy of character recognition is low because semantic recognition cannot be performed on the character in the text to be recognized, and achieving the effect of improving the user experience.

In an optional embodiment, before reading at least one character to be recognized obtained after a text to be recognized is scanned by a text scanning unit, the text recognition device displays prompt information on a text display unit when the text scanning unit is abnormal in scanning; and when the display duration of the prompt message is longer than the second preset duration, hiding the prompt message in the text display unit.

Optionally, the text recognition device may display a prompt message on the text display unit when the text scanning unit scans abnormally, for example, as shown in fig. 13, if the user triggers the pressing and lifting of the pen tip spring support, but the dictionary pen does not recognize any content, the user may enter the input guide diagram and pop up the prompt message "unrecognized, please retry". And hiding the prompt message after the preset duration lasts, wherein the preset duration can be set to be 4 seconds.

In addition, the above-mentioned input guidance diagram may guide the user to use the text recognition device, for example, when there is no user session control cache when the user queries and translates the text to be recognized for the first time, as shown in fig. 14, the guidance diagram may guide the user how to perform operations to input, specifically including: returning to control labeling, schematic labeling and guiding characters, please align the pen point alignment to the character center line and scan as perpendicular as possible to the paper surface.

Through the process, the fault reason can be visually displayed for the user, the user can be operated and guided, and the use experience of the user can be improved.

In an optional embodiment, the text recognition device detects a character type corresponding to at least one character to be recognized before determining a target character from the at least one character to be recognized in response to a selection instruction of the at least one character to be recognized included in the initial recognition result; and responding to the splitting instruction of the at least one character to be recognized, and displaying the at least one split character after the splitting operation is carried out on the at least one character to be recognized according to the character type on the text display unit.

Optionally, the character recognition device may detect a character type of the character to be recognized, respond to the splitting instruction of the recognized character, and display, on the text display unit, the at least one split character obtained by splitting the at least one character to be recognized according to the character type.

Optionally, as shown in fig. 15, the character to be recognized may be split through a node word splitting tree policy, where the node word splitting tree performs NLP on the OCR result scanned by the user, and then performs policy logic for unlimited downward splitting and searching based on a local dictionary, as shown in fig. 15, a sentence splitting unit "I connected the report as a possible" is split, and when the user clicks the sentence, the sentence is split into a plurality of phrases "I", "connected", "the", "report", "possible", and the phrase is split into a plurality of minimum units (words) by the user. Therefore, the translation from a sentence to each phrase and then to a word is realized, and the experience of infinite splitting is provided for the user.

In addition, the text recognition device also supports line feed logic, that is, as shown in fig. 17, before the user performs the operation of splitting the character to be recognized, the character to be recognized is displayed in multiple lines, and after the user clicks to split the character to be recognized, as shown in fig. 18, the character to be recognized is changed from multiple lines into one line, and left-right sliding viewing can be supported.

Through the process, the character recognition equipment can split the character to be recognized, so that the semantic unit is split into a plurality of minimum units, sentences, phrases and words in the splitting process are retrieved and translated, and the character query speed is improved.

In an optional embodiment, the text recognition device performs a splitting operation on at least one character to be recognized according to any one or more of the following manners; splitting at least one character to be recognized based on characters contained in a preset word stock; splitting at least one character to be recognized according to the number of units contained in each character to be recognized, wherein each character to be recognized is composed of at least one unit; and splitting the at least one character to be recognized according to the word frequency of the at least one character to be recognized.

Optionally, the preset lexicon may be a chinese vocabulary entry lexicon, including but not limited to: Chinese-Chinese dictionary, concise Chinese-English dictionary; or an english vocabulary entry library, including but not limited to: oxford dictionary and concise English-Chinese dictionary

The text recognition equipment splits at least one character to be recognized based on characters contained in a preset word bank, wherein dictionary entries in the preset word bank are preferred, namely split units can be searched in a local dictionary; the text recognition equipment performs splitting operation on at least one character to be recognized according to the number of units contained in each character to be recognized, wherein the splitting operation can be performed from high to low according to the minimum number of units contained in each character to be recognized, and the splitting operation is preferentially performed to form characters with high number of words; the text recognition device performs splitting operation on at least one character to be recognized according to the word frequency of the at least one character to be recognized, wherein the splitting operation can be performed according to a principle that the word frequency is from high to low.

Optionally, as shown in fig. 16, one splitting unit may be a semantic unit that can be split by the node word-number-of-segment policy, for example, a sentence "i want to design a drawing" in fig. 16. A minimum unit, which may be a chinese character, such as "i" or "i" in fig. 16, or a continuous alphabetic character string with spaces before and after an english character, if the content of scan recognition is sfamily d, then three english minimum units, s/family/d. And the splitting mode can be backward recursive splitting, namely, multi-layer splitting is carried out from backward to forward until the minimum unit is split. The character recognition equipment can make the characters to be recognized (including punctuations) output by the OCR and the NLP into a splitting tree through a node word-dividing number strategy, so that the characters to be recognized are split according to the principle that the word frequency is from high to low.

Through the process, the character recognition equipment can be infinitely split to the minimum unit when the user performs secondary intention positioning, so that the effect of improving the character query speed is realized.

In an optional embodiment, the text recognition device detects whether semantics corresponding to the target characters exist in a preset word bank; when no semantics corresponding to the target character exist in the preset word bank, performing character adding operation and/or character deleting operation on the target character to obtain a first target character; and querying the semantic corresponding to the first target character in a preset word bank, and displaying the semantic corresponding to the first target character in a text display unit.

Optionally, when the text recognition device detects whether the semantic corresponding to the target character exists in the preset word bank, and the semantic corresponding to the target character does not exist in the preset word bank, the text recognition device performs character adding operation and/or character deleting operation on the target character to obtain the first target character, for example, when the target character is "hoeing sunday", the text recognition device does not detect the corresponding semantic in the preset word bank, and the added character can be automatically supplemented to be "hoeing sunday and midday", that is, the first target character is obtained. If the target character is 'white day best mountain' and is directly obtained by searching in the poetry dictionary as shown in fig. 12, the corresponding semantic meaning is directly displayed in the text display unit.

Through the process, when the semanteme corresponding to the target character does not exist in the preset word bank, the character adding operation and/or the character deleting operation are/is carried out on the target character, the fault tolerance rate of a user can be improved, and when the character is lost or irrelevant characters are added, the character recognition equipment can automatically add or delete the characters, so that the fault tolerance rate of the user can be improved, and the effect of improving the accuracy of correct matching semanteme of character recognition is realized.

In an optional embodiment, the text recognition device detects whether semantics corresponding to the target characters exist in a preset word bank; when the semantics corresponding to the target characters exist in the preset word bank, highlighting the semantics corresponding to the target characters in the text display unit; performing character adding operation and/or character deleting operation on the target character to obtain a second target character; and querying the semantic meaning corresponding to the second target character in a preset word bank, and displaying the second target character and the semantic meaning corresponding to the second target character in a text display unit.

Optionally, the text display unit highlights semantics corresponding to the target character, which may be highlight mode display of a speech, where the preset lexicon includes but is not limited to: the online software development kit for Chinese-to-Chinese dictionary, Chinese-to-English dictionary, English-to-Chinese dictionary, Chinese-to-English translation and offline software development kit for Chinese-to-English translation are characterized in that various preset word banks can be ordered, for example, when target characters hit a plurality of dictionaries, the results are displayed in the following sequence: in the Chinese dictionary, when a target character hits a poetry text or a title, the poetry dictionary is explained as the first place, then a Chinese-to-Chinese dictionary is used, and finally a Chinese-to-English dictionary is used; in the english dictionary, the first digit is the english-chinese dictionary and then the english-english dictionary. In addition, when the text recognition device is on-line, a Chinese-English translation on-line software development kit is called, and when the text recognition device is off-line, a Chinese-English translation off-line software development kit is called.

The text recognition device to be described can perform character adding operation and/or character deleting operation on the target character to obtain a second character, and further query the semantic corresponding to the second target character, so that the fault tolerance rate of a user can be improved, and the effect of improving the accuracy of correct matching of the character recognition and the semantic is realized.

In an alternative embodiment, the text recognition device plays the target character and/or the recognition result of the target character in response to a touch operation of a voice playing unit in the text recognition device.

Optionally, the user may click a pronunciation button of the text recognition device to pronounce the target character and/or the recognition result of the target character, and click a read-after button to enter read-after, wherein the text recognition device may also pronounce automatically, the text recognition device recalls the content presentation directly after a user session control operation, and whether the pronunciation is given in the process depends on whether the user sets automatic pronunciation in the text recognition device. Wherein, the automatic pronunciation can pronounce the content language input by the user. When the input content is English, even if the user sets English pronunciation, the English pronunciation can be used when the English real person audio recall result exists in the preset dictionary, and if the English real person audio does not exist, the American pronunciation of the off-line TTS (Text To Speech, from Text To Speech) is used. Among them, the pronunciation button includes but is not limited to: pinyin button, English sound/American sound button and original text/translation button

Through the process, the text recognition device can play the target characters and/or the recognition results of the target characters through the voice playing unit, and in some special scenes, for example, visually-impaired people can acquire information or read contents in books for infants, the text recognition device can be used for completing conversion from characters to voice, so that the applicability of the text recognition device is improved.

Fig. 19 shows a flow chart of a character recognition method according to embodiment 1 of the present disclosure, so as to further explain the overall operation flow of the embodiment of the present disclosure, which is specifically described as follows:

optionally, when the text recognition device handles a user session control, an input operation of recognizing a user and content of a text to be recognized are performed first, where the input operation of the user includes: and identifying the content of the text to be identified through OCR by utilizing the processing strategies corresponding to the various operations. Firstly, carrying out first prediction positioning on the user intention through the NLP, carrying out default highlighting on the character to be recognized after prediction is finished, then endowing a parameter value to the character to be recognized, adding a 'click' label, explaining the character to be recognized by hearing the 'click' label to obtain a corresponding paraphrase, adding labels such as 'sentence' and 'word' to the character to be recognized, and carrying out splitting operation on the character to be recognized by the user to carry out secondary intention confirmation, wherein when secondary intention confirmation is carried out, active highlighting is carried out on the character to be recognized according to user selection.

Further, the character recognition device carries out calling and recalling operations on the characters, wherein the calling is an action that the character recognition device inquires a local or cloud preset dictionary through the target characters so as to obtain corresponding paraphrases or translation results in the preset dictionary. And recalling the action of returning the query result to the character recognition equipment for the preset dictionary in the local or cloud. Wherein, preset dictionary can be chinese-chinese dictionary, chinese-english dictionary, english-chinese dictionary, chinese-english translation online software development kit and chinese-english translation off-line software development kit to set up the priority to different preset dictionaries, show it, include: text display, audio play, TTS play, sentence follow-up reading, collection and the like. The word recognition device is provided with corresponding buttons for the display function.

Through the process, the scheme provided by the embodiment of the disclosure achieves the purpose of improving the character recognition accuracy, thereby realizing the technical effect of improving the user experience, and further solving the problem of low character recognition accuracy in the prior art.

Example 2

According to an embodiment of the present disclosure, there is also provided an embodiment of an apparatus for recognizing a character, where fig. 20 is a schematic diagram of an apparatus for recognizing a character according to embodiment 2 of the present disclosure, the apparatus including: an obtaining module 2001, configured to obtain at least one character to be recognized, where the character is obtained by scanning a text to be recognized; a display module 2003, configured to display an initial recognition result obtained by performing character error correction on at least one character to be recognized; a response module 2005, configured to determine, in response to a selection instruction for at least one to-be-recognized character included in the initial recognition result, a target character from the at least one to-be-recognized character; the recognition module 2007 is configured to recognize the target character to obtain a recognition result.

It should be noted that the acquiring module 2001, the displaying module 2003, the responding module 2005, and the identifying module 2007 correspond to steps S102 to S108 in the above embodiment, and the four modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the disclosure in embodiment 1.

Optionally, the apparatus for recognizing characters further includes: a detection module to: and after detecting that the text scanning unit scans the at least one character, displaying the at least one character on the text display unit.

Optionally, the apparatus for recognizing characters further includes: the device comprises a first acquisition module, a second acquisition module, a connection module and a first display module, wherein the first acquisition module is used for acquiring the distance between a scanning unit of text recognition equipment and a text to be recognized; the second acquisition module is used for recording a first duration when the distance is greater than the preset distance; the text recognition device comprises a continuing module, a judging module and a judging module, wherein the continuing module is used for acquiring a first character scanned by the text recognition device before a first time length and a second character scanned after the first time length when the first time length is smaller than the first preset time length; the first display module is used for carrying out continuing processing on the first character and the second character to obtain at least one character to be recognized; at least one character to be recognized is displayed on the text display unit.

Optionally, the display module further includes: and the processing module is used for displaying an initial recognition result obtained by performing natural language processing on at least one character to be recognized in the text display unit.

Optionally, the apparatus for recognizing characters further includes: the device comprises a first display module and a first processing module. The first display module is used for displaying prompt information on the text display unit when the text scanning unit scans abnormally before reading at least one character to be recognized obtained after the text scanning unit scans the text to be recognized; and the first processing module is used for hiding the prompt message in the text display unit when the display duration of the prompt message is longer than the second preset duration.

Optionally, the apparatus for recognizing characters further includes: the device comprises a first detection module and a first response module, wherein the first detection module is used for detecting a character type corresponding to at least one character to be recognized before a target character is determined from the at least one character to be recognized in response to a selection instruction of the at least one character to be recognized contained in an initial recognition result; and the first response module is used for responding to the splitting instruction of the at least one character to be recognized and displaying the at least one split character after the splitting operation is carried out on the at least one character to be recognized according to the character type on the text display unit.

Optionally, the apparatus for recognizing characters further includes: the device comprises a first splitting module, a second splitting module and a third splitting module. The first splitting module is used for splitting at least one character to be recognized based on characters contained in a preset word stock; the second splitting module is used for splitting at least one character to be recognized according to the number of units contained in each character to be recognized, wherein each character to be recognized is composed of at least one unit; and the third splitting module is used for splitting at least one character to be recognized according to the word frequency of the at least one character to be recognized.

Optionally, the identification module further includes: the system comprises a second detection module, a first adding and deleting module and a query module. The second detection module is used for detecting whether the semantics corresponding to the target characters exist in the preset word bank or not; when no semantics corresponding to the target character exist in the preset word bank, performing character adding operation and/or character deleting operation on the target character to obtain a first target character; and the query module is used for querying the semantic corresponding to the first target character in the preset word bank and displaying the semantic corresponding to the first target character in the text display unit.

Optionally, the identification module further includes: the device comprises a third detection module, a second adding and deleting module, a second display module and a first query module. The third detection module is used for detecting whether the semantics corresponding to the target characters exist in the preset word bank or not; the second display module is used for highlighting the semantics corresponding to the target characters in the text display unit when the semantics corresponding to the target characters exist in the preset word bank; the second adding and deleting module performs character adding operation and/or character deleting operation on the target character to obtain a second target character; and the first query module is used for querying the semantic meaning corresponding to the second target character in the preset word bank and displaying the second target character and the semantic meaning corresponding to the second target character in the text display unit.

Optionally, the apparatus for recognizing characters further includes: and the second response module is used for responding to the touch operation of the voice playing unit in the text recognition equipment and playing the target character and/or the recognition result of the target character.

Optionally, the obtaining module further includes: the third acquisition module is used for acquiring at least one character to be recognized obtained after the text scanning unit scans the file to be recognized, wherein the text recognition device at least comprises a text scanning unit and a text display unit, and the text display unit is at least used for displaying an initial recognition result, a target character and a recognition result.

Optionally, the display module further includes: the device comprises a fourth acquisition module and a first identification module. The fourth acquisition module is used for acquiring the semantics of the target character in the text to be recognized; and the first recognition module is used for recognizing the target character according to the semantic meaning to obtain a recognition result.

Example 3

According to another aspect of the embodiments of the present disclosure, there is also provided an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to perform the method of recognizing characters of embodiment 1 described above.

Example 4

According to another aspect of the embodiments of the present disclosure, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of recognizing characters in embodiment 1 above.

Example 5

According to another aspect of the embodiments of the present disclosure, there is also provided a computer program product including a computer program, which when executed by a processor, implements the method of recognizing characters in embodiment 1 described above.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.

Fig. 21 shows a schematic block diagram of an example electronic device 800 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 21, the apparatus 800 includes a computing unit 801 that can perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The calculation unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

A number of components in the device 800 are connected to the I/O interface 805, including: an input unit 806, such as a keyboard, a mouse, or the like; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, or the like; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Computing unit 801 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 801 executes the respective methods and processes described above, such as the prediction method of the vehicle trajectory. For example, in some embodiments, the method of predicting vehicle trajectories may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and/or installed onto device 800 via ROM 802 and/or communications unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the vehicle trajectory prediction method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the prediction method of the vehicle trajectory in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

Example 6

According to another aspect of the embodiments of the present disclosure, there is also provided a text recognition apparatus including: the text scanning unit is used for scanning the text to be recognized to obtain at least one character to be recognized; the text recognition unit is used for performing character error correction processing on at least one character to be recognized, determining a target character from the character to be recognized after the character error correction processing, and recognizing the target character according to the semantic meaning of the target character in the text to be recognized to obtain a recognition result; and the text display unit is used for displaying at least one character to be recognized and a recognition result.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method of recognizing a character, the method comprising:

acquiring at least one character to be recognized obtained after scanning a text to be recognized;

displaying an initial recognition result of character error correction on the at least one character to be recognized;

responding to a selection instruction of at least one character to be recognized contained in the initial recognition result, and determining a target character from the at least one character to be recognized;

and identifying the target character to obtain the identification result.

2. The method of claim 1, wherein obtaining at least one character to be recognized obtained after scanning a text to be recognized comprises: and acquiring at least one character to be recognized obtained after the text to be recognized is scanned by the text scanning unit, wherein the text recognition device at least comprises the text scanning unit and a text display unit, and the text display unit is at least used for displaying the initial recognition result, the target character and the recognition result.

3. The method of claim 1, wherein recognizing the target character to obtain the recognition result comprises:

obtaining the semantics of the target character in the text to be recognized;

and identifying the target character according to the semantics to obtain the identification result.

4. The method of claim 2, wherein the displaying an initial recognition result of the character error correction of the at least one character to be recognized comprises:

and displaying an initial recognition result obtained by performing natural language processing on the at least one character to be recognized in the text display unit.

5. The method of claim 2, before obtaining at least one character to be recognized obtained after scanning a text to be recognized, the method further comprising:

when the text scanning unit is abnormal in scanning, prompt information is displayed on the text display unit;

and when the display duration of the prompt message is longer than a second preset duration, hiding the prompt message in the text display unit.

6. The method according to claim 2, before determining a target character from at least one character to be recognized included in the initial recognition result in response to a selection instruction for the at least one character to be recognized, the method further comprising:

detecting a character type corresponding to the at least one character to be recognized;

and responding to the splitting instruction of the at least one character to be recognized, and displaying at least one split character obtained after the splitting operation is carried out on the at least one character to be recognized according to the character type on the text display unit.

7. The method of claim 6, further comprising:

splitting the at least one character to be recognized according to any one or more of the following modes;

splitting the at least one character to be recognized based on characters contained in a preset word stock;

splitting the at least one character to be recognized according to the number of units contained in each character to be recognized, wherein each character to be recognized is composed of at least one unit;

and splitting the at least one character to be recognized according to the word frequency of the at least one character to be recognized.

8. The method of claim 2, wherein the recognizing the target character to obtain the recognition result comprises:

detecting whether the semantics corresponding to the target characters exist in a preset word bank or not;

when the semantics corresponding to the target characters do not exist in the preset word stock, performing character adding operation and/or character deleting operation on the target characters to obtain first target characters;

and querying the semantic meaning corresponding to the first target character in the preset word bank, and displaying the semantic meaning corresponding to the first target character in the text display unit.

9. The method of claim 2, wherein the recognizing the target character to obtain the recognition result comprises:

when the semantics corresponding to the target characters exist in the preset word bank, highlighting the semantics corresponding to the target characters in the text display unit;

performing character adding operation and/or character deleting operation on the target character to obtain a second target character;

and querying the semantic meaning corresponding to the second target character in the preset word bank, and displaying the second target character and the semantic meaning corresponding to the second target character in the text display unit.

10. The method of claim 2, after the identifying the target character, the method further comprising:

and responding to the touch operation of a voice playing unit in the text recognition equipment, and playing the target character and/or the recognition result of the target character.

11. The method of claim 2, further comprising:

after detecting that at least one character is scanned by the text scanning unit, displaying the at least one character on the text display unit.

12. The method of claim 2, further comprising:

acquiring the distance between a scanning unit of the text recognition device and the text to be recognized;

recording a first duration of the distance greater than a preset distance;

when the first time length is less than a first preset time length, acquiring a first character scanned by the text recognition device before the first time length and a second character scanned after the first time length;

continuing the first character and the second character to obtain the at least one character to be recognized;

and displaying the at least one character to be recognized on the text display unit.

13. An apparatus for recognizing characters, the apparatus comprising:

the acquisition module is used for acquiring at least one character to be recognized obtained after the text to be recognized is scanned;

the display module is used for displaying an initial recognition result of character error correction of the at least one character to be recognized;

the response module is used for responding to a selection instruction of at least one character to be recognized contained in the initial recognition result and determining a target character from the at least one character to be recognized;

and the identification module is used for identifying the target character to obtain the identification result.

14. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of identifying characters as claimed in any one of claims 1 to 12.

15. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of recognizing a character according to any one of claims 1 to 12.

16. A computer program product comprising a computer program which, when executed by a processor, implements a method of recognizing a character according to any one of claims 1 to 12.

17. A text recognition apparatus comprising:

the text scanning unit is used for scanning the text to be recognized to obtain at least one character to be recognized;

the text recognition unit is used for performing character error correction processing on the at least one character to be recognized, determining a target character from the at least one character to be recognized after the character error correction processing, and recognizing the target character according to the semantic meaning of the target character in the text to be recognized to obtain a recognition result;

and the text display unit is used for displaying the at least one character to be recognized and the recognition result.