CN116755821A

CN116755821A - Display method and device, handheld reader and electronic equipment

Info

Publication number: CN116755821A
Application number: CN202310731365.0A
Authority: CN
Inventors: 王晓斐; 朱翠玲; 汪恒; 陈鑫; 黄晓旭
Original assignee: Anhui Toycloud Technology Co Ltd
Current assignee: Anhui Toycloud Technology Co Ltd
Priority date: 2023-06-16
Filing date: 2023-06-16
Publication date: 2023-09-15

Abstract

The invention provides a display method, a device, a handheld reader and an electronic device, wherein the method comprises the following steps: acquiring an image acquired by the handheld reader, and performing character recognition on the image to obtain a recognition result; displaying candidate characters with pronunciation matched with the pronunciation character string under the condition that the recognition result comprises the pronunciation character string; and receiving a designated operation, determining a target character corresponding to the designated operation from the candidate characters, and displaying character information of the target character. The display method, the display device, the handheld reader and the electronic equipment provided by the invention can enable a user to obtain target characters to be queried according to the pronunciation character string, increase the selectable range of character input and improve the user experience.

Description

Display method and device, handheld reader and electronic equipment

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a display method, a device, a handheld reader, and an electronic apparatus.

Background

With the development of digital, informationized and intelligent technologies, more and more people begin to use intelligent devices for work, learning and entertainment. Dictionary pens have become a popular learning tool as a portable intelligent device integrating various functions such as electronic dictionary, translation, recording, etc. However, at present, the dictionary pen only supports displaying the characters obtained by scanning and the related translation and explanation contents thereof, and when a user encounters characters which cannot be written or forgets how to write the characters, a feasible query mode cannot be given, so that the user experience is affected.

Disclosure of Invention

The invention provides a display method, a device, a handheld reader and electronic equipment, which are used for solving the problem that a user cannot inquire corresponding characters when encountering characters which cannot be written or forgetting how to write the characters in the prior art.

The invention provides a display method, which is applied to a handheld reader, and comprises the following steps:

acquiring an image acquired by the handheld reader, and performing character recognition on the image to obtain a recognition result;

displaying candidate characters with pronunciation matched with the pronunciation character string under the condition that the recognition result comprises the pronunciation character string;

and receiving a designated operation, determining a target character corresponding to the designated operation from the candidate characters, and displaying character information of the target character.

According to the display method provided by the invention, the candidate characters for displaying the pronunciation and the pronunciation character string match comprise the following steps:

determining a current mode from the pronunciation mode and the text mode;

and displaying candidate characters with pronunciation matched with the pronunciation character string under the condition that the current mode is the character mode.

According to the display method provided by the invention, the current mode is determined from the pronunciation mode and the text mode, and the display method comprises the following steps:

And determining the current mode from the pronunciation mode and the text mode based on the historical display frequency of the pronunciation mode and the text mode and/or the preset priority of the pronunciation mode and the text mode.

According to the display method provided by the invention, the method further comprises the following steps:

receiving a mode switching operation;

and switching the current mode in response to the mode switching operation.

According to the display method provided by the invention, the candidate characters with the pronunciation matched with the pronunciation character string are displayed, and the display method further comprises the following steps:

determining candidate characters at each character position based on the probability that each character position in the recognition result belongs to each preset pronunciation character respectively, and combining the candidate characters at each character position to obtain at least one candidate pronunciation character string;

the pronunciation character string is determined based on the at least one candidate pronunciation character string.

acquiring candidate pronunciations of the pronunciation character string under different tones;

and displaying the candidate pronunciation under the different tones and the candidate characters with the pronunciation matched with at least one candidate pronunciation.

acquiring the learning progress of the current user of the handheld reader;

and sequencing the candidate characters based on whether the candidate characters are in the raw character set under the learning progress or not, and displaying the sequenced candidate characters.

The invention also provides a display device for use in a handheld reader, the device comprising:

the identification unit is used for acquiring the image acquired by the handheld reader, and carrying out character identification on the image to obtain an identification result;

the first display unit is used for displaying candidate characters with pronunciation matched with the pronunciation character string when the identification result comprises the pronunciation character string;

and the second display unit is used for receiving the appointed operation, determining the target text corresponding to the appointed operation from the candidate text, and displaying the text information of the target text.

The invention also provides a handheld reader, which comprises a camera, a processor, a display screen and an interaction interface, wherein the camera, the processor and the display screen are sequentially connected;

the camera is used for collecting images and transmitting the images to the processor;

The processor is used for carrying out character recognition on the image to obtain a recognition result, and displaying candidate characters with pronunciation matched with the pronunciation character string on the basis of the display screen under the condition that the recognition result comprises the pronunciation character string;

the interaction interface is used for receiving a specified operation and transmitting the specified operation to the processor;

the processor is further used for determining target characters corresponding to the specified operation from the candidate characters and displaying character information of the target characters based on the display screen.

The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the presentation method as described in any one of the above when executing the program.

The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a presentation method as described in any of the above.

The invention also provides a computer program product comprising a computer program which, when executed by a processor, implements a method of presentation as described in any of the above.

According to the display method, the device, the handheld reader and the electronic equipment, the acquired images are subjected to character recognition, and the candidate characters matched with the pronunciation character string are displayed under the condition that the recognition result of the character recognition comprises the pronunciation character string, so that the target characters to be queried can be determined based on the candidate characters, the input mode of character input based on the pronunciation is realized in a scanning mode, a user can obtain the target characters to be queried according to the pronunciation character string, the selectable range of character input is increased, and the user experience is improved.

Drawings

In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a display method provided by the invention;

FIG. 2 is a schematic flow chart of step 120 in the display method provided by the present invention;

FIG. 3 is a schematic diagram of a handheld reader showing candidate text provided by the present invention;

FIG. 4 is a schematic view of a display device according to the present invention;

FIG. 5 is a schematic diagram of a handheld reader provided by the present invention;

fig. 6 is a schematic structural diagram of an electronic device provided by the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, 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.

The dictionary pen, which is a learning tool capable of helping people to quickly fetch/search words, adopts OCR (optical character recognition, optical symbol recognition) technology and an embedded translation system, replaces the key input mode of the traditional electronic dictionary with a scanning mode, and can quickly and accurately fetch/search words. For unrecognized new words such as Chinese words and English words, students can obtain the pronunciation, meaning, translation and other information of the new words by only slightly sweeping with a dictionary pen, and the operation is simple and convenient.

With the development of scientific technology, the dictionary pen is used as a portable handheld reader, and great convenience is brought to students' study. However, when the dictionary pen is used for scanning the pinyin, only the content related to the pinyin, such as pronunciation, initials, finals, tones, spelling methods and the like, can be obtained, but the function of scanning the pinyin to inquire about the corresponding Chinese characters cannot be realized.

In this regard, the embodiment of the present invention provides a display method, which can display candidate characters matching the pronunciation with the pronunciation character string based on the collected and identified pronunciation character string, so as to determine the target characters to be queried based on the candidate characters, so that the user can obtain the content to be queried, thereby overcoming the above problems.

Fig. 1 is a schematic flow chart of a display method provided by the invention, as shown in fig. 1, the method is applied to a handheld reader, and the method comprises the following steps:

step 110, acquiring an image acquired by a handheld reader, and performing character recognition on the image to obtain a recognition result;

It should be noted that, the display method of the embodiment of the present invention is applied to a handheld reader, where the handheld reader is a portable electronic device having functions of image acquisition, character recognition on images, and displaying corresponding information, and the handheld reader may be, for example, a dictionary pen, a translation pen, a scanning pen, etc., which is not particularly limited in the embodiment of the present invention.

Specifically, the handheld reader may include an image capturing device, such as a camera, and when capturing an image, the camera may be used to capture characters on a medium (such as paper or a screen) to obtain a captured image, where the captured image refers to an image to be subjected to character recognition, and may be a pronunciation character string image, such as a pinyin image, a phonetic symbol image, or the like, may also be a Chinese character image, or may also be an english word image.

After the image is obtained, character recognition can be carried out on the image by utilizing an OCR technology, and the character recognition can be carried out on the image by adopting a text recognition technology based on deep learning, so that a recognition result is obtained. Here, the recognition result may include a pronunciation character string, a chinese character, an english word, and the like. The pronunciation character string refers to a character string form in which Chinese characters or other characters are represented by phonetic letters or phonetic symbols, for example, chinese character love can be represented by the pronunciation character string of 'a i'; english word "hello" can be used as pronunciation character string To represent.

Step 120, displaying candidate characters with pronunciation matched with the pronunciation character string when the recognition result comprises the pronunciation character string;

specifically, when the user collects an image of the pronunciation character string by using the handheld reader, the obtained recognition result includes the pronunciation character string, and at this time, candidate characters with pronunciation matching the pronunciation character string can be displayed to the user. For example, when a user encounters a Chinese character which cannot be written, the corresponding pronunciation character string is written on the exercise book, the pronunciation character string refers to pinyin, an image of the pronunciation character string is collected through a handheld reader, character recognition is carried out on the image, an obtained recognition result is the pronunciation character string, automatic matching is carried out on the basis of the pronunciation character string, one or more Chinese characters with pronunciation matched with the pronunciation character string can be obtained, the one or more Chinese characters are displayed as candidate characters, and accordingly the user can obtain the Chinese character to be queried on the basis of the candidate characters.

The candidate characters refer to one or more characters of which the pronunciation is matched with the pronunciation character string obtained by recognition, the candidate characters can be obtained by automatically matching the pronunciation character string obtained by recognition through a handheld reader based on a dictionary library stored in advance, can be obtained by translating the pronunciation character string obtained by recognition through a built-in embedded translation system through the handheld reader, and can be one or more characters of which the pronunciation is matched with the pronunciation character string obtained by downloading through a network through the handheld reader, and the embodiment of the invention is not limited in particular. The handheld reader may include a presentation device, such as a display screen, on which the candidate text may be presented for viewing by the user after the candidate text is obtained.

It should be understood that, when the recognition result does not include the pronunciation character string, the recognition result may be directly used as a processing object to display the content related to the recognition result, for example, when the user uses the handheld reader to collect an image of a Chinese character, the user performs character recognition on the image to obtain the recognition result as the Chinese character, and at this time, the user may directly use the Chinese character as the processing object to obtain the content related to the Chinese character, such as pinyin, spelling, word sense, and the like, and display the content on the display screen, so as to facilitate the user to check and learn.

And 130, receiving the designated operation, determining a target character corresponding to the designated operation from the candidate characters, and displaying character information of the target character.

Specifically, the designating operation is an operation of selecting and designating any character in the candidate characters to determine the target character, specifically, the designating operation may be implemented by the user clicking or long-pressing a certain character in the candidate characters on the display screen, or the designating operation may be implemented by the user selecting one character from the candidate characters by holding a key on the reader.

After the handheld reader detects the appointed operation, the character appointed by the user, namely the target character to be inquired by the user, for example, the user collects an image of the pronunciation character string 'x ī ng' through the handheld reader, the candidate character matched with the pronunciation character string in pronunciation can be obtained, the candidate character comprises characters such as 'star', 'Xingzhi', 'fishy', 'gorian', and the like, the candidate character is displayed on the display screen, the user realizes the appointed operation by touching or long-pressing the 'star' in the candidate character on the display screen, and after the handheld reader detects the appointed operation, the target character appointed by the user can be determined to be the 'star', and character information of the 'star' is displayed on the display screen.

After the target text specified by the user is determined, the handheld reader can query and acquire the text information of the target text based on a pre-stored dictionary library, and can also download the text information of the target text from a network so as to realize the display of the text information on a display screen, thereby facilitating the user to check. Here, the text information of the target text may include the target text and the pinyin, spelling, word meaning, and the like corresponding to the target text.

According to the display method provided by the embodiment of the invention, the acquired image is subjected to character recognition, and the candidate characters matched with the pronunciation character string are displayed under the condition that the recognition result of the character recognition comprises the pronunciation character string, so that the target characters to be queried can be determined based on the candidate characters, the word entry mode based on the pronunciation is realized through the scanning mode, the target characters to be queried can be obtained by a user according to the pronunciation character string, the selectable range of word entry is increased, and the user experience is improved.

Based on the above embodiment, fig. 2 is a flow chart of step 120 in the display method provided by the present invention, as shown in fig. 2, in step 120, candidate characters with pronunciation matched with pronunciation character strings are displayed, including:

Step 121, determining a current mode from the pronunciation mode and the text mode;

step 122, when the current mode is a text mode, displaying candidate text whose pronunciation matches the pronunciation character string.

It should be noted that, in practical application, when a user uses a handheld reader to collect an image of a pronunciation character string, the user may want to obtain a corresponding target text based on the pronunciation character string, for example, when the user encounters a Chinese character which cannot be written, but can write pinyin, the user may obtain the Chinese character to be queried based on the pronunciation character string; however, the user may want to obtain the pronunciation information related to the pronunciation character string, for example, when the user learns pinyin, the user wants to query to obtain the pronunciation information related to the pinyin, such as pronunciation, initials, finals, tones, spelling methods, etc.

In this regard, the embodiment of the present invention provides a display method, where, when the recognition result includes a pronunciation character string, the current mode may be determined from the pronunciation mode and the text mode, and corresponding pronunciation information or text information is displayed based on the current mode, so as to satisfy the requirement that the user obtains the target text or target pronunciation information based on the pronunciation character string query.

Specifically, the pronunciation mode is a mode of obtaining pronunciation information related to a pronunciation character string obtained by recognition as a processing object, and the character mode is a mode of obtaining corresponding target characters based on the pronunciation character string obtained by recognition and then obtaining character information of the target characters by taking the target characters as a processing object. The current mode is one mode determined from the pronunciation mode and the text mode.

In an embodiment, two different trigger icons can be displayed on the display screen, and the two trigger icons correspond to the pronunciation mode and the text mode respectively, so that a user can select the corresponding trigger icon according to actual requirements, and after the handheld reader detects the selection operation, the current mode can be determined from the pronunciation mode and the text mode. In the embodiment of the invention, the user can select the proper mode according to the actual requirement by setting the pronunciation mode and the text mode for the user to select, so as to obtain the content to be queried.

In another embodiment, the current mode may be automatically determined from the pronunciation mode and the text mode based on a default mode preset by the user, for example, the user is currently learning pinyin, the default mode may be preset as the pronunciation mode, when the user collects an image of a pronunciation character string by using the handheld reader, the handheld reader obtains pronunciation information related to the pronunciation character string based on the obtained default mode and uses the pronunciation character string as a processing object, and displays the pronunciation information on the display screen, so that the user can learn according to actual requirements.

After the current mode is determined from the pronunciation mode and the text mode, corresponding information can be displayed based on the current mode, and the acquired pronunciation information related to the pronunciation character string can be displayed under the condition that the current mode is the pronunciation mode, so that the requirement for acquiring the pronunciation information based on the pronunciation character string is met; under the condition that the current mode is a text mode, candidate characters with pronunciation matched with the pronunciation character string can be displayed, so that target characters to be queried can be determined based on the candidate characters later, and text information of the target characters can be displayed, and therefore the requirement that a user obtains the target characters based on the pronunciation character string query is met.

Based on the above embodiment, in step 121, determining the current mode from the pronunciation mode and the text mode includes:

the current mode is determined from the pronunciation mode and the text mode based on the historical display frequency of the pronunciation mode and the text mode and/or the preset priority of the pronunciation mode and the text mode.

It should be noted that, in the above embodiment, by displaying two different trigger icons on the display screen, before determining the current mode, the user needs to perform corresponding operations, so that the user needs to perform corresponding operations each time when querying, which is relatively complicated. In order to further improve user experience and reduce operation times of a user, in the embodiment of the invention, the current mode can be automatically determined from the two modes by displaying the frequency based on historic pronunciation modes and text modes and/or the preset priority of the pronunciation modes and the text modes without selection by the user operation.

Specifically, the history displaying frequency refers to the number of times that the pronunciation mode and the character mode are respectively selected to be displayed in a certain statistical history period, where the history period may be a period of one day, one week, one month or longer. The preset priority refers to the priority of the pronunciation mode and the text mode preset by the user according to the actual use requirement.

It can be understood that the handheld reader can be used by a plurality of users at the same time, handwriting recognition can be performed on the images collected by the histories when the histories of the pronunciation mode and the character mode are obtained, the histories of the pronunciation mode and the character mode of different users are counted based on the handwriting recognition result, and therefore the histories of the pronunciation mode and the character mode of the current user are obtained, and the current mode is determined. For example, the same handheld reader is used for Zhang three and Li four, after Zhang three frequently writes a pronunciation character string on a exercise book, the handheld reader is used for inquiring pronunciation information, and Li four frequently uses the handheld reader for inquiring target characters and character information, so that based on handwriting recognition on a history acquired image, the history display frequencies of the pronunciation mode and the character mode corresponding to Zhang three and Li four can be respectively counted, and under the condition that the current user is Zhang three, the history display frequency of the pronunciation mode corresponding to Zhang three can be obtained and is higher than the history display frequency of the character mode, and the current mode can be determined.

In an embodiment, the use requirement of the current user may be determined based on the historical display frequency of the pronunciation mode and the text mode, where the higher the historical display frequency is, the greater the use requirement of the corresponding mode is, so that the current mode may be automatically determined from the two modes. Under the condition that the historical display frequency of the pronunciation mode is higher than that of the text mode, the method indicates that the number of times of inquiring the pronunciation information by using the handheld reader is more and the demand is larger, so that the current mode can be automatically determined to be the pronunciation mode from the two modes; under the condition that the historical display frequency of the text mode is higher than that of the pronunciation mode, the method indicates that the number of times of the user using the handheld reader to inquire the target text and the text information of the target text is more and the demand is larger, so that the current mode can be automatically determined to be the text mode from the two modes.

In another embodiment, the use requirement of the current user can be determined based on the preset priorities of the pronunciation mode and the text mode, the higher the preset priority is, the larger the use requirement of the corresponding mode is indicated, and the current mode can be automatically determined to be the pronunciation mode under the condition that the preset priority of the pronunciation mode is higher than the preset priority of the text mode; under the condition that the preset priority of the text mode is higher than the preset priority of the pronunciation mode, the current mode can be automatically determined to be the text mode.

In yet another embodiment, the current mode may be determined from the pronunciation mode and the text mode based on the historical display frequency and the preset priority, for example, the current mode may be determined based on the preset priority first, and the current mode may be determined based on the historical display frequency when the preset priority of the pronunciation mode and the preset priority of the text mode are the same.

Based on any of the above embodiments, the method further comprises:

receiving a mode switching operation;

in response to the mode switching operation, the current mode is switched.

Specifically, the mode switching operation is an operation of switching from a pronunciation mode to a text mode or from a text mode to a pronunciation mode, and the user can implement the mode switching operation by clicking a trigger icon, sliding a screen up and down, sliding a screen left and right, or the like. The handheld reader can switch the current mode after detecting the mode switching operation.

In an embodiment, a user can determine that the current mode is a text mode by clicking or long-pressing a trigger icon, after determining the text mode, display candidate text on a display screen, and set a trigger icon of a pronunciation mode on a display page of the candidate text, so that the user can switch the current mode by clicking the trigger icon of the pronunciation mode, and enter the pronunciation mode from the text mode. It can be understood that, in the page for displaying the candidate characters, the user can perform the designated operation, after the handheld reader detects the designated operation, the target characters can be determined from the candidate characters, the character information of the target characters is displayed, and on the display page of the character information, the trigger icon of the pronunciation mode can be set, so that the user can conveniently switch modes according to the requirements.

In another embodiment, based on the historical display frequency of the pronunciation mode and the text mode and/or the preset priority of the pronunciation mode and the text mode, the current mode can be determined to be the pronunciation mode, after the pronunciation mode is determined, the pronunciation information of the pronunciation character string is displayed on the display screen, a trigger icon of the text mode can be set on a display page of the pronunciation information, and a user can switch the current mode by clicking the trigger icon of the text mode to enter the text mode from the pronunciation mode.

In still another embodiment, in the case that the recognition result includes a pronunciation character string, the pronunciation information of the pronunciation character string and the candidate characters whose pronunciation matches the pronunciation character string may be obtained simultaneously, so that the pronunciation information and the candidate characters are displayed on the same screen on the display screen, for example, the pronunciation information and the candidate characters are directly tiled, and the user may perform a mode switching operation by sliding the screen up and down or sliding the screen left and right.

Based on any of the above embodiments, in step 120, displaying the candidate text whose pronunciation matches the pronunciation character string further includes:

A pronunciation character string is determined based on the at least one candidate pronunciation character string.

It should be noted that, after the image acquired by the handheld reader is acquired, the character recognition is performed on the image, and the obtained recognition result may not be an accurate character, because in practical applications, different variants or transition portions may exist in the character, so that the character cannot be completely accurately recognized, for example, the character recognition is performed on the pronunciation character string handwritten by the user, and an accurate pronunciation character string may not be obtained. In this regard, in the embodiment of the present invention, the candidate character is determined based on the probability that each character position in the recognition result belongs to each preset pronunciation character, and then at least one candidate pronunciation character string is determined based on the candidate character, so that a correct pronunciation character string can be determined based on the candidate pronunciation character string, so that a subsequent user can obtain pronunciation information or text information to be queried according to the correct pronunciation character string.

Specifically, in the case where the recognition result includes a pronunciation character string, recognition may be performed by a character recognition model based on deep learning, such as a convolutional neural network (Convolutional Neural Network, CNN), a self encoder (Autoencoder), or the like, to obtain probabilities that each character position in the recognition result belongs to each preset pronunciation character, respectively. It can be understood that, in the case that the pronunciation character string is pinyin, the character positions may correspond to the initials and the finals respectively, and character recognition is performed on the initials and the finals so as to predict and obtain probabilities that the initials and the finals respectively belong to each preset pronunciation character, where the preset pronunciation characters include all initials and finals in the existing pinyin. Under the condition that the pronunciation character string is an English word, each character position can correspond to one letter in the word, character recognition is respectively carried out on each letter, so that the probability that each letter respectively belongs to each preset pronunciation character is predicted, and here, the preset pronunciation characters can be 26 English letters.

After obtaining probabilities that each character position belongs to each preset pronunciation character respectively, candidate characters at each character position can be determined. For example, pronunciation characters with probability larger than a preset probability, which may be set according to actual conditions, such as 60%, 70% or 80%, may be selected as candidate characters; or selecting one pronunciation character with highest probability as a candidate character; the pronunciation characters arranged in the first three bits or the first two bits when the probability is ordered from high to low can also be selected as candidate characters, and the embodiment of the invention is not particularly limited to this.

In one embodiment, after determining the candidate character at each character position, the candidate characters may be combined to obtain at least one candidate pronunciation character string, and then the candidate pronunciation character strings are filtered to determine the correct pronunciation character string. For example, in the case where the pronunciation character string is pinyin, it is determined that the candidate character at the initial position includes "g", "q", the candidate character at the final position includes "ia", and the candidate character is combined to obtain the candidate pronunciation character string including "gia", "qia", and it is obvious that the candidate pronunciation character string "gia" is absent in the pinyin, and thus it is determined that the correct pronunciation character string is "qia". It can be understood that after screening the candidate pronunciation character strings, under the condition that a plurality of obtained candidate pronunciation character strings still exist, the plurality of candidate pronunciation character strings can be displayed on a display screen of the handheld reader, and a user can realize selection operation by touching or long-pressing any one of the plurality of candidate pronunciation character strings, and after detecting the selection operation, the handheld reader can determine the correct pronunciation character string from the plurality of candidate pronunciation character strings.

In another embodiment, after determining the candidate characters at each character position, the candidate characters at each character position may be used as options, a string selection list may be constructed and displayed, and the user may select the candidate characters at each character position in turn based on the string selection list to determine the correct pronunciation string. For example, in the case that the pronunciation character string is pinyin, the obtained candidate characters at the initial position are determined to be "l", "k", "x", the candidate characters at the final position are determined to be "ang", "ing", "iang", the candidate characters at the initial position and the final position can be used as selectable items in consideration of limited size of a display screen of the handheld reader, a character string selection list capable of scrolling up and down is constructed, the character string selection list is provided with two columns respectively used for displaying the candidate characters at the initial position and the candidate characters at the final position, each column can scroll up and down to select the candidate characters at the initial position and the final position, if a user can select the candidate characters at the initial position to be "x", the candidate characters at the final position can be selected to be "ing", and the handheld reader can combine the candidate characters at each character position determined by the selection operation after detecting the selection operation of the user, so as to obtain a candidate pronunciation character string "xing", and the determined pronunciation character string can be a correct pronunciation character string based on the candidate pronunciation character string.

Based on any of the above embodiments, in step 120, displaying the candidate text with the pronunciation matching the pronunciation character string includes:

acquiring candidate pronunciation of the pronunciation character string under different tones;

and displaying the candidate pronunciation under different tones and the candidate characters with pronunciation matched with at least one candidate pronunciation.

It should be noted that, the pinyin may include an initial consonant, a final and a tone, and in order to display accurate pronunciation information or target characters of the pronunciation character string in the case that the pronunciation character string is pinyin, when the pronunciation character string is identified, the tone of the pronunciation character string may be identified and obtained, so that characters with pronunciation matching with the candidate pronunciation can be displayed based on the candidate pronunciation under the tone, without the need of a user to select correct candidate pronunciation from the candidate pronunciation under different tones, so as to reduce user operations, and thus the user can quickly obtain the target characters to be queried.

Specifically, four tones are included in the Pinyin, namely, flat tone (first tone), up tone (second tone), down tone (third tone) and in tone (fourth tone), and candidate pronunciations under different tones are the candidate pronunciations under the four tones. For example, when the recognized pronunciation character string is "xing", candidate pronunciation of the pronunciation character string under different tones may be obtained, which may include "x ī ng", "xi ng", "x ǐ ng", "x i ng".

After the candidate pronunciations of the pronunciation character string under different tones are obtained, the candidate pronunciations under different tones can be displayed on a display screen, for example, the candidate pronunciations under different tones can be directly tiled and displayed, can be displayed through a scrolling selection list, can be displayed through a drop-down list, and the embodiment of the invention is not particularly limited. The candidate characters with the pronunciation matched with at least one candidate pronunciation can be displayed while the candidate pronunciation under different tones is displayed, and the user can switch the candidate pronunciation under different tones, so that the candidate characters with the pronunciation matched with the candidate pronunciation under the selected tone are displayed, and the user can conveniently obtain the target characters to be queried from the candidate characters.

For example, since there are four candidate pronunciations under different tones, the candidate pronunciations can be directly tiled on the display screen, so that the candidate pronunciations are convenient for a user to view and acquire. For example, fig. 3 is a schematic diagram of a handheld reader provided by the invention for displaying candidate characters, as shown in fig. 3, the obtained candidate pronunciations of the pronunciation character string under different tones include "x ī ng", "xi ng", "x ǐ ng", "x i ng", the candidate pronunciations can be displayed on a display screen, when the recognized pronunciation of the obtained pronunciation character string is the first tone, the candidate characters with the pronunciation matching with "x ī ng", such as "star", "Xing", "fishy", "gorilla" and the like, can be automatically queried and obtained, and the candidate characters can be displayed under the candidate pronunciations on the display screen, and meanwhile, the "x ī ng" in the candidate pronunciations can be highlighted to distinguish the candidate pronunciations under other tones. In the embodiment of the invention, under the condition of identifying the tone of the obtained pronunciation character string, the candidate characters with the pronunciation matched with the candidate pronunciation under the tone can be directly displayed, the user does not need to select the correct candidate pronunciation from the candidate pronunciation under different tones, the user operation is reduced, the user can quickly obtain the target characters to be queried, and the user experience is improved.

Here, on the display page of the candidate pronunciation, the user can also realize the switching display of the candidate characters by clicking or long-pressing each candidate pronunciation on the display screen, so that the user can still obtain the target characters to be queried and the corresponding character information under the condition that the tone of the pronunciation character string is not recognized or the tone of the pronunciation character string is wrong.

It can be understood that the handheld reader can include a speaker, when each candidate pronunciation under different tones is displayed, a speaker icon can be set beside each candidate pronunciation, and after the handheld reader detects the operation of clicking the speaker icon by a user, the corresponding pronunciation audio of the candidate pronunciation can be played through the speaker, so as to meet the learning requirement of the user.

In the display page of the candidate characters, a user can realize the appointed operation by clicking or long-pressing a certain candidate character on the display screen, for example, the user realizes the appointed operation by clicking or long-pressing a 'star' in the candidate characters on the display screen, after detecting the appointed operation, the handheld reader can determine that the target character appointed by the user is the 'star', and the character information of the 'star' is displayed on the display screen, so that the user can conveniently view and acquire the character information.

It should be understood that, in the upper right corner of the candidate text and text information display page, a trigger icon of the pronunciation mode may be set, and the user may switch the current mode to the pronunciation mode by clicking the icon, so as to view the pronunciation information of the pronunciation character string. The display page of the text information can comprise information such as the target text, the pinyin, the spelling and the meaning of the target text, and a speaker icon can be arranged at the display position of the pinyin, the spelling and the meaning, so that a user can conveniently obtain corresponding audio information by clicking the speaker icon, and the user experience is further improved.

acquiring the learning progress of the current user of the handheld reader;

and sorting the candidate characters based on whether the candidate characters are in the raw character set under the learning progress or not, and displaying the sorted candidate characters.

It should be noted that, the user uses the handheld reader to query the target text, which is usually performed under the condition that a certain text is not known or the meaning of a certain text is not understood, so in order to further enable the user to quickly obtain the target text to be queried, in the embodiment of the invention, the display sequence of the candidate text is ordered based on whether the candidate text is in the raw text set under the learning progress or not by acquiring the learning progress of the current user, so that the target text to be queried by the user is preferentially displayed, thereby enabling the user to quickly obtain the target text and improving the query efficiency.

Specifically, the learning progress of the current user refers to the learning degree of the current user on a word of a certain language type, and the learning progress of the current user may be obtained through learning progress preset by the user, may be obtained based on historical learning data of the user, may also be obtained based on learning progress preset by the user in combination with the historical learning data of the user, and the embodiment of the present invention is not limited in this way.

For example, when a user learns pinyin and chinese characters using a handheld reader, the learning progress may be preset on the handheld reader to be "primary second-order," indicating that the user is currently learning chinese characters of primary second-order, i.e., for the current user, chinese characters of primary second-order and above constitute a new set of words for the current user at the current learning progress, where the new set of words refers to a set of chinese characters for the current user that do not recognize or understand word meaning at the current learning progress. After the handheld reader acquires each candidate character with the pronunciation matched with the recognized pronunciation character string, the handheld reader can judge whether each candidate character is in a new character set under the current learning progress of the user, wherein the new character set can be automatically downloaded from a network based on the learning progress preset by the user, or can be obtained after updating the pre-stored new character set based on the learning progress preset by the user.

When judging whether each candidate character is in the raw character set under the learning progress, each candidate character can be matched with each character in the raw character set in sequence, if the matching is successful, the candidate character is indicated to be in the raw character set under the learning progress, the sorting position of the candidate character in each candidate character can be moved forward at the moment, and if the matching is unsuccessful, the candidate character is indicated to be not in the raw character set under the learning progress, and the sorting position of the candidate character in each candidate character can be moved backward at the moment. After the candidate characters are judged, sorting the candidate characters based on the final judging result, and displaying the sorted candidate characters.

It should be understood that, based on the historical learning data of the current user, the new word set under the learning progress of the current user may be automatically updated, for example, the "star" of the Chinese character is in the new word set under the learning progress of the current user, the current user designates the target word to be queried as the "star" in each candidate word, and after detecting the designated operation of the current user, the handheld reader displays the "star" of the target word and the corresponding word information, and simultaneously deletes the "star" of the Chinese character from the new word set to obtain the new word set under the updated learning progress, so as to serve as the basis for subsequently sorting the candidate words. After a user learns for a period of time, the handheld reader can automatically update the learning progress of the current user when detecting that the Chinese characters in the new character set belong to the three-grade or more Chinese character set of primary school.

Based on any of the above embodiments, fig. 4 is a schematic structural diagram of a display device provided by the present invention, and as shown in fig. 4, the device is applied to a handheld reader, and the device includes:

the recognition unit 410 is configured to acquire an image acquired by the handheld reader, and perform character recognition on the image to obtain a recognition result;

a first display unit 420, configured to display candidate characters whose pronunciation matches the pronunciation character string if the recognition result includes the pronunciation character string;

the second display unit 430 is configured to receive the specified operation, determine a target text corresponding to the specified operation from the candidate text, and display text information of the target text.

According to the display device provided by the embodiment of the invention, the acquired image is subjected to character recognition, and the candidate characters matched with the pronunciation character string are displayed under the condition that the recognition result of the character recognition comprises the pronunciation character string, so that the target characters to be queried can be determined based on the candidate characters, the word entry mode based on the pronunciation is realized in a scanning mode, a user can obtain the target characters to be queried according to the pronunciation character string, the selectable range of word entry is increased, and the user experience is improved.

Based on any of the above embodiments, the first display unit 420 includes:

a determining subunit, configured to determine a current mode from the pronunciation mode and the text mode;

and the display subunit is used for displaying candidate characters with pronunciation matched with the pronunciation character string under the condition that the current mode is a character mode.

Based on any of the above embodiments, the determining subunit is specifically configured to:

Based on any of the above embodiments, the apparatus further includes a mode switching unit, where the mode switching unit is specifically configured to:

receiving a mode switching operation;

in response to the mode switching operation, the current mode is switched.

Based on any one of the above embodiments, the apparatus further includes a pronunciation character string determining unit, where the pronunciation character string determining unit is specifically configured to:

Based on any of the above embodiments, the first display unit 420 is configured to:

Based on any of the above embodiments, the first display unit 420 is further configured to:

acquiring the learning progress of the current user of the handheld reader;

Based on any of the above embodiments, fig. 5 is a schematic structural diagram of a handheld reader provided by the present invention, and as shown in fig. 5, the handheld reader includes a camera 510, a processor 520, and a display 530, which are sequentially connected, and an interaction interface 540 connected to the processor;

the camera 510 is used for acquiring an image and transmitting the image to the processor 520;

the processor 520 is configured to perform character recognition on the image to obtain a recognition result, and display candidate characters with pronunciation matching the pronunciation character string based on the display screen 530 if the recognition result includes the pronunciation character string;

The interaction interface 540 is configured to receive the specified operation and transmit the specified operation to the processor 520;

the processor 520 is further configured to determine a target text corresponding to the specified operation from the candidate text, and display text information of the target text based on the display 530.

Specifically, the handheld reader can comprise a camera for image acquisition of a user, a processor for realizing relevant function control and data processing, a display screen for information display and an interactive interface for receiving user operation. It will be appreciated that in some embodiments, the touch screen may function as both a display screen and an interactive interface, where the display screen and the interactive interface are the same component.

The user can acquire images through a camera arranged on the handheld reader to obtain character images required to be input by the user, then the camera transmits the acquired images to the processor, the processor can recognize the characters of the images after receiving the images to obtain recognition results, and under the condition that the recognition results comprise pronunciation character strings, one or more characters matched with the pronunciation character strings are obtained through matching, the one or more characters are used as candidate characters and transmitted to the display screen, and the display screen displays the candidate characters. Here, the candidate text obtained by matching may be obtained by automatic matching based on a dictionary library stored in advance, or may be obtained by translating a pronunciation character string based on a built-in embedded translation system, which is not particularly limited in the embodiment of the present invention.

The user can check the candidate characters obtained by matching through the display screen, and the user performs the appointed operation on the candidate characters through the interactive interface on the handheld reader, and the interactive interface transmits the appointed operation to the processor after receiving the appointed operation. After receiving the specified operation, the processor can respond to the specified operation, determines the target text corresponding to the specified operation from the candidate text, takes the target text as a processing object, obtains relevant text information, transmits the obtained text information of the target text to the display screen, and displays the text information of the target text by the display screen, thereby being convenient for a user to view. The text information may be obtained based on a dictionary library stored in advance, or may be obtained by searching or may be obtained by downloading from a network, which is not particularly limited in the embodiment of the present invention.

According to the handheld reader provided by the embodiment of the invention, the acquired image is subjected to character recognition, and the candidate characters matched with the pronunciation character string are displayed under the condition that the recognition result of the character recognition comprises the pronunciation character string, so that the target characters to be queried can be determined based on the candidate characters, the input mode of character input based on the pronunciation is realized in a scanning mode, a user can obtain the target characters to be queried according to the pronunciation character string, the selectable range of character input is increased, and the user experience is improved.

Fig. 6 illustrates a physical schematic diagram of an electronic device, as shown in fig. 6, which may include: processor 610, communication interface (Communications Interface) 620, memory 630, and communication bus 640, wherein processor 610, communication interface 620, and memory 630 communicate with each other via communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform the presentation method, which includes: acquiring an image acquired by a handheld reader, and performing character recognition on the image to obtain a recognition result; displaying candidate characters with pronunciation matched with the pronunciation character string under the condition that the recognition result comprises the pronunciation character string; and receiving the designated operation, determining the target text corresponding to the designated operation from the candidate text, and displaying the text information of the target text.

Further, the logic instructions in the memory 630 may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

In another aspect, the present invention also provides a computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing the presentation method provided by the methods described above, the method comprising: acquiring an image acquired by a handheld reader, and performing character recognition on the image to obtain a recognition result; displaying candidate characters with pronunciation matched with the pronunciation character string under the condition that the recognition result comprises the pronunciation character string; and receiving the designated operation, determining the target text corresponding to the designated operation from the candidate text, and displaying the text information of the target text.

In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the presentation method provided by the above methods, the method comprising: acquiring an image acquired by a handheld reader, and performing character recognition on the image to obtain a recognition result; displaying candidate characters with pronunciation matched with the pronunciation character string under the condition that the recognition result comprises the pronunciation character string; and receiving the designated operation, determining the target text corresponding to the designated operation from the candidate text, and displaying the text information of the target text.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A display method for use with a handheld reader, the method comprising:

2. The display method according to claim 1, wherein the displaying the candidate text whose pronunciation matches the pronunciation character string includes:

Determining a current mode from the pronunciation mode and the text mode;

3. The display method according to claim 2, wherein determining the current mode from the pronunciation mode and the text mode includes:

4. The display method according to claim 2, further comprising:

receiving a mode switching operation;

and switching the current mode in response to the mode switching operation.

5. The display method according to any one of claims 1 to 4, wherein the displaying the candidate text whose pronunciation matches the pronunciation character string further comprises:

6. The display method according to any one of claims 1 to 4, wherein the displaying candidate characters whose pronunciation matches the pronunciation character string includes:

7. The display method according to any one of claims 1 to 4, wherein the displaying candidate characters whose pronunciation matches the pronunciation character string includes:

acquiring the learning progress of the current user of the handheld reader;

8. A display device for use with a handheld reader, the device comprising:

9. The handheld reader is characterized by comprising a camera, a processor, a display screen and an interaction interface, wherein the camera, the processor and the display screen are sequentially connected;

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the presentation method of any one of claims 1 to 7 when the program is executed by the processor.