A method, device and computer equipment for reminding pronunciation of uncommon characters

Abstract

The present invention relates to a method, device and computer equipment for pronouncing uncommon characters. The method for pronouncing uncommon characters comprises: S10, displaying a text to be read aloud; S20, receiving a voice to be read aloud, identifying the characters corresponding to the voice to be read aloud, and tracking the characters in the text to be read aloud word by word; S30, when it is judged that the reading parameters meet the stagnation condition, the first character to be read aloud is regarded as an uncommon character according to the tracking progress, and the pronunciation of the uncommon character is reminded. In the present invention, when it is detected that the reader encounters an uncommon character during the reading process, the pronunciation of the uncommon character can be automatically reminded without the reader having to query by himself, thereby improving the coherence and efficiency of the reading.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more particularly to a method, device and computer equipment for reminding the pronunciation of uncommon characters. Background Art

[0002] In the process of studying at school or self-study, people often need to read aloud an article or a paragraph. During the reading process, if they encounter an uncommon character, they need to stop and look up the pronunciation of the uncommon character in a dictionary or on the Internet before continuing to read aloud, which brings inconvenience to the reader. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an improved method, device and computer equipment for reminding the pronunciation of uncommon characters.

[0004] The technical solution adopted by the present invention to solve the technical problem is: constructing a pronunciation reminder method for uncommon characters, comprising:

[0005] S10, displaying the text to be read aloud;

[0006] S20, receiving a read voice, identifying the text corresponding to the read voice, and tracking the text in the read text word by word;

[0007] S30: When it is determined that the reading parameter meets the stagnation condition, the first character to be read is regarded as an uncommon character according to the tracking progress, and a pronunciation reminder is given for the uncommon character.

[0008] Preferably, the pronunciation reminder for the uncommon characters includes: using a homophone with the uncommon characters to remind the pronunciation of the uncommon characters; wherein the homophone is more commonly used than the uncommon characters.

[0009] Preferably, the pronunciation reminder for the uncommon characters includes: pronouncing the uncommon characters by the pinyin of the uncommon characters, and / or pronouncing the uncommon characters by voice.

[0010] Preferably, the method further includes: classifying each character into a common level, where characters with a high common level are more commonly used than characters with a low common level; grouping homophones in the characters classified into common levels to form a homophone group library; or

[0011] Grouping homophones in each character; classifying each character in each group into a common level, where characters with a high common level are more commonly used than characters with a low common level, thereby forming a homophone group library;

[0012] In step S30, the uncommon character is pronounced with a homophone that is the same as the uncommon character; wherein the homophone is more commonly used than the uncommon character; including:

[0013] Homophones in the same group as the uncommon character are searched in the homophone group database, and homophones with a higher common level than the uncommon character are obtained to remind the uncommon character to be pronounced.

[0014] Preferably, the characters include: extracting sample text by itself, performing single-word segmentation and statistics on the sample text to obtain the characters; or obtaining third-party statistical data of the input method to obtain the characters;

[0015] When each character is obtained by extracting sample texts, the classification of each character into common levels includes: classifying each character into common levels according to the number of times each character appears;

[0016] When each character is obtained by acquiring third-party statistical data of the input method, classifying each character into a frequently used level includes: classifying each character into a frequently used level according to the number of times each character is used.

[0017] Preferably, obtaining a homophone with a higher common level than the uncommon character to remind the pronunciation of the uncommon character includes:

[0018] A plurality of homophones with a higher commonness level than the uncommon character are obtained to perform interval replacement pronunciation reminders on the uncommon character; wherein, among the plurality of homophones, the characters with a higher commonness level are given priority in the reminder.

[0019] Preferably, the method further comprises: receiving a trial reading voice, and acquiring a normal time interval and a normal reading speed in a normal reading state according to the trial reading voice;

[0020] The reading parameter is the current stagnation time, and the stagnation condition is the normal time interval; in step S30, when it is determined that the reading parameter meets the stagnation condition, it includes: when it is determined that the current stagnation time is greater than the normal time interval; or,

[0021] The reading parameter is the current reading speed, and the stagnation condition is the normal reading speed. In step S30, when it is determined that the reading parameter meets the stagnation condition, it includes: when it is determined that the current reading speed is less than the normal reading speed.

[0022] Preferably, the method of reminding the pronunciation of the uncommon character by using a homophone with the uncommon character includes: displaying the homophone above the uncommon character.

[0023] The present invention also provides a device for reminding the pronunciation of uncommon characters, comprising:

[0024] A display unit, for displaying the text to be read aloud;

[0025] A tracking unit, configured to receive a read voice, identify characters corresponding to the read voice, and track the characters in the read text word by word;

[0026] The execution unit is used for, when it is determined that the reading parameter meets the stagnation condition, taking the first character to be read as an uncommon character according to the tracking progress, and providing a pronunciation reminder for the uncommon character.

[0027] The present invention also constructs a computer device, comprising a processor and a memory, wherein the processor is communicatively connected to the memory;

[0028] The memory is used to store computer programs;

[0029] The processor is configured to execute a computer program stored in the memory to implement any of the above-mentioned methods for reminding the pronunciation of uncommon characters.

[0030] The method, device and computer equipment for reminding the pronunciation of uncommon characters of the present invention have the following beneficial effects:

[0031] When it is detected that the reader encounters an uncommon character during reading, the pronunciation reminder of the uncommon character can be automatically given without the reader having to look it up on their own, thereby improving the coherence and efficiency of reading. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0033] Figure 1 It is a flow chart of the method for reminding the pronunciation of uncommon characters of the present invention;

[0034] Figure 2 It is a structural diagram of the uncommon Chinese character pronunciation reminder device of the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] See also Figure 1 , Figure 1 Schematic diagram of the process of the method for reminding the pronunciation of rare characters of the present invention, as shown in FIG. Figure 1 As shown, the method for reminding the pronunciation of uncommon characters includes the following steps:

[0037] Step S10: Display the text to be read aloud.

[0038] It can be understood that the text to be read aloud is a text that can be read aloud by people. The text to be read aloud can be a document reading material such as an article or news. The text to be read aloud can include text content, graphic content, and the like.

[0039] In step S10, the reading text that the reader needs to read aloud is displayed for the reader to view and read according to the reading text, and for the reader to view the reminder of uncommon characters. It can be understood that the reading text can be displayed according to the reader's selection.

[0040] Step S20: receiving the read voice, identifying the text corresponding to the read voice, and tracking the text in the read text word by word.

[0041] It is understandable that the text content in the read-aloud text is composed of multiple characters. When people read the text content, they read the characters one by one according to the direction of the text content. For example, based on the characteristics of Chinese characters and human physiological habits, the direction of text content is generally from top to bottom and from left to right. This embodiment uses this direction as an example for explanation. Of course, some text content can also be written from top to bottom and from left to right.

[0042] When the reader reads the text aloud, the characters in the text content are read one by one in the direction of the text content, that is, from top to bottom and from left to right. During the reading process, the reader receives the reading voice, recognizes the characters corresponding to the reading voice, and tracks the characters in the text aloud word by word. Specifically, the reading voice can be received using a voice-to-text conversion technology to recognize the characters corresponding to the reading voice, and the recognized characters are matched with the characters in the text content to track the characters in the text aloud word by word.

[0043] It is understandable that the tracking process can also be understood as gradually adjusting the tracking speed according to the current reader's reading speed, that is, according to the conversion of the reading speech into text, and using a speed adapted to the reading speed to track the words in the reading text one by one according to the direction of the text content, so that the tracked text is synchronized with the reading text. It is understandable that the technology for converting speech into text can be directly implemented using existing technology, such as the existing speech-to-text technology of third-party speech-to-text conversion such as Baidu, iFlytek, etc.

[0044] Of course, the tracking progress can also be adjusted by receiving adjustment instructions input by the reader. For example, the adjustment instructions may include pause, fast forward, etc., and the adjustment instructions can be implemented by pressing keys, etc. In some implementation scenarios, the cursor position is consistent with the tracking progress. Therefore, the current tracking progress can be adjusted by changing the cursor position.

[0045] The currently tracked text may be highlighted in other colors, other fonts, or other forms of expression to indicate the tracking or reading progress.

[0046] Step S30: When it is determined that the reading parameter meets the stagnation condition, the first character to be read is regarded as an uncommon character according to the tracking progress, and a pronunciation reminder is given for the uncommon character.

[0047] It can be understood that when the reading parameters of the reader meet the stagnation condition, it is considered that the reader is stagnant and the tracking is stopped.

[0048] The uncommon-character pronunciation reminder method of this embodiment further includes: receiving a trial reading voice, and obtaining a normal time interval and a normal reading speed in a normal reading state according to the trial reading voice.

[0049] It is understood that before the formal reading, the reader can first input a normal reading voice as a trial reading voice. The trial reading voice can be input by the reader reading the whole or part of the reading text normally; or by playing the reader's speech in a normal speaking state; or by directly inputting the corresponding voice and using the voice input by the reader as the trial reading voice. It is understood that the normal reading and normal speaking mentioned here are to obtain the reader's normal speaking speed, not the speed of speech in a pause or other state.

[0050] A trial reading voice is received, and a normal time interval and a normal reading speed of the reader in a normal reading state are obtained based on the trial reading voice. It is understood that the normal time interval can be obtained by calculating the time interval between two characters during the normal reading or normal speaking process of the reader. The normal reading speed can be obtained by calculating the rated number of characters read or spoken by the reader within a rated time during the normal reading or normal speaking process of the reader. It is understood that the normal time interval and the normal reading speed can be specific values ​​or ranges of values.

[0051] In step S30, the reading parameter may be the current pause time of reading, and the pause condition may be a normal time interval. It is understood that when the reading parameter is determined to meet the pause condition, including when the current pause time is determined to be greater than the normal time interval, indicating that the reader is in a pause state, the reader is deemed to have encountered an uncommon character, and the first character in the text to be read following the current character being tracked is identified as an uncommon character according to the direction of the text, and a pronunciation reminder is provided for the uncommon character.

[0052] Alternatively, in step S30, the reading parameter can be the current reading speed, and the stagnation condition can be the normal reading speed. Understandably, when it is determined that the reading parameter meets the stagnation condition, it includes: when it is determined that the current reading speed is less than the normal reading speed, that is, when the reader fails to complete the reading of the rated number of words within the rated time, it is considered that the current reading speed is less than the normal reading speed, indicating that the reader is in a stagnant state, then it is considered that the reader encounters a rare character, and pronunciation reminder is given to this rare character.

[0053] In this embodiment, the method of giving pronunciation reminder to rare characters includes: using a homophone of the rare character to give pronunciation reminder to the rare character; among them, the homophone is more commonly used than the rare character.

[0054] The method of giving pronunciation reminder to rare characters in this embodiment further includes: step S01, dividing each character into different common levels, and the character with a higher common level is more commonly used than the character with a lower common level; grouping the homophones among the characters with divided common levels to form a homophone group library.

[0055] This step S01 can be before step S10. Understandably, before the reader reads, each character is processed first, so that a homophone can be used to give pronunciation reminder to the rare character.

[0056] In this step, the acquisition of each character includes: by extracting sample texts by oneself, performing single-character cutting and statistics on the text content in the sample texts to obtain each character; or, obtaining third-party statistical data of the input method to obtain each character.

[0057] When each character is obtained by extracting sample texts by oneself, the division of the common level of each character includes: dividing the common level of each character according to the number of times each character appears. Understandably, the sample text can be document readings such as news, articles, etc., and one or more sample texts can be used. The text content in the sample text should cover as many characters as possible to make the characters more comprehensive.

[0058] Understandably, for single-character cutting and statistics, for example, if the text content includes characters such as "报抱暴豹古", it can be cut into characters such as "报", "抱", "暴", "豹", "古", and the number of times each character appears is counted. For example, if "报", "抱", "暴", "豹", "古" appear 30 times, 20 times, 15 times, 8 times, and 10 times respectively, the common level can be used to distinguish the common degree of each character. Here, the character with a higher number of appearances has a higher common level than the character with a lower number of appearances. There can be multiple common levels. For example, the common levels include 10 common levels from common level 1 to common level 10. The smaller the number of the common level, the higher the common level.

[0059] When each character is obtained by acquiring third-party statistical data of an input method, the classification of each character into common levels includes: classifying each character into common levels according to the usage frequency of each character. Among them, the input method can be Sogou or Baidu Input Method. The common level of a character with a higher usage frequency is relatively higher than that of a character with a lower usage frequency.

[0060] After completing the classification of each character into common levels, group the homophonic characters among the characters with classified common levels to form a homophone group library. It can be understood that homophonic characters have the same pinyin and the same tone. For example, the pronunciations of "报", "抱", "暴", and "豹" in the above text content are all "bào", so these multiple characters are homophonic characters, and these multiple homophonic characters are grouped into the same homophone group. Therefore, this homophone group includes homophonic characters "报", "抱", "暴", and "豹" with common levels of common level 2, common level 4, common level 6, and common level 8 respectively, and the homophonic characters can be sorted according to the common level. It can be understood that the common levels of the homophonic characters in this homophone group are only for illustrative purposes and do not represent the actual common levels. Multiple homophone groups are set up like this to form a homophone group library.

[0061] In some embodiments, step S01 can be: group the homophonic characters among each character; classify each character in each group into common levels, and a character with a higher common level is more common than a character with a lower common level, to form a homophone group library.

[0062] It can be understood that the difference between step S01 in these some embodiments and S01 in this embodiment is that in this embodiment, the classification of each character into common levels is completed first, and then the homophonic characters among the characters with classified common levels are grouped. In some embodiments, first, the homophonic characters among each character are grouped, and then each character in each group is classified into common levels. It can be understood that the two are only different in the execution order. In the present invention, the execution order of these two steps is not limited, as long as it can achieve the formation of each homophone group in the homophone group library, and each character in each homophone group has a corresponding common level. Of course, the characters in each homophone group can be sorted according to the common level.

[0063] In step S30, use the homophonic character that is homophonic to a rare character to give a pronunciation reminder to the rare character; among them, the homophonic character is more common than the rare character. Specifically, when a rare character is recognized, retrieve the homophonic characters in the same group as the rare character in the homophone group library, and obtain the homophonic character with a higher common level than the rare character to give a pronunciation reminder to the rare character.

[0064] Further, homophones with a higher common usage level than the rare character are obtained to provide pronunciation reminders for the rare character, including: obtaining multiple homophones with a higher common usage level than the rare character for interval replacement pronunciation reminders; among the multiple homophones, the character with a higher common usage level is reminded first.

[0065] Specifically, all homophones with a higher common usage level than the rare character are retrieved from the homophone group library, and several homophones with a relatively higher common usage level are obtained. For example, the three homophones with the highest common usage level are obtained for interval replacement pronunciation reminders for the rare character.

[0066] Of course, replacement reminders can also be made with other numbers of homophones. For example, when there are more than three homophones with a higher common usage level than the rare character, these multiple homophones are used for interval replacement, or the first few homophones with a relatively higher common usage level are used for interval replacement; when there are less than three homophones with a higher common usage level than the rare character, all the homophones are used for interval replacement.

[0067] The method of interval replacement pronunciation reminder includes: interval replacement at regular time intervals for three homophones. For example, when the identified rare character is "豹" (bao), it is retrieved from the homophone group library, and the homophone group where the character "豹" is located, such as "报" (bao), "抱" (bao), "暴" (bao), "豹" (bao), is obtained. Among this homophone group, the characters "报", "抱", and "暴" have a higher common usage level than the character "豹". Therefore, pronunciation reminders can be made by alternately replacing with "报", "抱", and "暴".

[0068] For example, first, the homophone "报" with the highest common usage level is used for pronunciation reminder. Starting from the time when "报" is used for reminder, when the set regular time is reached, the homophone "抱" with the next highest common usage level is used for pronunciation reminder; starting from the time when "抱" is used for reminder, when the set regular time is reached, the homophone "暴" with the next highest common usage level is used for pronunciation reminder. Starting from the time when "暴" is used for reminder, when the set regular time is reached, if it is determined that the reader has not resumed reading, then "报" is used for pronunciation reminder again, and so on in a loop until the reader resumes reading. It can be understood that this regular time can be set according to requirements.

[0069] This regular time can be a time for determining whether the reader is still in a stagnant state. It can be understood that in step S << 30 >>, timing starts when a homophone is used for pronunciation reminder for the rare character. If the reader is still in a stagnant state when this regular time is reached, it is considered that this homophone is still a rare character for the reader. Therefore, another homophone is replaced for pronunciation reminder for the rare character. This regular time can be the same as the normal time interval or greater than the normal time interval to provide the reader with more discrimination time. Or, this regular time can be less than the normal time interval. For example, the regular time is one-third of the normal time interval to show more homophones to the reader.

[0070] Of course, the method of judging whether the reader is in a stagnant state can also be implemented by using the above method of judging whether the current reading speed is lower than the normal reading speed. This is the same as the above judgment method and will not be repeated here.

[0071] In some embodiments, the method of interval replacement pronunciation reminder includes: by receiving the replacement instruction input by the reader, performing the replacement reminder of homophones, and similarly, the replacement of the homophones is also prioritized by displaying the most commonly used ones, that is, the reminder is performed in the order of most commonly used to least commonly used.

[0072] In this application, the pronunciation reminder of uncommon characters is given priority to homophones with high common levels, that is, homophones with small common level numbers, and multiple homophones are used to pronounce uncommon characters to improve the reading efficiency of the reader. In other embodiments, multiple homophones can be used simultaneously to pronounce uncommon characters.

[0073] Among them, the pronunciation reminder of uncommon characters with homophones can be displayed above the uncommon characters. It can be understood that in the text content, there is a gap between each line of text, and displaying the homophone above the uncommon characters is convenient for readers to view and is in line with daily habits.

[0074] It is understandable that before the reader reads the text, the homophone group library can be recorded into the reading device first. Therefore, during the reader's reading process, the pronunciation reminder of uncommon characters can be realized through the homophone group library, and the homophone can be displayed in a prominent form, for example, the homophone is different from other characters in the reading text in color, thickness, font, etc.

[0075] It is understandable that the same reader may read different texts at different speeds, and different readers may read the same text at different speeds. Therefore, in step S20, the text in the text is tracked based on the current reader's reading speed, that is, the conversion of speech into text; and in step S30, a stagnation condition is set based on the current reader's reading speed.

[0076] In this embodiment, the pronunciation of uncommon characters is automatically prompted based on the reader's reading speed, and homophones can be dynamically replaced according to the reader's pauses, which can improve the reader's reading coherence and efficiency.

[0077] In another embodiment of the present invention, the method for reminding the pronunciation of uncommon characters comprises the following steps:

[0078] Step S10: Display the text to be read aloud.

[0079] Step S20: receiving the read voice, identifying the text corresponding to the read voice, and tracking the text in the read text word by word.

[0080] Step S30: When it is determined that the reading parameter meets the stagnation condition, the first character to be read is regarded as an uncommon character according to the tracking progress, and a pronunciation reminder is given for the uncommon character.

[0081] The difference between this embodiment and the above embodiment is that in step S30, the pronunciation reminder for uncommon characters includes: pronouncing the uncommon characters with homophones of the uncommon characters; and / or pronouncing the uncommon characters with the pinyin of the uncommon characters; and / or pronouncing the uncommon characters in voice.

[0082] It is understandable that the pronunciation reminder of the uncommon characters is performed using the homophones of the uncommon characters, which is the same as the method in the above embodiment and will not be described in detail here. Specifically, the pronunciation reminder of the uncommon characters can be performed by pre-establishing a Chinese phonetic library for each character. When the uncommon characters are recognized, the Chinese phonetic library corresponding to the uncommon characters is retrieved from the Chinese phonetic library and the Chinese phonetic library is displayed above the uncommon characters. Of course, the Chinese phonetic library can be implemented using an existing Chinese phonetic library.

[0083] The uncommon characters are reminded to be pronounced in a voice manner. Specifically, a voice unit can be provided so that when an uncommon character is recognized, the uncommon character is announced through the voice unit.

[0084] It is understandable that one or more of the above-mentioned combinations can be used to provide pronunciation reminders for uncommon characters, so as to be suitable for a variety of people.

[0085] See also Figure 2 , Figure 2 1 is a schematic diagram of the structure of the uncommon character pronunciation reminder device of the present invention. The function realized by the uncommon character pronunciation reminder device 10 corresponds to the above-mentioned uncommon character pronunciation reminder method. Figure 2 As shown, the uncommon character pronunciation reminder device 10 includes:

[0086] The display unit 101 is used to display the text to be read aloud.

[0087] It can be understood that the text to be read aloud is a text that can be read aloud by people. The text to be read aloud can be a document reading material such as an article or news. The text to be read aloud can include text content, graphic content, and the like.

[0088] The display unit 101 displays the text that the reader needs to read aloud, so that the reader can view and read according to the text, and can also view reminders of uncommon characters.

[0089] The tracking unit 102 is used to receive the read speech, identify the text corresponding to the read speech, and track the text in the read text word by word.

[0090] It is understandable that the text content in the read-aloud text is composed of multiple characters. When people read the text content, they read the characters one by one according to the direction of the text content. For example, based on the characteristics of Chinese characters and human physiological habits, the direction of text content is generally from top to bottom and from left to right. This embodiment uses this direction as an example for explanation. Of course, some text content can also be written from top to bottom and from left to right.

[0091] When the reader reads the text aloud, the characters in the text content are read one by one in the direction of the text content, that is, from top to bottom and from left to right. During the reading process, the reader receives the reading voice, recognizes the characters corresponding to the reading voice, and tracks the characters in the text aloud word by word. Specifically, the reading voice can be received using a voice-to-text conversion technology to recognize the characters corresponding to the reading voice, and the recognized characters are matched with the characters in the text content to track the characters in the text aloud word by word.

[0092] It is understandable that the tracking process can also be understood as gradually adjusting the tracking speed according to the current reader's reading speed, that is, according to the conversion of the reading speech into text, and using a speed adapted to the reading speed to track the words in the reading text one by one according to the direction of the text content, so that the tracked text is synchronized with the reading text. It is understandable that the technology for converting speech into text can be directly implemented using existing technology, such as the existing speech-to-text technology of third-party speech-to-text conversion such as Baidu, iFlytek, etc.

[0093] Of course, the tracking progress can also be adjusted by receiving adjustment instructions input by the reader. For example, the adjustment instructions may include pause, fast forward, etc., and the adjustment instructions can be implemented by pressing keys, etc. In some implementation scenarios, the cursor position is consistent with the tracking progress. Therefore, the current tracking progress can be adjusted by changing the cursor position.

[0094] The currently tracked text may be highlighted in other colors, other fonts, or other forms of expression to indicate the tracking or reading progress.

[0095] The execution unit 103 is configured to, when it is determined that the reading parameter satisfies the stagnation condition, set the first character to be read as an uncommon character according to the tracking progress and provide a pronunciation reminder for the uncommon character.

[0096] It can be understood that when the reading parameters of the reader meet the stagnation condition, it is considered that the reader is stagnant and the tracking is stopped.

[0097] The uncommon-character pronunciation reminder device 10 of this embodiment further includes: a receiving and obtaining unit for receiving a trial reading voice, and obtaining a normal time interval and a normal reading speed in a normal reading state according to the trial reading voice.

[0098] It is understood that before the formal reading, the reader can first input a normal reading voice as a trial reading voice. The trial reading voice can be input by the reader reading the whole or part of the reading text normally; or by playing the reader's speech in a normal speaking state; or by directly inputting the corresponding voice and using the voice input by the reader as the trial reading voice. It is understood that the normal reading and normal speaking mentioned here are to obtain the reader's normal speaking speed, not the speed of speech in a pause or other state.

[0099] A trial reading voice is received, and a normal time interval and a normal reading speed of the reader in a normal reading state are obtained based on the trial reading voice. It is understood that the normal time interval can be obtained by calculating the time interval between two characters during the normal reading or normal speaking process of the reader. The normal reading speed can be obtained by calculating the rated number of characters read or spoken by the reader within a rated time during the normal reading or normal speaking process of the reader. It is understood that the normal time interval and the normal reading speed can be specific values ​​or ranges of values.

[0100] In the execution unit 103, the reading parameter may be the current pause time of the reading, and the pause condition may be a normal time interval. It is understood that when the reading parameter is determined to meet the pause condition, including when the current pause time is determined to be greater than the normal time interval, indicating that the reader is in a pause state, the reader is deemed to have encountered an uncommon character, and the first character in the text to be read following the current character being tracked is identified as an uncommon character according to the direction of the text, and a pronunciation reminder is provided for the uncommon character.

[0101] Alternatively, in the execution unit 103, the reading parameter may be the current reading speed, and the stagnation condition may be the normal reading speed. It is understood that when the reading parameter is determined to meet the stagnation condition, it is determined that the current reading speed is less than the normal reading speed, that is, when the reader fails to complete the reading of the rated number of words within the rated time, the current reading speed is considered to be less than the normal reading speed, indicating that the reader is in a stagnant state, and the reader is considered to have encountered an uncommon character, and a pronunciation reminder for the uncommon character is provided.

[0102] In this embodiment, the method of pronouncing uncommon characters includes: pronouncing uncommon characters with homophones that have the same pronunciation as the uncommon characters; wherein homophones are more commonly used than uncommon characters.

[0103] The rare - character pronunciation reminder device 10 of this embodiment further includes: a grouping and division unit, which is used to divide each character into common - use levels. Characters with a higher common - use level are more common than those with a lower common - use level; group the homophonic characters among the characters with divided common - use levels to form a homophone group library.

[0104] This grouping and division unit can be executed before the display unit 101. It can be understood that before the reader reads aloud, each character is processed first, so that homophonic characters can be used to remind the pronunciation of rare characters.

[0105] The acquisition of each character includes: by extracting sample texts by oneself, performing single - character cutting and statistics on the character content in the sample texts to obtain each character; or, obtaining third - party statistical data of the input method to obtain each character.

[0106] When each character is obtained by extracting sample texts by oneself, the division of each character into common - use levels includes: dividing each character into common - use levels according to the number of times each character appears. It can be understood that the sample texts can be document readings such as news and articles, and one or more sample texts can be used. The character content in the sample texts should cover as many characters as possible to make the characters more comprehensive.

[0107] It can be understood that for single - character cutting and statistics, for example, if the character content includes characters such as "报抱暴豹古", it can be cut into characters "报", "抱", "暴", "豹", "古", and the number of times each character appears is counted. For example, if "报", "抱", "暴", "豹", "古" appear 30 times, 20 times, 15 times, 8 times, and 10 times respectively, the common - use levels can be used to distinguish the common - use degree of each character. Here, the character with a higher number of appearances has a higher common - use level than the character with a lower number of appearances. The common - use levels can include multiple levels. For example, the common - use levels include 10 common - use levels from common - use level 1 to common - use level 10. The smaller the number of the common - use level, the higher the common - use level.

[0108] When each character is obtained by obtaining third - party statistical data of the input method, the division of each character into common - use levels includes: dividing each character into common - use levels according to the usage times of each character. Among them, the input method can be Sogou or Baidu Input Method. Characters with higher usage times have a higher common - use level than those with lower usage times.

[0109] After completing the classification of the common levels of each character, group the homophonic characters in the characters with classified common levels to form a homophonic group library. Understandably, homophonic characters have the same pinyin and the same tone. For example, the pronunciations of "报", "抱", "暴", and "豹" in the above text content are all "bào", so these multiple characters are homophonic characters, and these multiple homophonic characters are grouped in the same homophonic group. Therefore, this homophonic group includes the homophonic characters "报", "抱", "暴", and "豹" with common levels of common level 2, common level 4, common level 6, and common level 8 respectively, and the homophonic characters can be sorted according to the common level. Understandably, the common levels of the homophonic characters in this homophonic group are only used for illustrative purposes and do not represent the actual common levels. Multiple homophonic groups are set up like this to form a homophonic group library.

[0110] In some embodiments, in the grouping and classification unit, group the homophonic characters in each character; classify the common levels of each character in each group. The character with a higher common level is more commonly used than the character with a lower common level, and a homophonic group library is formed.

[0111] Understandably, the difference between the grouping and classification unit in these some embodiments and the grouping and classification unit in this embodiment is that in this embodiment, first complete the classification of the common levels of each character, and then group the homophonic characters in the characters with classified common levels. In some embodiments, first group the homophonic characters in each character, and then classify the common levels of each character in each group. Understandably, the two are only different in the execution order. In the present invention, the execution order of these two steps is not limited, as long as it can be realized to form each homophonic character group in the homophonic group library, and each character in each homophonic group has a corresponding common level. Of course, the characters in each homophonic character group can be sorted according to the common level.

[0112] In the execution unit 103, use the homophonic characters that are homophonic to the rare characters to give pronunciation reminders to the rare characters; among them, the homophonic characters are more commonly used than the rare characters. Specifically, when a rare character is recognized, retrieve the homophonic characters in the same group as the rare character in the homophonic group library, and obtain the homophonic characters with a higher common level than the rare character to give pronunciation reminders to the rare character.

[0113] Furthermore, obtaining the homophonic characters with a higher common level than the rare character to give pronunciation reminders to the rare character includes: obtaining multiple homophonic characters with a higher common level than the rare character to give interval replacement pronunciation reminders to the rare character; among the multiple homophonic characters, the character with a higher common level is reminded first.

[0114] Specifically, retrieve all the homophonic characters with a higher common level than the rare character in the homophonic group library, and obtain several homophonic characters with a higher common level, for example, obtain the three homophonic characters with the highest common level, and give interval replacement pronunciation reminders to the rare character.

[0115] Of course, it is also possible to use other quantities of homophones for replacement reminders. For example, when there are more than three homophones with a higher common usage level than the rare character, these multiple homophones are replaced at intervals, or the first few homophones with a higher common usage level are used for interval replacement; when the number of homophones with a higher common usage level than the rare character is less than three, all the homophones are used for interval replacement.

[0116] The method of interval replacement pronunciation reminder includes: replacing at regular intervals with three homophones. For example, when the recognized rare character is "豹", it is retrieved in the homophone group library, and the homophone group "报", "抱", "暴", "豹" where the character "豹" is located is retrieved. In this homophone group, the characters "报", "抱", "暴" have a higher common usage level than the character "豹". Therefore, "报", "抱", "暴" can be replaced轮流 to give pronunciation reminders.

[0117] For example, first use the homophone "报" with the highest common usage level for pronunciation reminder. Starting from the time when "报" is used for reminder, when the set regular time is reached, then use the homophone "抱" with the second highest common usage level for pronunciation reminder; starting from the time when "抱" is used for reminder, when the set regular time is reached, then use the homophone "暴" with the second highest common usage level for pronunciation reminder. Starting from the time when "暴" is used for reminder, when the set regular time is reached, if it is determined that the reader has not resumed reading, then use "报" again for pronunciation reminder, and so on in a loop until the reader resumes reading. It can be understood that the regular time can be set according to requirements.

[0118] The regular time can be the time to determine whether the reader is still in a stagnant state. It can be understood that in the execution unit 103, timing starts when a homophone is used to give a pronunciation reminder to a rare character. If the reader is still in a stagnant state after reaching this regular time, it is considered that this homophone is still a rare character for the reader. Therefore, another homophone is replaced to give a pronunciation reminder to the rare character. The regular time can be the same as the normal time interval or greater than the normal time interval to provide the reader with more discrimination time. Or, the regular time is less than the normal time interval, for example, the regular time is one-third of the normal time interval, to show more homophones to the reader.

[0119] Of course, to determine whether the reader is in a stagnant state, the same method of determining whether the current reading speed is less than the normal reading speed as described above can also be used. This is the same as the above determination method and will not be repeated here.

[0120] In some embodiments, the method of interval replacement pronunciation reminder includes: receiving a replacement instruction input by the reader to perform homophone replacement reminder. Similarly, the replacement of homophones is also in the order of preferentially displaying those with a higher common usage level, that is, reminder is performed in the order from the highest common usage level to the lowest common usage level.

[0121] In this application, the pronunciation reminder of uncommon characters is given priority to homophones with high common levels, that is, homophones with small common level numbers, and multiple homophones are used to pronounce uncommon characters to improve the reading efficiency of the reader. In other embodiments, multiple homophones can be used simultaneously to pronounce uncommon characters.

[0122] Among them, the pronunciation reminder of uncommon characters with homophones can be displayed above the uncommon characters. It can be understood that in the text content, there is a gap between each line of text, and displaying the homophone above the uncommon characters is convenient for readers to view and is in line with daily habits.

[0123] It is understandable that before the reader reads the text, the homophone group library can be recorded into the reading device first. Therefore, during the reader's reading process, the pronunciation reminder of uncommon characters can be realized through the homophone group library, and the homophone can be displayed in a prominent form, for example, the homophone is different from other characters in the reading text in color, thickness, font, etc.

[0124] It is understandable that the same reader may read different texts at different speeds, and different readers may read the same text at different speeds. Therefore, the tracking unit 102 tracks the text in the text according to the current reader's reading speed, that is, the conversion of speech into text; and the execution unit 103 sets a pause condition based on the current reader's reading speed.

[0125] In this embodiment, the pronunciation of uncommon characters is automatically prompted based on the reader's reading speed, and homophones can be dynamically replaced according to the reader's pauses, which can improve the reader's reading coherence and efficiency.

[0126] In another embodiment of the present invention, the device for reminding the pronunciation of uncommon characters comprises:

[0127] The display unit is used to display the text to be read aloud.

[0128] The tracking unit is used to receive the read voice, identify the text corresponding to the read voice, and track the text in the read text word by word.

[0129] The execution unit is used to, when it is determined that the reading parameters meet the stagnation condition, take the first character to be read as an uncommon character according to the tracking progress and provide a pronunciation reminder for the uncommon character.

[0130] The difference between this embodiment and the above embodiment is that, in the execution unit, the pronunciation reminder for uncommon characters includes: pronouncing the uncommon characters with homophones that have the same pronunciation as the uncommon characters; and / or, pronouncing the uncommon characters with the pinyin of the uncommon characters; and / or, pronouncing the uncommon characters in the form of voice.

[0131] It is understandable that the pronunciation reminder of the uncommon character is performed using a homophone of the uncommon character, which is the same as the execution method of the above embodiment and will not be described in detail here. Specifically, the pronunciation reminder of the uncommon character can be performed by pre-establishing a Chinese Pinyin library for each character. When the uncommon character is recognized, the Chinese Pinyin corresponding to the uncommon character is retrieved from the Chinese Pinyin library and the Chinese Pinyin corresponding to the uncommon character is displayed above the uncommon character. Of course, the Chinese Pinyin library can be implemented using an existing Chinese Pinyin library.

[0132] The uncommon characters are reminded to be pronounced in a voice manner. Specifically, a voice unit can be provided so that when an uncommon character is recognized, the uncommon character is announced through the voice unit.

[0133] It is understandable that one or more of the above-mentioned combinations can be used to provide pronunciation reminders for uncommon characters, so as to be suitable for a variety of people.

[0134] The present invention provides a computer device, which includes a processor and a memory, wherein the processor is communicatively connected to the memory; the memory is used to store computer programs; and the processor is used to execute the computer programs stored in the memory to implement the steps of the above-mentioned uncommon character pronunciation reminder method.

[0135] A readable storage medium of the present invention stores a computer program thereon, and when the computer program is executed by a processor, the steps of the above-mentioned uncommon character pronunciation reminder method are implemented.

[0136] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The above-described program can be stored in a readable storage medium of a terminal device such as a computer or a mobile phone. When executed, the program can include the processes in the above-described method embodiments. The above-described storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0137] It is understandable that the above embodiments only express the preferred implementation modes of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the patent scope of the present invention. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present invention, the above technical features can be freely combined, and several deformations and improvements can be made, all of which fall within the scope of protection of the present invention. Therefore, all equivalent changes and modifications made to the scope of the claims of the present invention should fall within the scope of coverage of the claims of the present invention.

Claims

1. A method for reminding the pronunciation of uncommon characters. It is characterized in that include: S01. Classify each character into common use levels, where characters with high common use levels are more commonly used than characters with low common use levels; Grouping homophones in the characters classified into common levels to form a homophone group library; or, Grouping homophones in each character; dividing each character in each group into common use levels, where characters with high common use levels are more commonly used than characters with low common use levels, to form a homophone group library; S10, displaying the reading text; S20, receiving a read voice, identifying the text corresponding to the read voice, and tracking the text in the read text word by word; S30. When it is determined that the reading parameters meet the stagnation condition, the first character to be read is regarded as an uncommon character according to the tracking progress, and homophones in the same group as the uncommon character are searched in the homophone group library, and homophones with a higher common level than the uncommon character are obtained to remind the pronunciation of the uncommon character.

2. The method for reminding the pronunciation of uncommon characters according to claim 1, It is characterized in that Pronouncing the uncommon characters includes: pronouncing the uncommon characters by the pinyin of the uncommon characters, and / or pronouncing the uncommon characters by voice.

3. The method for reminding the pronunciation of uncommon characters according to claim 1, It is characterized in that The characters include: extracting sample text by itself, performing single-word segmentation and statistics on the sample text to obtain the characters; or obtaining third-party statistical data of the input method to obtain the characters; When each character is obtained by extracting sample texts by itself, the common level classification of each character includes: classifying each character into common levels according to the number of times each character appears; When each character is obtained by acquiring third-party statistical data of the input method, classifying each character into commonly used levels includes: classifying each character into commonly used levels according to the number of times each character is used.

4. The method for reminding the pronunciation of uncommon characters according to claim 1, It is characterized in that Obtaining a homophone with a higher common level than the uncommon character to remind the uncommon character of pronunciation, including: A plurality of homophones with a higher common level than the uncommon character are obtained to perform interval replacement pronunciation reminders on the uncommon character; wherein, among the plurality of homophones, the characters with a higher common level are reminded first.

5. The method for reminding the pronunciation of uncommon characters according to claim 1, It is characterized in that Also includes: receiving a trial reading voice, and obtaining a normal time interval and a normal reading speed in a normal reading state according to the trial reading voice; The reading parameter is the current stagnation time, and the stagnation condition is the normal time interval; in step S30, when it is determined that the reading parameter meets the stagnation condition, it includes: when it is determined that the current stagnation time is greater than the normal time interval; or, The reading parameter is the current reading speed, and the stagnation condition is the normal reading speed. In step S30, when it is determined that the reading parameter meets the stagnation condition, it includes: when it is determined that the current reading speed is less than the normal reading speed.

6. The method for reminding the pronunciation of uncommon characters according to claim 1, It is characterized in that The method of reminding the pronunciation of the uncommon character by using a homophone with the uncommon character includes: displaying the homophone above the uncommon character.

7. A device for reminding the pronunciation of uncommon characters. It is characterized in that include: A grouping unit is used to classify each character into a common level, where characters with a high common level are more commonly used than characters with a low common level; Grouping homophones in the characters classified into common levels to form a homophone group library; or, Grouping homophones in each character; dividing each character in each group into common levels, where characters with high common levels are more commonly used than characters with low common levels, to form a homophone group library; A display unit, used for displaying the text to be read aloud; A tracking unit, used for receiving a read voice, identifying the text corresponding to the read voice, and tracking the text in the read text word by word; The execution unit is used to, when it is determined that the reading parameters meet the stagnation condition, take the first character to be read as an uncommon character according to the tracking progress, retrieve homophones in the same group as the uncommon character in the homophone group library, and obtain homophones with a higher common level than the uncommon character to remind the pronunciation of the uncommon character.

8. A computer device, It is characterized in that It comprises a processor and a memory, wherein the processor is communicatively connected to the memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to implement the pronunciation reminder method for uncommon characters as described in any one of claims 1-6.

Images