Input Recognition Method, Device and Storage Medium

Abstract

The present invention discloses an input recognition method, device and storage medium, mainly aiming to solve the problem of forgetting the characters when writing by hand and being unable to input by spelling. Among them, the above input recognition method may include: determining first text information corresponding to the graphical data according to the input graphical data, where the graphical data includes writing data of the text. Recognizing the first text information and obtaining pronunciation information of the first text information. Generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information.

Description

Technical Field

[0001] The present invention relates to the technical field of text processing, and in particular, to an input recognition method, apparatus, and storage medium. Background Art

[0002] An input method refers to an encoding method adopted for inputting various symbols into an electronic information device (such as a computer or a mobile phone). The handwriting input method is widely used because users do not need to master the text spelling ability. However, the current handwriting input method requires users to master the writing ability of the text to be input, which brings great resistance to the use of the handwriting input method in today's era when forgetting the characters often occurs. Summary of the Invention

[0003] In view of the above problems, embodiments of the present application provide an input recognition method, apparatus, and storage medium, mainly aiming to solve the problem of forgetting the characters during handwriting input and being unable to input by spelling.

[0004] To solve the above technical problems, in a first aspect, embodiments of the present application provide an input recognition method, which may include:

[0005] Determine first text information corresponding to the graphical data according to the input graphical data, where the graphical data includes writing data of the text;

[0006] Recognize the first text information and obtain pronunciation information of the first text information;

[0007] Generate second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information.

[0008] In a first possible implementation manner of the first aspect, the first text information is Chinese character text information.

[0009] The recognizing the first text information and obtaining the pronunciation information of the first text information includes:

[0010] Recognize the Chinese character text information and obtain the pinyin syllable of each Chinese character in the Chinese character text information;

[0011] The generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information includes:

[0012] Generate candidate Chinese character text information having the same or similar pronunciation as the combination of the pinyin syllables based on the pinyin syllables.

[0013] In a second possible implementation manner of the first aspect, the generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information includes:

[0014] Generate phrases that have the same or similar pronunciations as the pronunciation information through a preset phrase combination model based on the pronunciation information.

[0015] In the third possible implementation manner of the first aspect, the method further includes:

[0016] Use the second text information as a candidate item, or display the second text information.

[0017] In the fourth possible implementation manner of the first aspect, the displaying the second text information includes:

[0018] When it is recognized that the first text information is an unconventional phrase and / or the second text information is a high-frequency phrase, display the second text information.

[0019] In the fifth possible implementation manner of the first aspect, the generating, based on the pronunciation information, second text information that has the same or similar pronunciation as the pronunciation information includes:

[0020] Generate second text information that has the same or similar pronunciation as the pronunciation information based on the pronunciation information and in combination with the above text information.

[0021] In the sixth possible implementation manner of the first aspect, the method further includes:

[0022] Respectively determine the relevance degrees of the first text information and the second text information to the above text information;

[0023] Select the text information with a higher relevance degree to the above text information for display.

[0024] In a second aspect, an input recognition device provided by an embodiment of the present application may include:

[0025] A determination unit, configured to determine first text information corresponding to the graphical data according to the input graphical data, where the graphical data includes writing data of the text;

[0026] An identification unit, configured to identify the first text information and obtain the pronunciation information of the first text information;

[0027] A generation unit, configured to generate second text information that has the same or similar pronunciation as the pronunciation information based on the pronunciation information.

[0028] In the first possible implementation manner of the second aspect, the first text information is Chinese character text information, and the identification unit is specifically configured to:

[0029] Identify the Chinese character text information, and obtain the pinyin syllables of each Chinese character in the Chinese character text information;

[0030] The generating unit is specifically configured to:

[0031] Based on the pinyin syllables, generate candidate Chinese character text information that has the same or similar pronunciation as the combination of the pinyin syllables.

[0032] In the second possible implementation manner of the second aspect, the generating unit is specifically configured to:

[0033] Based on the pronunciation information, generate phrases that have the same or similar pronunciation as the pronunciation information through a preset word formation model.

[0034] In the third possible implementation manner of the second aspect, the generating unit is further configured to:

[0035] Use the second text information as a candidate, or display the second text information.

[0036] In the fourth possible implementation manner of the second aspect, the generating unit is specifically configured to:

[0037] When it is recognized that the first text information is an unconventional phrase and / or the second text information is a high-frequency phrase, display the second text information.

[0038] In the fifth possible implementation manner of the second aspect, the generating unit is specifically configured to:

[0039] Based on the pronunciation information and in combination with the above context information, generate second text information that has the same or similar pronunciation as the pronunciation information.

[0040] In the sixth possible implementation manner of the second aspect, the generating unit further includes:

[0041] Respectively determine the relevance of the first text information and the second text information to the above context information;

[0042] Select the text information with a higher relevance to the above context information for display.

[0043] In a third aspect, an embodiment of the present application provides a storage medium, the storage medium includes a stored program, wherein when the program runs, it controls the device where the storage medium is located to execute the input recognition method as described in any one of the foregoing first aspects.

[0044] Fourthly, an embodiment of the present application provides a device for input recognition, including a memory and one or more programs. One or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include the input recognition method as described in any one of the foregoing first aspects.

[0045] With the above technical solution, for the problems existing in the prior art, the input recognition method provided by the embodiment of the present application determines the first text information corresponding to the graphical data according to the input graphical data, where the graphical data includes the writing data of the text. Recognize the first text information and obtain the pronunciation information of the first text information. Based on the pronunciation information, generate second text information having the same or similar pronunciation as the pronunciation information. In the above solution, by recognizing the writing data of the text in the graphical data, that is, by analyzing the glyphs of the input text to obtain the first text. Then, through the pronunciation information of the first text obtained by analysis, obtain second text information having the same or similar pronunciation as the pronunciation information. Thus, it can be ensured that when the user cannot write a specific text, the user can input a text having the same or similar pronunciation as the text to be written. Through this recognition method, after recognizing the written text, generate a text having the same or similar pronunciation as the written text according to the pronunciation corresponding to the written text, so as to facilitate the user to quickly assist in generating the text that the user hopes to input but cannot write through the text that the user can write when forgetting the characters and not having the text spelling ability. It provides great convenience for the user to use the input method. Reduces the usage threshold of the handwriting input method. Improves the efficiency of the user's text input through the handwriting input method and improves the user experience at the same time.

[0046] Correspondingly, the device and storage medium based on the above input recognition method also have the same effect. The above description is only an overview of the technical solution of the embodiment of the present application. In order to be able to understand the technical means of the embodiment of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and understandable, the following specifically illustrates the specific implementation manners of the embodiment of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the embodiments of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0048] Figure 1 Shows a flowchart of an input recognition method provided by an embodiment of the present application;

[0049] Figure 2 A block diagram of an input recognition device provided by an embodiment of the present application is shown;

[0050] Figure 3 A schematic diagram of the structure of the client provided in the embodiment of the present application;

[0051] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the embodiments of the present application to be fully communicated to those skilled in the art.

[0053] The present application embodiment provides an input recognition method, such as Figure 1 As shown, the method may include steps: S101, S102 and S103.

[0054] S101, determining first text information corresponding to the input graphic data according to the graphic data.

[0055] The above-mentioned graphical data includes text writing data.

[0056] Exemplarily, the graphical data may be understood as image data recording writing data of Chinese characters or other languages. The Chinese characters or other languages ​​may be directly input by handwriting or by other hardware devices such as a stylus pen, which is not limited here.

[0057] Exemplarily, the first text information may be obtained by recognizing a preset handwriting model based on the graphical data. The preset handwriting model may be obtained by training a large number of image data samples to protect writing data. The preset handwriting model may predict the corresponding text information based on the writing data of the text recorded in the image data. For example, a user writes the word "you" with his finger on the mobile phone screen, and image data recording the writing data of the word "you" is generated. The image data recording the writing data of the word "you" can be recognized by the preset handwriting model, thereby predicting the text information "you" corresponding to the image data recording the writing data of the word "you".

[0058] S102: Identify the first text information and obtain pronunciation information of the first text information.

[0059] Exemplarily, the pronunciation information corresponding to the above first text information can be queried according to the pre-stored correspondence between text information and pronunciation.

[0060] For example, the handwritten writing data is "tao tie sheng yan", and the recognized first text information is "tao tie sheng yan". Then, according to the pre-stored correspondence between characters and pronunciation, the pronunciation of the above "tao tie sheng yan" can be queried as "tao tie shengyan". It should be noted that the above pronunciation can be pronunciation information with intonation or without intonation.

[0061] Exemplarily, the pre-stored correspondence between text information and pronunciation can be corresponding data stored in the terminal or corresponding data stored in the server. If the above correspondence is the corresponding data stored in the server, then the terminal can send the recognized text information to the server, enabling the server to query the pronunciation information corresponding to the above first text information according to the pre-stored correspondence between text information and pronunciation.

[0062] S103, based on the above pronunciation information, generate a second text information having the same or similar pronunciation as the above pronunciation information.

[0063] Exemplarily, the above second text information can be text information having the same pronunciation as the above pronunciation information. If the user hopes to input "tao tie sheng yan", but due to the complex glyphs or large number of strokes of some characters, there are situations such as forgetting the character when picking up the pen or being unsure of the specific writing method. For example, unable to write "tao", "tie", and "yan" among them, then the user may replace the characters that cannot be written with homophonic characters that they can write. For example, handwritten input can form image data including the writing data of "tao tie sheng yan", and then the recognized first text information is "tao tie sheng yan". Then, according to the pre-stored correspondence between characters and pronunciation, the pronunciation of the above "tao tie sheng yan" can be queried as "tao tie sheng yan", and then the above second text information can be "tao tie sheng yan" which also has the pronunciation of "tao tie sheng yan".

[0064] Exemplary, if the user wants to input "Tao Tie Sheng Yan", but due to the complex shape of some characters, or the large number of strokes, the user may forget the characters or be uncertain about the specific writing method. For example, the "Tao", "Tie" and "Yan" cannot be written, and the user can't think of the characters that are homophonic with "Yan", or the user can't write the characters that are homophonic with "Yan". Then the user may replace the characters that cannot be written with characters that are similar in pronunciation to the characters that he can write. For example, the image data including the writing data of "Tao Tie Sheng Yan" can be formed by handwriting input, and the first text information is identified as "Tao Tie Sheng Yan". Then according to the correspondence between the pre-stored characters and the pronunciation, it can be found that the pronunciation of the above "Tao Tie Sheng Yan" is "tao tie shengyan", and if the "yan" here includes the tone, it should be the second tone, so the above second text information can be "Tao Tie Sheng Yan" with a pronunciation similar to the above "Tao Tie Sheng Yan".

[0065] In summary, the above embodiment provides an input recognition method, for the problems existing in the prior art, the above method determines the first text information corresponding to the graphical data according to the input graphical data, wherein the graphical data includes the writing data of the text. Identify the above first text information and obtain the pronunciation information of the above first text information. Based on the above pronunciation information, generate the second text information with the same or similar pronunciation as the above pronunciation information. In the above scheme, the writing data of the text in the graphical data is identified, that is, the first text is obtained by analyzing the glyph of the input text. Then, the second text information with the same or similar pronunciation as the above pronunciation information is obtained by analyzing the pronunciation information of the obtained first text. Thus, it can be ensured that when the user cannot write a specific text, the text with the same or similar pronunciation as the text to be written can be input, and after the written text is identified through this recognition method, the text with the same or similar pronunciation as the written text is generated according to the pronunciation corresponding to the written text, so as to facilitate the user to quickly generate the text that he wants to input but cannot write through the text he can write when he forgets the words and does not have the ability to spell the text. It provides great convenience for users to use input methods. It lowers the threshold for using handwriting input methods. It improves the efficiency of text input by users through handwriting input methods and improves the user experience.

[0066] According to some embodiments, the first text information is Chinese text information.

[0067] The step of identifying the first text information and obtaining the pronunciation information of the first text information includes:

[0068] Recognize the above Chinese character text information, and obtain the pinyin syllable of each Chinese character in the above Chinese character text information;

[0069] Generating second text information having the same or similar pronunciation as the above pronunciation information based on the above pronunciation information, including:

[0070] Generating candidate Chinese character text information having the same or similar pronunciation as the combination of the above pinyin syllables based on the above pinyin syllables.

[0071] It should be noted that since there are a very large number of second text information having the same or similar pronunciation as the pronunciation information corresponding to the first text information, further screening is required to determine the text that the user actually hopes to write. According to some embodiments, generating second text information having the same or similar pronunciation as the above pronunciation information based on the above pronunciation information, including:

[0072] Generating phrases having the same or similar pronunciation as the above pronunciation information through a preset word combination model based on the above pronunciation information.

[0073] Exemplarily, if the handwritten writing data is "tao tie sheng yan", the recognized first text information is "tao tie sheng yan". Then, according to the pre-stored correspondence between characters and pronunciations, it can be queried that the pronunciation of the above "tao tie sheng yan" is "taotie sheng yan". Then, the above second text information can be different texts such as "taotie sheng yan" (gluttonous feast), "taotie sheng yan" (gluttonous leftover feast), and "taotie sheng yan" (gluttonous victory in beauty), or texts with similar pronunciations such as "taotie sheng yan" (gluttonous voice statement), "taotie sheng yan" (gluttonous grand banquet), etc. Then, the second text information can be finally determined as "taotie sheng yan" according to the above preset word combination model.

[0074] According to some embodiments, the above method may further include:

[0075] Using the second text information as a candidate item, or displaying the second text information.

[0076] It should be noted that after generating the second text information, the second text information can be used as a candidate item for the user to select, or the above second text information can be directly displayed. To recommend the text information recognized by this method to the user, which provides convenience for the user's input. And give the user a chance to choose to avoid causing trouble to the user due to misrecognition. For example, if the text that the user hopes to input is "xiaoqiao", because the user cannot write "qiao", the handwritten text is "xiaoqiao". If the finally recognized second text information is "xiaoqiao", if it is directly typed into the text box as the result text, since "xiaoqiao" does not belong to the text that the user hopes to input, it may cause trouble to the user. And if the second text information is displayed for the user to select. When the generated text cannot be further distinguished by the recognition model, all possible second texts can be displayed for the user to select to achieve the effect of accurate input.

[0077] Exemplarily, the displaying of the second text information may include:

[0078] When it is recognized that the first text information is an unconventional phrase and / or the second text information is a high-frequency phrase, display the second text information.

[0079] Exemplarily, when considering whether to recommend the recognized second text information to the user, it may be considered whether the first text information is an unconventional phrase. If it is an unconventional phrase, then it can be judged that one or more characters in the text input by the user are likely to be incorrect. In this case, it is possible to select and recommend the second text information recognized according to the pronunciation information of the first text information.

[0080] For example, the first text information is "Tao Tie". When considering whether to recommend the recognized second text information to the user, it may be considered whether the first text information "Tao Tie" is an unconventional phrase. Obviously, the first text information "Tao Tie" is an unconventional phrase. Then it can be judged that one or more characters in the text input by the user are likely to be incorrect. In this case, it is possible to select and recommend the second text information "Taotie" recognized according to the pronunciation information of the first text information.

[0081] For example, the first text information is "Xiao Qiao". When considering whether to recommend the recognized second text information to the user, it may be considered whether the first text information "Xiao Qiao" is an unconventional phrase. Obviously, the first text information "Xiao Qiao" is a conventional phrase. Then it can be judged that the text input by the user is likely to be the text originally intended to be input. In this case, it is possible not to select and recommend the second text information "Xiaociao" recognized according to the pronunciation information of the first text information. Or not perform the recognition operation of the second text information to reduce the consumption of computing resources and improve the efficiency of the input recognition method.

[0082] Exemplarily, the above-mentioned high-frequency phrase may be a phrase frequently used by this user obtained through statistics, or a phrase frequently used by all users of the network, or a phrase frequently used by a specific user within a certain time period, which is not limited here. When considering whether to recommend the recognized second text information to the user, it may also be considered whether the second text information is a high-frequency phrase. If it is a high-frequency phrase, then it can be judged that one or more characters in the text input by the user are likely to be incorrect, resulting in the failure to directly recognize the second text through the handwriting model. In this case, it is possible to select and recommend the second text information recognized according to the pronunciation information of the first text information.

[0083] For example, if the first text information is "Tao Tie", when considering whether to recommend the recognized second text information to the user, it is also possible to consider whether the above-mentioned second text information "Taotie" is a high-frequency phrase. Obviously, "Taotie" is a high-frequency phrase both in the phrases frequently used by users across the network and in the phrases frequently used by this user obtained through statistics. Therefore, it can be judged that it is very likely that one or more characters in the text input by the user are incorrect, resulting in the failure to directly recognize the second text "Taotie" through the handwriting model. In this case, it is possible to select and recommend the second text information "Taotie" recognized based on the pronunciation information of the first text information.

[0084] Since there are very many second text information with the same or similar pronunciations as the pronunciation information corresponding to the first text information, further screening is required to determine the text that the user actually hopes to write. To solve the above problem, generating, based on the pronunciation information, second text information with the same or similar pronunciation as the pronunciation information includes:

[0085] Generating, based on the pronunciation information and in combination with the above text information, second text information with the same or similar pronunciation as the pronunciation information.

[0086] Exemplarily, the above text information may be the text information that the user has input before inputting the above graphical data. It is possible to select and display the text information with a relatively high degree of association with the above text information to further screen and determine the text that the user actually hopes to write, and improve the accuracy of text recommendation when the user inputs.

[0087] In some examples, the above method may further include:

[0088] Respectively judge the degree of association between the above first text information and the above second text information and the above text information;

[0089] Select and display the text information with a relatively high degree of association with the above text information.

[0090] Exemplarily, when determining whether to recommend the first text information or the second text information, it is possible to consider the text information that the user has input before inputting the above graphical data, select and display the text information with a relatively high degree of association with the above text information to further screen and determine the text that the user actually hopes to write, and improve the accuracy of text recommendation when the user inputs.

[0091] Exemplarily, the first text information is "look down upon", and the second text information is "small bridge". When determining whether to recommend the first text information "look down upon" or the second text information "small bridge", the text information that the user has entered before inputting the above graphical data can be considered. For example, if the text information that the user has entered before inputting the above graphical data is "a river passes through", then the text information "small bridge" with a higher relevance to the above information can be selected for display to further screen and determine the text that the user actually hopes to write, thereby improving the accuracy of text recommendation when the user inputs text.

[0092] In the above example, factors such as whether it can form a phrase or a sentence with the recognized text information are used as selection conditions to further screen and determine the text that the user actually hopes to write. In some examples, the overall meaning of the text information that the user has entered before inputting the above graphical data can also be used to further screen and determine the text that the user actually hopes to write. For example, the first text information is "look down upon", and the second text information is "small bridge". When determining whether to recommend the first text information "look down upon" or the second text information "small bridge", the text information that the user has entered before inputting the above graphical data can be considered. For example, if the overall meaning of the text information that the user has entered before inputting the above graphical data describes landscape and other information, then the text information "small bridge" with a higher relevance to the above information can be selected for display to further screen and determine the text that the user actually hopes to write, thereby improving the accuracy of text recommendation when the user inputs text.

[0093] According to some embodiments, as an implementation of the input recognition method shown in the above Figure 1 and various embodiments, the embodiment of the present application further provides a generating device for generating a generative summary, which is used to implement the above Figure 1 and the methods shown in the above multiple embodiments. The device embodiment corresponds to the foregoing method embodiment. For the convenience of reading, the details in the foregoing method embodiment will not be repeated one by one in this device embodiment. However, it should be clear that the device in this embodiment can correspondingly implement all the contents in the foregoing method embodiment. As Figure 2 shown, the input recognition device includes: a determination unit 21, an identification unit 22, and a generation unit 23, where:

[0094] The generation unit 21 can be used to determine the first text information corresponding to the graphical data according to the input graphical data, where the graphical data includes the writing data of the text.

[0095] The identification unit 22 can be used to identify the first text information and obtain the pronunciation information of the first text information.

[0096] The recognition unit 23 can be used to generate second text information that has the same or similar pronunciation as the pronunciation information based on the pronunciation information.

[0097] With the above technical solution, for the problems existing in the prior art, the above input recognition device determines the first text information corresponding to the graphical data according to the input graphical data, where the graphical data includes the writing data of the text. Recognize the first text information and obtain the pronunciation information of the first text information. Based on the pronunciation information, generate second text information that has the same or similar pronunciation as the pronunciation information. In the above solution, by recognizing the writing data of the text in the graphical data, that is, by analyzing the glyphs of the input text to obtain the first text. Then, through the pronunciation information of the first text obtained by analysis, obtain second text information that has the same or similar pronunciation as the pronunciation information. Thus, it can be ensured that when the user cannot write a specific text, the user can input a text with the same or similar pronunciation as the text that the user hopes to write. Through this recognition method, after the written text is recognized, according to the pronunciation corresponding to the written text, generate a text with the same or similar pronunciation as the written text, so as to facilitate the user to quickly generate the text that the user hopes to input but cannot write with the text that the user can write when forgetting the characters and not having the text spelling ability. It provides great convenience for the user to use the input method. Reduces the usage threshold of the handwriting input method. Improves the efficiency of the user to input text through the handwriting input method and at the same time improves the user experience.

[0098] Exemplarily, the first text information is Chinese character text information, and the recognition unit is specifically used for:

[0099] Recognize the Chinese character text information and obtain the pinyin syllables of each Chinese character in the Chinese character text information;

[0100] The generation unit is specifically used for:

[0101] Based on the pinyin syllables, generate candidate Chinese character text information that has the same or similar pronunciation as the combination of the pinyin syllables.

[0102] Exemplarily, the generation unit is specifically used for:

[0103] Based on the pronunciation information, generate phrases that have the same or similar pronunciation as the pronunciation information through a preset word formation model.

[0104] Exemplarily, the generation unit is further used for:

[0105] Use the second text information as a candidate item, or display the second text information.

[0106] Exemplarily, the generation unit is specifically used for:

[0107] When it is recognized that the first text information is an unconventional phrase and / or the second text information is a high-frequency phrase, display the second text information.

[0108] Exemplarily, the generating unit is specifically configured to:

[0109] Based on the pronunciation information and in combination with the previous context information, generate second text information having the same or similar pronunciation as the pronunciation information.

[0110] Exemplarily, the generating unit further includes:

[0111] Respectively determine the relevance of the first text information and the second text information to the previous context information;

[0112] Select the text information with a higher relevance to the previous context information for display.

[0113] Exemplarily, the generating unit further includes:

[0114] Respectively determine the relevance of the first text information and the second text information to the previous context information;

[0115] Select the text information with a higher relevance to the previous context information for display.

[0116] The method provided by the embodiments of the present application can be executed by a client or by a server. The client and the server for executing the above method are described below respectively.

[0117] Figure 3 FIG. shows a block diagram of a client 300. For example, the client 300 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0118] Referring to Figure 3 , the client 300 may include one or more of the following components: a processing component 302, a memory 304, a power component 306, a multimedia component 308, an audio component 310, an input / output (I / O) interface 312, a sensor component 314, and a communication component 316.

[0119] The processing component 302 generally controls the overall operations of the client 300, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing element 302 may include one or more processors 320 to execute instructions to complete all or part of the steps of the above - mentioned methods. In addition, the processing component 302 may include one or more modules to facilitate the interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate the interaction between the multimedia component 308 and the processing component 302.

[0120] The memory 304 is configured to store various types of data to support the operations of the client 300. Examples of such data include instructions for any application or method operating on the client 300, contact data, phone book data, messages, pictures, videos, etc. The memory 304 can be implemented by any type of volatile or non - volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read - only memory (EEPROM), erasable programmable read - only memory (EPROM), programmable read - only memory (PROM), read - only memory (ROM), magnetic memory, flash memory, magnetic disks, or optical disks.

[0121] The power component 306 provides power for various components of the client 300. The power component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the client 300.

[0122] The multimedia component 308 includes a screen that provides an output interface between the client 300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can not only sense the boundaries of touch or swipe actions, but also detect the duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 308 includes a front - facing camera and / or a rear - facing camera. When the client 300 is in an operating mode, such as a shooting mode or a video mode, the front - facing camera and / or the rear - facing camera can receive external multimedia data. Each front - facing camera and rear - facing camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0123] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC) that is configured to receive external audio signals when the client 300 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 304 or transmitted via the communication component 316. In some embodiments, the audio component 310 further includes a speaker for outputting audio signals.

[0124] The I / O interface provides an interface between the processing component 302 and a peripheral interface module, and the peripheral interface module can be a keyboard, a click wheel, buttons, etc. These buttons can include, but are not limited to: a home button, a volume button, a power button, and a lock button.

[0125] The sensor component 314 includes one or more sensors for providing an assessment of various aspects of the status of the client 300. For example, the sensor component 314 can detect the on / off state of the device 300, the relative positioning of components, such as the display and keypad of the client 300, the sensor component 314 can also detect a change in the position of the client 300 or a component of the client 300, the presence or absence of user contact with the client 300, the orientation or acceleration / deceleration of the client 300, and the temperature change of the client 300. The sensor component 314 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor component 314 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 314 can further include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0126] The communication component 316 is configured to facilitate communication between the client 300 and other devices in a wired or wireless manner. The client 300 can access a wireless network based on communication standards, such as WiFi, 2G, or 3G, or a combination thereof. In an exemplary embodiment, the communication component 316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0127] In an exemplary embodiment, the client 300 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the following method:

[0128] Determine first text information corresponding to the input graphical data, where the graphical data includes writing data of text;

[0129] Identify the first text information and obtain pronunciation information of the first text information;

[0130] Generate second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information.

[0131] Exemplarily, the above first text information is Chinese character text information,

[0132] The identifying the first text information and obtaining the pronunciation information of the first text information includes:

[0133] Identify the Chinese character text information and obtain the pinyin syllables of each Chinese character in the Chinese character text information;

[0134] The generating the second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information includes:

[0135] Generate candidate Chinese character text information having the same or similar pronunciation as the combination of the pinyin syllables based on the pinyin syllables.

[0136] Exemplarily, the generating the second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information includes:

[0137] Generate phrases having the same or similar pronunciation as the pronunciation information through a preset word combination model based on the pronunciation information.

[0138] Exemplarily, the above method further includes:

[0139] Use the second text information as a candidate item, or display the second text information.

[0140] Exemplarily, the displaying the second text information includes:

[0141] When it is recognized that the first text information is an unconventional phrase and / or the second text information is a high-frequency phrase, display the second text information.

[0142] Exemplarily, generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information includes:

[0143] Generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information and in combination with the above text information.

[0144] Exemplarily, the above method further includes:

[0145] Respectively determining the relevance of the first text information and the second text information to the above text information;

[0146] Selecting the text information with a higher relevance to the above text information for display.

[0147] Figure 4 FIG. is a schematic structural diagram of a server in an embodiment of the present application. The server 400 may vary greatly due to different configurations or performances, and may include one or more central processing units (CPUs) 422 (for example, one or more processors) and a memory 432, and one or more storage media 430 (for example, one or more mass storage devices) for storing application programs 442 or data 444. Among them, the memory 432 and the storage media 430 may be transient storage or persistent storage. The program stored in the storage media 430 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Further, the central processing unit 422 may be configured to communicate with the storage media 430 and execute a series of instruction operations in the storage media 430 on the server 400.

[0148] Further, the central processing unit 422 may execute the following method:

[0149] Determining first text information corresponding to the graphical data according to the input graphical data, where the graphical data includes writing data of the text;

[0150] Recognizing the first text information and obtaining pronunciation information of the first text information;

[0151] Generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information.

[0152] Exemplarily, the above first text information is Chinese character text information,

[0153] The recognizing the first text information and obtaining pronunciation information of the first text information includes:

[0154] Identify the Chinese character text information and obtain the pinyin syllables of each Chinese character in the Chinese character text information;

[0155] Generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information includes:

[0156] Based on the pinyin syllables, generate candidate Chinese character text information having the same or similar pronunciation as the combination of the pinyin syllables.

[0157] Exemplarily, generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information includes:

[0158] Generate phrases having the same or similar pronunciation as the pronunciation information through a preset word formation model based on the pronunciation information.

[0159] Exemplarily, the above method further includes:

[0160] Use the second text information as a candidate item, or display the second text information.

[0161] Exemplarily, displaying the second text information includes:

[0162] When it is recognized that the first text information is an unconventional phrase and / or the second text information is a high-frequency phrase, display the second text information.

[0163] Exemplarily, generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information includes:

[0164] Generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information and in combination with the above text information.

[0165] Exemplarily, the above method further includes:

[0166] Respectively determine the relevance of the first text information and the second text information to the above text information;

[0167] Select the text information with a higher relevance to the above text information for display.

[0168] The server 400 may further include one or more power supplies 426, one or more wired or wireless network interfaces 450, one or more input / output interfaces 456, one or more keyboards 456, and / or, one or more operating systems 441, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0169] The embodiments of the present application also provide a computer-readable medium, on which instructions are stored, and when executed by one or more processors, cause the device to execute the input recognition method provided in the above method embodiments.

[0170] In summary, for the problems existing in the prior art, the above method determines the first text information corresponding to the graphical data according to the input graphical data, where the graphical data includes the writing data of the text. Recognize the first text information and obtain the pronunciation information of the first text information. Based on the pronunciation information, generate a second text information having the same or similar pronunciation as the pronunciation information. In the above solution, by recognizing the writing data of the text in the graphical data, that is, by analyzing the glyphs of the input text to obtain the first text. Then, through the pronunciation information of the first text obtained by analysis, obtain a second text information having the same or similar pronunciation as the pronunciation information. Thus, it can be ensured that when the user cannot write a specific text, the user can input a text having the same or similar pronunciation as the text to be written, and through this recognition method, after recognizing the written text, generate a text having the same or similar pronunciation as the written text according to the pronunciation corresponding to the written text, thereby facilitating the user to quickly assist in generating the text that the user hopes to input but cannot write through the text that the user can write when forgetting the characters and not having the text spelling ability. It provides great convenience for the user to use the input method. It reduces the usage threshold of the handwriting input method. It improves the efficiency of the user to input text through the handwriting input method and at the same time improves the user experience.

[0171] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present application are pointed out by the following claims.

[0172] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

[0173] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An input recognition method, characterized in that, including: determining first text information corresponding to the input graphical data, where the graphical data includes writing data of text, and the graphical data is image data recording writing data of Chinese characters or text in other languages; identifying the first text information, and querying pronunciation information of the first text information according to a pre-stored correspondence between text information and pronunciation, where the pronunciation information includes pronunciation information without intonation; when it is recognized that the first text information is an unconventional phrase, generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information and in combination with the previous text information; using the second text information as a candidate item, or when the second text information is a high-frequency phrase of all network users, displaying the second text information as a result text and entering it into a text box; when it is recognized that the first text information is a conventional phrase, stopping the recognition of the second text information.

2. The method according to claim 1, characterized in that, The first text information is Chinese character text information. The identifying the first text information and querying the pronunciation information of the first text information according to a pre-stored correspondence between text information and pronunciation includes: identifying the Chinese character text information, and querying the pinyin syllables of each Chinese character in the Chinese character text information according to a pre-stored correspondence between text information and pronunciation; The generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information and in combination with the previous text information includes: generating candidate Chinese character text information having the same or similar pronunciation as the combination of the pinyin syllables based on the pinyin syllables and in combination with the previous text information.

3. The method according to claim 1, wherein The generating second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information and in combination with the previous text information includes: generating a phrase having the same or similar pronunciation as the pronunciation information based on the pronunciation information and in combination with the previous text information through a preset word formation model.

4. The method according to claim 1, wherein The method further includes: respectively determining the relevance degrees of the first text information and the second text information with the previous text information; selecting the text information with a higher relevance degree to the previous text information for display.

5. An input recognition device, characterized in that, including: a determining unit, configured to determine first text information corresponding to the input graphical data, where the graphical data includes writing data of text, and the graphical data is image data recording writing data of Chinese characters or text in other languages; an identifying unit, configured to identify the first text information, and query pronunciation information of the first text information according to a pre-stored correspondence between text information and pronunciation, where the pronunciation information includes pronunciation information without intonation; a generating unit, configured to generate second text information having the same or similar pronunciation as the pronunciation information based on the pronunciation information and in combination with the previous text information when it is recognized that the first text information is an unconventional phrase; using the second text information as a candidate item, or when the second text information is a high-frequency phrase of all network users, displaying the second text information as a result text and entering it into a text box; when it is recognized that the first text information is a conventional phrase, stopping the recognition of the second text information.

6. The device according to claim 5, wherein The first text information is Chinese character text information, and the recognition unit is specifically configured to: Recognize the Chinese character text information, and query the pinyin syllables of each Chinese character in the Chinese character text information according to the pre-stored correspondence between text information and pronunciation. The generation unit is specifically configured to: Based on the pinyin syllables and in combination with the above text information, generate candidate Chinese character text information that has the same or similar pronunciation as the combination of the pinyin syllables.

7. The device according to claim 5, characterized in that, The generation unit is specifically configured to: Based on the pronunciation information, through a preset word combination model and in combination with the above text information, generate word combinations that have the same or similar pronunciation as the pronunciation information.

8. A storage medium, characterized in that, The storage medium includes a stored program, wherein when the program runs, it controls the device where the storage medium is located to execute the input recognition method described in any one of claims 1 to 4.

9. An apparatus for input recognition, characterized in that, It includes a memory, and one or more programs, wherein one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include the input recognition method described in any one of claims 1 to 4.

Images