CN112650398B - Input method, device and medium - Google Patents

Abstract

The embodiments of the present invention provide an input method, device and medium. The method specifically includes: receiving a user's input string; performing intent recognition on the input string to obtain an input intent; and determining and outputting a first candidate corresponding to the input string according to the input intent. The embodiments of the present invention can reduce the user's memory difficulty and improve the input efficiency and input accuracy of the target information.

Description

Input methods, devices and media

Technical Field

The present invention relates to the field of input technology, and in particular to an input method, device and medium therefor.

Background Art

Input method refers to the encoding method used to input characters into computers or other devices (such as mobile phones, tablets, etc.). Input method can be applied in a variety of scenarios.

Current input methods can search in the word library according to the user's input string to obtain corresponding candidates. For example, for the input string "hello", the input method can provide the following candidates: "hello", "your number", "nice", etc.

The inventors discovered during the implementation of the embodiments of the present invention that current input methods usually require users to memorize the pronunciation of target information (including text, or text components, etc., which the user wants to input), which increases the difficulty of memory for the user; moreover, when the pronunciation is remembered incorrectly, the input of the target information cannot be achieved, which affects the input efficiency and accuracy of the target information.

Summary of the invention

The embodiments of the present invention provide an input method, device and medium, which can reduce the memory difficulty of users and improve the input efficiency and input accuracy of target information.

In order to solve the above problem, an embodiment of the present invention discloses an input method, including:

Receive the user's input string;

Performing intent recognition on the input string to obtain input intent;

According to the input intention, a first candidate corresponding to the input string is determined and output.

On the other hand, an embodiment of the present invention discloses an input device, comprising:

A receiving module, used for receiving an input string from a user;

an intention recognition module, used to perform intention recognition on the input string to obtain input intention; and

The first candidate processing module is used to determine and output a first candidate corresponding to the input string according to the input intention.

In another aspect, an embodiment of the present invention discloses a device for input, comprising a memory and one or more programs, wherein the 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 instructions for performing the following operations:

Receive the user's input string;

Performing intent recognition on the input string to obtain input intent;

According to the input intention, a first candidate corresponding to the input string is determined and output.

On the other hand, an embodiment of the present invention discloses a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes a device to perform one or more of the input methods described above.

The embodiments of the present invention include the following advantages:

The embodiment of the present invention performs intent recognition on the input string, and determines and outputs the first candidate corresponding to the input string according to the input intent obtained by the recognition. The above-mentioned intent recognition does not require the user to remember the pronunciation of the target information. Therefore, the embodiment of the present invention can not only reduce the memory difficulty of the user, but also improve the input efficiency and input accuracy of the target information.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

FIG1 is a schematic diagram of an application environment of an input method according to an embodiment of the present invention;

FIG2 is a flow chart of the steps of an input method embodiment 1 of the present invention;

FIG3 is a flow chart of the steps of a second embodiment of an input method of the present invention;

FIG4 is a flow chart of the steps of a third embodiment of an input method of the present invention;

FIG5 is a flow chart of the steps of a fourth embodiment of an input method of the present invention;

FIG6 is a block diagram of an input device embodiment of the present invention;

FIG. 7 is a block diagram of a device 1100 for inputting according to the present invention; and

FIG. 8 is a schematic diagram of the structure of a server in some embodiments of the present invention.

DETAILED DESCRIPTION

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

In view of the difficulty in remembering the pronunciation of radicals in traditional technologies, as well as the low input efficiency and low input accuracy, an input solution is proposed in an embodiment of the present invention. The input solution may include: receiving an input string from a user; performing intent recognition on the input string to obtain an input intent; and determining and outputting a first candidate corresponding to the input string based on the input intent.

The embodiment of the present invention performs intent recognition on the input string, and determines and outputs the first candidate corresponding to the input string according to the input intent obtained by recognition. The above-mentioned intent recognition does not require the user to remember the pronunciation of the target information to be input. Therefore, the embodiment of the present invention can not only reduce the memory difficulty of the user, but also improve the input efficiency and input accuracy of the target information.

The input method provided by the embodiment of the present invention can be applied to the application environment shown in Figure 1. As shown in Figure 1, the client 100 and the server 200 are located in a wired or wireless network, and the client 100 and the server 200 interact with data through the wired or wireless network.

Optionally, the client 100 can be run on a terminal, which specifically includes but is not limited to: a smart phone, a tablet computer, an e-book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer, a car computer, a desktop computer, a set-top box, a smart TV, a wearable device, etc. The client 100 can correspond to a website or an APP (Application). The client 100 can correspond to an application such as an input method APP and an instant messaging APP.

The server of the embodiment of the present invention may be a cloud server. The cloud server is a simple, efficient, secure, reliable, and elastically scalable computing service. The resource information of the cloud server is dynamic, so that its processing capacity can be elastically scalable. The server can use rich resources to obtain corresponding prediction candidates for prediction requests. The server can also return prediction candidates to the client if the quality of the prediction candidate meets the preset quality conditions (such as the quality score exceeds the score threshold, etc.); in other words, if there is no prediction candidate that meets the preset quality conditions, the prediction candidate will not be returned to the client.

The embodiments of the present invention can be applied to input method programs of various input methods such as keyboard symbols, handwriting, and voice. Taking the keyboard symbol input method as an example, the user can input text through a coded string, and the input string can refer to the coded string input by the user. In the field of input methods, for input method programs such as Chinese, Japanese, Korean, or other languages, the input string input by the user can usually be converted into a candidate of the corresponding language. The following is mainly explained by taking Chinese as an example, and other languages such as Japanese and Korean can be referenced to each other. It can be understood that the above-mentioned Chinese input method can include but is not limited to full spelling, simplified spelling, strokes, Wubi, etc., and the embodiments of the present invention do not limit the specific input method program corresponding to a certain language.

Taking Chinese input as an example, the types of encoded character strings may include: pinyin string, character string (such as Wubi string, etc.), or voice feature string, etc. Taking English input as an example, the types of encoded character strings may include: letter string, etc.

In actual applications, for the input method of keyboard symbols, the user can input the above input string through a physical keyboard or a virtual keyboard. For example, for a terminal with a touch screen, a virtual keyboard can be set in the input interface to input the input string by triggering the virtual keys included in the above virtual keyboard. Optionally, examples of the above virtual keyboard may include: a 9-key keyboard and a 26-key keyboard. In addition, it can be understood that in addition to the virtual keys corresponding to letters, the above input interface can also be provided with symbol keys, number keys, function keys such as Chinese-English switching keys, or toolbar keys, etc. It can be understood that the embodiment of the present invention does not limit the specific keys included in the input interface.

According to some embodiments, the input string may include, but is not limited to, a key symbol or a combination of multiple key symbols input by the user through keys. The key symbol may specifically include pinyin, strokes, kana, and the like.

In the embodiment of the present invention, the candidate may be used to represent one or more characters provided by the input method program to be selected by the user. The candidate may be characters in languages such as Chinese characters, English characters, and Japanese characters, and the candidate may also be a combination of symbols in the form of emoticons, pictures, and the like. The emoticons include but are not limited to pictures composed of lines, symbols, and words. For example, examples of the emoticons may include: “：P”, “:-o”, “:-)”, and the like.

Method Example 1

2, a flow chart of the steps of an input method embodiment 1 of the present invention is shown, which may specifically include the following steps:

Step 201, receiving a user input string;

Step 202: performing intent recognition on the input string to obtain input intent;

Step 203: According to the input intention, determine and output the first candidate corresponding to the input string.

In step 201, the types of input strings may include: pinyin string, glyph string (such as Wubi string, etc.), or voice feature string, etc., wherein the pinyin string corresponds to the pinyin input method, the glyph string corresponds to the glyph input method, and the voice feature string corresponds to the voice input method.

Alternatively, the type of input string may include: content that has been put on screen. Putting on screen may refer to the operation of outputting the content in the preview window to the application window. Specifically for the input method, putting on screen may refer to the operation of displaying the candidate output in the candidate window to the application window.

The on-screen content may represent a candidate for being on-screen. The on-screen content of the embodiment of the present invention may include: one or more on-screen contents. The on-screen content may correspond to language units such as words, phrases, and sentences.

In step 202, the embodiment of the present invention may perform intent recognition on the input string according to the rules of the target information to obtain the input intent.

The embodiment of the present invention can provide the following technical solution for performing intent recognition on the above input string:

Technical solution 1,

Technical solution 1 can be applied to the input of text components. In the embodiment of the present invention, the text components can represent the components of text. The text components can include: radicals, radicals or strokes. The text components can be applied to Chinese characters, Japanese characters, Mongolian and other languages.

The current input method utilizes the strong mapping relationship between radicals and the pronunciation of Chinese characters before the radicals are transformed. Referring to Table 1, a schematic diagram of the strong mapping between radicals and the pronunciation of Chinese characters before the radicals are transformed is shown.

Table 1

The current input method requires users to remember the pronunciation of radicals accurately, which increases the difficulty of memory for users; moreover, when the pronunciation is remembered incorrectly, the input of radicals will be impossible, which affects the input efficiency and accuracy of radicals.

In view of the difficulty in remembering the pronunciation of radicals in traditional technologies, as well as the low input efficiency and low input accuracy, an input scheme is proposed in an embodiment of the present invention. The input scheme may include: receiving an input string from a user; searching in a mapping relationship between text components and encoding strings corresponding to text component names according to the input string to obtain text component candidates corresponding to the input string; and outputting the text component candidates.

The inventors found in the process of implementing the embodiments of the present invention that the names of the text components are well known to most users. For example, users are familiar with the names of the text components such as the handle radical, the knife radical, the roof of a treasure, and the bald roof of a treasure. Therefore, the embodiments of the present invention input the text components according to the encoding string corresponding to the text component names. Since the text component names are well known to most users, the embodiments of the present invention can not only reduce the memory difficulty of users, but also improve the input efficiency and input accuracy of the text components.

The embodiments of the present invention can be applied to input scenarios of text components. For example, in a teaching scenario, a teacher can use the input text components for teaching; in a chat scenario, a user can use the input text components for chatting, etc. It can be understood that the embodiments of the present invention are not limited to specific input scenarios.

In Technical Solution 1, the above-mentioned intention recognition of the input string includes: matching the input string with the encoded character string corresponding to the text component name, if the match is successful, the input intention may include: text component input intention, and the first candidate corresponding to the input string may include: text component candidate.

When the input intention includes a text component input intention, the text component input intention and the text component candidates corresponding to the text component input intention may be determined based on a mapping relationship between text components and encoding character strings corresponding to text component names.

Taking the pinyin input method as an example, if the user wants to input the radical "扌", he can enter the encoded string corresponding to the name of the radical, such as "tishoupang".

According to an embodiment, a corresponding text component name may be determined for a text component. The text component name may be a specific noun used to identify the text component. The text component name may be a legal name, a standard name, an alias, or a nickname. The embodiment of the present invention does not limit the specific text component name.

The encoding string can represent the string corresponding to the encoding method of the input method. Taking the pinyin input method as an example, the encoding string corresponding to the name of the radical "扌" "提手旁" can include: "tishoupang", "tishoup", "tishp", "tshp", etc. It can be understood that the encoding string can be a full pinyin string or a simplified pinyin string.

The embodiment of the present invention can determine the corresponding encoding string for the text component name, and save the mapping relationship between the text component and the encoding string corresponding to the text component name.

The embodiment of the present invention can pre-establish and save the mapping relationship between the text component and the encoding string corresponding to the text component name. In this way, the text component candidate corresponding to the input string can be searched in the above mapping relationship according to the input string. Referring to Table 2, a schematic diagram of the text component name and encoding string corresponding to the text component is shown.

Table 2

Radical Chinese characters before radicals are transformed Encoding Strings 扌 Next to the handle tishoupan 刂 Next to the sharp knife lidaopang Roof Baogaitou baogaitou 冖 Bald Baogai tubaogai … … …

In one embodiment of the present invention, searching in the above mapping relationship may include: matching the above input string or corrected input string with the encoded string in the mapping relationship, and using the successfully matched text component as the text component candidate corresponding to the above input string. For example, if the input string is "tishoup", its corresponding text component candidate "扌" can be obtained based on the mapping relationship.

The corrected input string can be a string obtained after error correction of the input string. In actual applications, users are likely to enter an incorrect input string due to reasons such as pressing the wrong key (on a PC) or clicking the wrong screen position (on a mobile phone). Input error correction is an input method system solution for the above errors. It can actively identify user input errors and correct the incorrect input string into a correct input string, so that users can enter the correct text without modifying the input string.

The input error correction scheme of the embodiment of the present invention may specifically include: an error correction scheme based on edit distance and an error correction scheme based on statistics; wherein, the error correction scheme based on edit distance may perform the following correction attempts on each position of the input string: insert a character, delete a character, replace a character, etc., to generate an error correction candidate corresponding to the input string; the error correction scheme based on statistics may generate an error correction model through big data mining, and the error correction model may be used to learn the probability that the error correction candidate is mistakenly input as the input string.

For example, the input string is "tishoupeng", which can be corrected to obtain the corrected input string "tishoupang".

Technical Solution 2

Technical solution 2 can be applied to the input of pronunciation. The traditional input method can provide a tone soft keyboard with tones, and the tone soft keyboard can be provided with letter keys with tones for users to select and input. However, the triggering of the tone soft keyboard and the input with letter granularity usually consume more operating costs. For example, if the user wants to input the pronunciation "háo", he needs to trigger the tone soft keyboard after clicking "h" on the ordinary keyboard, and click "á" on the tone soft keyboard, and then return to the ordinary keyboard and input "o".

Technical Solution 2 is based on intention recognition and automatically identifies the voice input intention, which can save the switching cost between the ordinary keyboard and the tone soft keyboard and improve the input efficiency of pronunciation.

In Technical Solution 2, the above-mentioned intention recognition of the input string may specifically include: if the input string includes: a second character string representing the first tone information, and a first character string used to represent the first syllable, then the input intention is a pronunciation input intention, and the first candidate corresponding to the input string includes: the pronunciation candidate corresponding to the first character string, and the pronunciation candidate may include: the first syllable and the first tone information.

In the embodiment of the present invention, a syllable is a basic unit of speech that can be clearly distinguished. A syllable is usually a spelling syllable composed of an initial consonant and a final vowel, a spelling syllable composed of two final vowels, or a spelling syllable composed of one final vowel.

The embodiment of the present invention automatically identifies a first character string and a second character string from an input string, wherein the first character string may represent a syllable to which a tone is to be added, and the second character string may represent first tone information.

In an optional embodiment of the present invention, a second character string matching the preset tone content can be determined from the input string. The preset tone content may include: "first tone", "second tone", "third tone", "fourth tone", etc. The preset tone content may correspond to a pinyin form, such as "yisheng", "ersheng", "sansheng", "sisheng", etc. Of course, the preset tone content may correspond to a glyph form or a phonetic form.

For example, the second character string "ersheng" matching the preset tone content can be determined from the input string "haoersheng" or "ershenghao" or "haodeersheng". For another example, if the voice feature string corresponds to "好二声", the first character string corresponding to "好" and the second character string corresponding to "二声" can be determined from the voice feature string.

Optionally, the first string may be obtained based on a string adjacent to the second string in the input string. For example, the string "hao" adjacent to the second string "ersheng" in the input string "haoersheng" or "ershenghao" is used as the first string.

The embodiment of the present invention can add a tone to the first syllable corresponding to the first character string according to the first tone information corresponding to the second character string, so as to obtain a pronunciation candidate corresponding to the first character string. Specifically, a tone can be added to the first syllable corresponding to the first character string according to the correspondence between the syllable and the tone information. For example, the correspondence between the syllable "hao" and the tone information such as "first tone", "second tone", "third tone", and "fourth tone" can be saved, so that the tone can be added according to the search of the correspondence. For example, the tone corresponding to "ersheng" is added to the first syllable "hao" in the input string "haoersheng" or "ershenghao", and the pronunciation candidate "háo" is obtained.

Technical Solution 3

In technical solution 3, a pronunciation-based recommendation service can be provided for the user's on-screen content according to the second syllable and second tone information indicated in the on-screen content.

For example, an embodiment of the present invention can determine the second syllable "hao" and the second tone information "second tone" for the on-screen content A "What are the words with the second tone of 好", and provide a word recommendation service based on the pronunciation "háo"; specifically, words with "háo" can be recommended, such as "毫", "豪", "嗷", "号", etc.

In Technical Solution 3, the above-mentioned input string may include: the content that has been on the screen, and the above-mentioned intention recognition of the input string includes: if the content that has been on the screen indicates a second syllable and a second tone information, then the input intention is a voice recommendation intention, and the first candidate corresponding to the input string specifically includes: the recommendation candidate corresponding to the second syllable, the second tone information and the voice information of the content that has been on the screen.

The process of determining the second syllable and the second tone information specifically includes: determining the tone content that matches the preset tone content from the user's on-screen content; determining the syllable content corresponding to the tone content from the user's on-screen content; determining the second tone information corresponding to the tone content, and determining the second syllable corresponding to the syllable content. For example, the embodiment of the present invention can determine the tone content "second tone" and its corresponding second tone information from the on-screen content A "what are the words with the second tone of good"; further, it can determine the syllable content "good" and its corresponding second syllable "hao" adjacent to the tone content "second tone" from the user's on-screen content.

According to an embodiment, the determining and outputting the first candidate corresponding to the input string specifically includes: determining a target database corresponding to the semantic information, and querying the target database according to the second syllable and the second tone information to obtain a recommended candidate.

The type of the target database may be matched with the semantic information, and the type of the recommendation candidate may be matched with the type of the target database. For example, the types of the recommendation candidate include: characters, words, idioms, sentences, etc.

For example, for the content B on the screen, "How to form words with the second tone of the word hao", the embodiment of the present invention can recommend word formation results for "two-tone hao", such as "howling", "wailing", "crying", "mourning", etc. For another example, for the content C on the screen, "How to form sentences with the second tone of the word hao", the embodiment of the present invention can provide sentence formation services, etc. For another example, for the content D on the screen, "What are the idioms composed entirely of the second tone", the embodiment of the present invention can provide idiom services, etc.

The embodiment of the present invention can use a semantic analysis method to determine the semantic information corresponding to the on-screen content. The semantic analysis method can include: a sentence component analysis method, a machine learning method, etc. It can be understood that the embodiment of the present invention does not limit the specific semantic analysis method.

The above technical solutions 1 to 3 have introduced in detail the process of intent recognition of the input string. It can be understood that those skilled in the art can adopt any one or a combination of the above technical solutions 1 to 3 according to actual application requirements.

In step 203, a first candidate corresponding to the input string may be determined and output according to the input intention.

Specifically, when the input intention includes a text component input intention, the first candidate corresponding to the input string may include: a text component candidate. When the input intention is a pronunciation input intention, the first candidate corresponding to the input string includes: a pronunciation candidate corresponding to the first character string. When the input intention is a voice recommendation intention, the first candidate corresponding to the input string specifically includes: a recommendation candidate corresponding to the second syllable, the second tone information, and the voice information of the on-screen content.

In the embodiment of the present invention, optionally, the first candidate may be displayed at the first screen position of the input method.

The embodiment of the present invention can display the candidates corresponding to the input string in the candidate area. Due to the limitation of the display area, the number of candidates carried by the display area of one screen is usually limited. For example, the number of candidates is between 4 and 6. The user needs to switch the screen through the page turning operation. For example, the backward page turning operation is used to switch the candidates from the i-th (i can be a natural number greater than 0) screen to the (i+1)-th screen; the forward page turning operation is used to switch the candidates from the i-th screen to the (i-1)-th screen.

The embodiment of the present invention displays the first candidate at the first screen position, and can provide the first candidate when the user does not trigger a page turning operation, thereby improving the first input efficiency.

In an optional embodiment of the present invention, the method may further include: searching in a word library according to the input string to obtain a second candidate corresponding to the input string. The types of the second candidate specifically include: text candidates, image candidates, or expression candidates, etc. For example, according to the input string "tishoupeng", the corresponding text candidates "提手旁", "提手", etc. are searched in the word library.

In summary, the input method of the embodiment of the present invention performs intent recognition on the input string, and determines and outputs the first candidate corresponding to the input string according to the input intent obtained by recognition. The above-mentioned intent recognition does not require the user to remember the pronunciation of the target information. Therefore, the embodiment of the present invention can not only reduce the memory difficulty of the user, but also improve the input efficiency and input accuracy of the target information.

Method Example 2

3, a flow chart of the steps of Embodiment 2 of an input method of the present invention is shown, which may specifically include the following steps:

Step 301, receiving a user input string;

Step 302: Based on the input string, search in the mapping relationship between the text components and the encoding character strings corresponding to the text component names to obtain text component candidates corresponding to the input string;

Step 303: output the above text component candidates.

In step 302, it is possible to identify whether the input string corresponds to the text component input intention based on the mapping relationship between the text component and the encoding string corresponding to the text component name. If so, the text component candidate corresponding to the input string can be obtained.

In step 303, the server may output the above text component candidates to the client, or the client may display the above text component candidates for user selection.

In an optional embodiment of the present invention, the text component candidates can be displayed at the first screen position of the input method. The embodiment of the present invention displays the text component candidates at the first screen position, and can provide text component candidates without the user triggering a page turning operation, thereby improving the input efficiency of the text component candidates.

In summary, the input method of the embodiment of the present invention inputs the text components according to the mapping relationship between the text components and the encoding strings corresponding to the text component names. Since the text component names are well known to most users, the embodiment of the present invention can not only reduce the memory difficulty of the user, but also improve the input efficiency and input accuracy of the text components.

Method Example 3

4, a flowchart of a third embodiment of an input method of the present invention is shown, which is applied to a server and may specifically include the following steps:

Step 401: receiving a user input string;

Step 402: Determine a first character string and a second character string from the input string;

Step 403: adding a tone to the syllable corresponding to the first character string according to the first tone information corresponding to the second character string, so as to obtain a pronunciation candidate corresponding to the first character string;

Step 404: output the above-mentioned pronunciation candidates.

The embodiment of the present invention is used to automatically add indicated tones to syllables indicated by an input string, and output pronunciation candidates after the tones are added, thereby realizing convenient input of pronunciation.

The embodiment of the present invention can display the pronunciation candidates in the candidate area, that is, the pronunciation candidates can be displayed as candidates for the user to select. It can be understood that the pronunciation candidates can be put on the screen according to the user's selection operation on the pronunciation candidates, thereby realizing the convenient input of the pronunciation candidates.

In summary, the input method of the embodiment of the present invention automatically adds the indicated tone to the syllable indicated by the input string, and outputs the pronunciation candidates after the tone is added, thereby realizing convenient input of the pronunciation.

Method Example 4

5, a flowchart of a fourth embodiment of an input method of the present invention is shown, which may specifically include the following steps:

Step 501: receiving the user's on-screen content;

Step 502: Determine the second syllable and the second tone information according to the above-mentioned on-screen content;

Step 503: Determine and output a recommendation candidate based on the second syllable, the second tone information, and the semantic information corresponding to the on-screen content.

The embodiment of the present invention can provide a pronunciation-based recommendation service for the user's on-screen content according to the second syllable and second tone information indicated in the on-screen content.

For example, an embodiment of the present invention can determine the second syllable "hao" and the second tone information "second tone" for the on-screen content A "What are the words with the second tone of 好", and provide a word recommendation service based on the pronunciation "háo"; specifically, words with "háo" can be recommended, such as "毫", "豪", "嗷", "号", etc.

The embodiment of the present invention can display the recommended candidates in the candidate area, that is, the recommended candidates can be displayed as candidates for the user to select. It can be understood that the recommended candidates can be put on the screen according to the user's selection operation on the recommended candidates, thereby realizing the convenient input of the recommended candidates.

In summary, the embodiment of the present invention provides a pronunciation-based recommendation service for the user's on-screen content according to the second syllable and second tone information indicated in the on-screen content. The above recommendation service can be a recommendation service for words, idioms or sentences, which can improve the intelligence of the recommendation.

It should be noted that, for the method embodiments, for the sake of simplicity of description, they are all described as a series of motion combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the described sequence of actions, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the motions involved are not necessarily required by the embodiments of the present invention.

Device Embodiment

6, a structural block diagram of an input device embodiment of the present invention is shown, which may specifically include:

Receiving module 601, used to receive a user input string;

The intention recognition module 602 is used to perform intention recognition on the input string to obtain the input intention; and

The first candidate processing module 603 is used to determine and output the first candidate corresponding to the input string according to the input intention.

Optionally, the intention recognition module 602 may include:

The first intention recognition module is used to match the above input string with the encoded character string corresponding to the text component name. If the match is successful, the input intention may include: text component input intention, and the first candidate corresponding to the above input string may include: text component candidate.

Optionally, the input intention may include: text component input intention; determining the text component input intention and text component candidates corresponding to the text component input intention based on a mapping relationship between text components and encoding character strings corresponding to text component names.

Optionally, the intention recognition module 602 may include:

The second intention recognition module is used for if the above-mentioned input string can include: a second character string representing the first tone information, and a first character string used to represent the first syllable, then the above-mentioned input intention is a pronunciation input intention, and the first candidate corresponding to the above-mentioned input string may include: a pronunciation candidate corresponding to the above-mentioned first character string, and the above-mentioned pronunciation candidate may include: the above-mentioned first syllable and the above-mentioned first tone information.

Optionally, the input string may include: content that has been on the screen, and the intention recognition module 602 may include:

The third intention recognition module is used for if the above-mentioned on-screen content indicates the second syllable and the second tone information, then the above-mentioned input intention is a voice recommendation intention, and the first candidate corresponding to the above-mentioned input string may include: the recommendation candidates corresponding to the above-mentioned second syllable, the above-mentioned second tone information and the voice information of the above-mentioned on-screen content.

Optionally, the above device may further include:

A first determining module, used to determine the tone content matching the preset tone content from the above-mentioned on-screen content;

A second determination module is used to determine the syllable content corresponding to the tone content from the content on the screen;

The third determining module is used to determine the second tone information corresponding to the tone content and determine the second syllable corresponding to the syllable content.

Optionally, the first candidate processing module 603 may include:

A database determination module, used to determine the target database corresponding to the above semantic information;

The database query module is used to query the target database according to the second syllable and the second tone information to obtain the recommendation candidates.

Optionally, the first candidate processing module 603 may include:

The display module is used to display the first candidate at the first screen position of the input method.

Optionally, the above device may further include:

The second candidate determination module is used to search in the word library according to the input string to obtain the second candidate corresponding to the input string.

As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

An embodiment of the present invention provides a device for input, including a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: receiving an input string from a user; performing intent recognition on the input string to obtain an input intent; and determining and outputting a first candidate corresponding to the input string based on the input intent.

Fig. 7 is a block diagram of a device 1100 for input according to an exemplary embodiment. For example, the device 1100 may 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.

7 , device 1100 may include one or more of the following components: a processing component 1102 , a memory 1104 , a power component 1106 , a multimedia component 1108 , an audio component 1110 , an input/output (I/O) interface 1112 , a sensor component 1114 , and a communication component 1116 .

The processing component 1102 generally controls the overall operation of the device 1100, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1102 may include one or more processors 1120 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 1102 may include one or more modules to facilitate interaction between the processing component 1102 and other components. For example, the processing component 1102 may include a multimedia module to facilitate interaction between the multimedia component 1108 and the processing component 1102.

The memory 1104 is configured to store various types of data to support operations on the device 1100. Examples of such data include instructions for any application or method operating on the device 1100, contact data, phone book data, messages, pictures, videos, etc. The memory 1104 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 disk or optical disk.

The power supply component 1106 provides power to the various components of the device 1100. The power supply component 1106 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 1100.

The multimedia component 1108 includes a screen that provides an output interface between the device 1100 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 may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1108 includes a front camera and/or a rear camera. When the device 1100 is in an operating mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 1110 is configured to output and/or input audio signals. For example, the audio component 1110 includes a microphone (MIC), and when the device 1100 is in an operation mode, such as a call mode, a recording mode, and a voice input mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1104 or sent via the communication component 1116. In some embodiments, the audio component 1110 also includes a speaker for outputting audio signals.

I/O interface 1112 provides an interface between processing component 1102 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 1114 includes one or more sensors for providing various aspects of the status assessment of the device 1100. For example, the sensor assembly 1114 can detect the open/closed state of the device 1100, the relative positioning of components, such as the display and keypad of the device 1100, the sensor assembly 1114 can also detect the position change of the device 1100 or a component of the device 1100, the presence or absence of user contact with the device 1100, the orientation or acceleration/deceleration of the device 1100, and the temperature change of the device 1100. The sensor assembly 1114 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1114 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1114 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 1116 is configured to facilitate wired or wireless communication between the device 1100 and other devices. The device 1100 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1116 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 1116 also 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, Radio Frequency Identification) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, the device 1100 can 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 to perform the above methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1104 including instructions, and the instructions can be executed by the processor 1120 of the device 1100 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

FIG8 is a schematic diagram of the structure of a server in some embodiments of the present invention. The server 1900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1922 (for example, one or more processors) and memory 1932, and one or more storage media 1930 (for example, one or more mass storage devices) storing application programs 1942 or data 1944. Among them, the memory 1932 and the storage medium 1930 may be short-term storage or permanent storage. The program stored in the storage medium 1930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the server. Furthermore, the central processing unit 1922 may be configured to communicate with the storage medium 1930 and execute a series of instruction operations in the storage medium 1930 on the server 1900.

The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input and output interfaces 1958, one or more keyboards 1956, and/or, one or more operating systems 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to execute the input method shown in Figure 2 or Figure 3 or Figure 4 or Figure 5.

A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to execute an input method, the method comprising: receiving a user's input string; performing intent recognition on the input string to obtain an input intent; and determining and outputting a first candidate corresponding to the input string based on the input intent.

The embodiment of the present invention discloses A1, an input method, the method comprising:

Receive the user's input string;

Performing intent recognition on the input string to obtain input intent;

According to the input intention, a first candidate corresponding to the input string is determined and output.

A2. The method according to A1, characterized in that the performing intent recognition on the input string comprises:

The input string is matched with the encoded character string corresponding to the text component name. If the match is successful, the input intention includes: text component input intention, and the first candidate corresponding to the input string includes: text component candidate.

A3. The method according to A1 is characterized in that the input intention includes: text component input intention; determining the text component input intention and the text component candidates corresponding to the text component input intention based on the mapping relationship between the text component and the encoding string corresponding to the text component name.

A4. The method according to A1, characterized in that the performing intent recognition on the input string comprises:

If the input string includes: a second character string representing a first tone information, and a first character string used to represent a first syllable, then the input intention is a pronunciation input intention, and the first candidate corresponding to the input string includes: a pronunciation candidate corresponding to the first character string, and the pronunciation candidate includes: the first syllable and the first tone information.

A5. The method according to A1, characterized in that the input string includes: content that has been on the screen, and the performing intent recognition on the input string includes:

If the on-screen content indicates a second syllable and second tone information, the input intention is a voice recommendation intention, and the first candidate corresponding to the input string includes: the second syllable, the second tone information and the recommendation candidate corresponding to the voice information of the on-screen content.

A6. The method according to A5, characterized in that the method further comprises:

Determining tone content that matches preset tone content from the on-screen content;

Determining the syllable content corresponding to the tone content from the content already on the screen;

The second tone information corresponding to the tone content is determined, and the second syllable corresponding to the syllable content is determined.

A7. The method according to A5, characterized in that the determining and outputting the first candidate corresponding to the input string comprises:

Determining a target database corresponding to the semantic information;

The target database is queried according to the second syllable and the second tone information to obtain recommendation candidates.

A8. The method according to any one of A1 to A7, characterized in that the determining and outputting the first candidate corresponding to the input string comprises:

The first candidate is displayed on the first screen of the input method.

A9. The method according to any one of A1 to A7, characterized in that the method further comprises:

According to the input string, a search is performed in the word library to obtain a second candidate corresponding to the input string.

The embodiment of the present invention discloses B10, an input device, characterized in that it includes:

A receiving module, used for receiving an input string from a user;

an intention recognition module, used to perform intention recognition on the input string to obtain input intention; and

The first candidate processing module is used to determine and output a first candidate corresponding to the input string according to the input intention.

B11. The device according to B10, wherein the intention recognition module comprises:

The first intention recognition module is used to match the input string with the encoded character string corresponding to the text component name. If the match is successful, the input intention includes: text component input intention, and the first candidate corresponding to the input string includes: text component candidate.

B12. The device according to B10 is characterized in that the input intention includes: text component input intention; determining the text component input intention and the text component candidates corresponding to the text component input intention based on the mapping relationship between the text component and the encoding string corresponding to the text component name.

B13. The device according to B10, wherein the intention recognition module comprises:

A second intention recognition module is used for if the input string includes: a second character string representing the first tone information, and a first character string used to represent the first syllable, then the input intention is a pronunciation input intention, and the first candidate corresponding to the input string includes: the pronunciation candidate corresponding to the first character string, and the pronunciation candidate includes: the first syllable and the first tone information.

B14. The device according to B10, characterized in that the input string includes: content that has been on the screen, and the intention recognition module includes:

The third intention recognition module is used to: if the on-screen content indicates a second syllable and a second tone information, the input intention is a voice recommendation intention, and the first candidate corresponding to the input string includes: the second syllable, the second tone information and the recommendation candidate corresponding to the voice information of the on-screen content.

B15. The device according to B14, characterized in that the device further comprises:

A first determining module, configured to determine, from the on-screen content, a tone content that matches a preset tone content;

A second determination module is used to determine the syllable content corresponding to the tone content from the content that has been displayed on the screen;

The third determining module is used to determine the second tone information corresponding to the tone content and determine the second syllable corresponding to the syllable content.

B16. The device according to B14, wherein the first candidate processing module comprises:

A database determination module, used to determine a target database corresponding to the semantic information;

The database query module is used to query the target database according to the second syllable and the second tone information to obtain recommendation candidates.

B17. The device according to any one of B10 to B16, wherein the first candidate processing module comprises:

The display module is used to display the first candidate at the first screen position of the input method.

B18. The device according to any one of B10 to B16, characterized in that the device further comprises:

The second candidate determination module is used to search in a word library according to the input string to obtain a second candidate corresponding to the input string.

The embodiment of the present invention discloses C19, a device for input, characterized in that it includes a memory and one or more programs, wherein the 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 instructions for performing the following operations:

Receive the user's input string;

Performing intent recognition on the input string to obtain input intent;

According to the input intention, a first candidate corresponding to the input string is determined and output.

C20. The device according to C19, wherein the performing intent recognition on the input string comprises:

The input string is matched with the encoded character string corresponding to the text component name. If the match is successful, the input intention includes: text component input intention, and the first candidate corresponding to the input string includes: text component candidate.

C21. The device according to C19 is characterized in that the input intention includes: text component input intention; determining the text component input intention and the text component candidates corresponding to the text component input intention based on the mapping relationship between the text component and the encoding string corresponding to the text component name.

C22. The device according to C19, wherein the performing intent recognition on the input string comprises:

If the input string includes: a second character string representing a first tone information, and a first character string used to represent a first syllable, then the input intention is a pronunciation input intention, and the first candidate corresponding to the input string includes: a pronunciation candidate corresponding to the first character string, and the pronunciation candidate includes: the first syllable and the first tone information.

C23. The device according to C19, wherein the input string includes: content that has been on the screen, and the performing intent recognition on the input string includes:

If the on-screen content indicates a second syllable and second tone information, the input intention is a voice recommendation intention, and the first candidate corresponding to the input string includes: the second syllable, the second tone information and the recommendation candidate corresponding to the voice information of the on-screen content.

C24. The device according to C23, characterized in that the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

Determining tone content that matches preset tone content from the on-screen content;

Determining the syllable content corresponding to the tone content from the content already on the screen;

The second tone information corresponding to the tone content is determined, and the second syllable corresponding to the syllable content is determined.

C25. The device according to C23, characterized in that the determining and outputting the first candidate corresponding to the input string comprises:

Determining a target database corresponding to the semantic information;

The target database is queried according to the second syllable and the second tone information to obtain recommendation candidates.

C26. The device according to any one of C19 to C25, wherein determining and outputting the first candidate corresponding to the input string comprises:

The first candidate is displayed on the first screen of the input method.

C27. The device according to any one of C19 to C25, characterized in that the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

According to the input string, a search is performed in the word library to obtain a second candidate corresponding to the input string.

An embodiment of the present invention discloses D28, a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, enables a device to execute an input method as described in one or more of A1 to A9.

Those skilled in the art will readily appreciate other embodiments of the invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

The above is a detailed introduction to an input method, an input device, a device for input, and a machine-readable medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for a person skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims (8)

1. An input method, the method comprising:

receiving an input string of a user, the input string comprising: on-screen content;

performing intention recognition on the input string to obtain an input intention;

determining and outputting a first candidate corresponding to the input string according to the input intention;

The intent recognition of the input string includes:

If the on-screen content indicates second syllable and second voice information, the input intention is voice recommendation intention, and the first candidate corresponding to the input string comprises: recommendation candidates corresponding to the second syllable, the second tone information and the voice information of the on-screen content;

Determining tone content matched with preset tone content from the on-screen content;

Determining syllable content corresponding to the tone content from the on-screen content;

Determining second tone information corresponding to the tone content and determining a second syllable corresponding to the syllable content;

The determining and outputting the first candidate corresponding to the input string includes:

determining semantic information corresponding to the on-screen content, and determining a target database corresponding to the semantic information;

Inquiring the target database according to the second syllable and the second tone information to obtain recommendation candidates; the type of the recommendation candidate is matched with the type of the target database; the types of the recommendation candidates include: words, phrases, sentences.

2. The method of claim 1, wherein the determining and outputting the first candidate corresponding to the input string comprises:

and displaying the first candidate at the first screen position of the input method.

3. The method according to claim 1, wherein the method further comprises:

And searching in a word stock according to the input string to obtain a second candidate corresponding to the input string.

4. An input device, comprising:

A receiving module, configured to receive an input string of a user, where the input string includes: on-screen content;

The intention recognition module is used for carrying out intention recognition on the input string so as to obtain an input intention; and

The first candidate processing module is used for determining and outputting a first candidate corresponding to the input string according to the input intention;

The intention recognition module includes:

a third intention recognition module, configured to, if the on-screen content indicates second syllable and second voice information, determine that the input intention is a voice recommendation intention, where the first candidate corresponding to the input string includes: recommendation candidates corresponding to the second syllable, the second tone information and the voice information of the on-screen content;

The apparatus further comprises:

the first determining module is used for determining tone content matched with preset tone content from the on-screen content;

The second determining module is used for determining syllable content corresponding to the tone content from the on-screen content;

a third determining module, configured to determine second tone information corresponding to the tone content, and determine a second syllable corresponding to the syllable content;

The first candidate processing module includes:

The database determining module is used for determining semantic information corresponding to the on-screen content and determining a target database corresponding to the semantic information;

The database query module is used for querying the target database according to the second syllable and the second tone information to obtain recommendation candidates; the type of the recommendation candidate is matched with the type of the target database; the types of the recommendation candidates include: words, phrases, sentences.

5. The apparatus of claim 4, wherein the first candidate processing module comprises:

and the display module is used for displaying the first candidate at the first screen position of the input method.

6. The apparatus of claim 4, wherein the apparatus further comprises:

and the second candidate determining module is used for searching in a word stock according to the input string so as to obtain a second candidate corresponding to the input string.

7. An apparatus for inputting comprising a memory and one or more programs, wherein one or more programs are stored in the memory and when executed by one or more processors, implement the steps of the method of any of claims 1 to 3.

8. A machine readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the input method of one or more of claims 1 to 3.