Input method and device

Abstract

The application discloses an input method and device, the method comprises the following steps: obtaining the current input of a user; extracting an entity object and action information in the input; obtaining a word set related to the entity object; selecting a word matching the action information from the word set as a candidate word; and recommending the candidate word to the user. The application can intelligently provide more vivid and rich word expression for the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the input method field, and in particular to an input method and device. BACKGROUND

[0002] Input method is a kind of coding method for inputting various symbols into computer or other devices, and is an indispensable tool for human and computer interaction. At present, in order to better meet the needs of users and improve the input experience of users, special edition input method appears. The special edition input method is specially customized for the characteristics of a certain industry, and the basic principle is to extract as many words as possible related to the industry, and try to be longer words. In this way, long words can be predicted under the condition of inputting less string by the user, thereby greatly improving the input efficiency of the user. For example, the input method designed for users engaged in live broadcast of sports competition text, after the user inputs "James", the input method can give the corresponding candidate words "dribble to the basket" and the like.

[0003] Using special edition input method can greatly improve input efficiency. However, the existing special edition input method recommends the same text content to the user as the candidate words for different entity objects in the industry, and the content of such candidate words is single and the language is not rich enough. SUMMARY

[0004] The embodiments of the present application provide an input method and device to solve the problem of single content and insufficient language of candidate words recommended by the existing special edition input method to the user.

[0005] Therefore, the present application provides the following technical solutions:

[0006] An input method, the method comprising:

[0007] obtaining the previous text input by the user;

[0008] extracting the entity object and action information in the previous text;

[0009] obtaining a word set related to the entity object;

[0010] selecting a word matching the action information from the word set as a candidate word;

[0011] recommending the candidate word to the user.

[0012] Optionally, the obtaining of the word set related to the entity object comprises:

[0013] obtaining the feature type of the entity object;

[0014] obtaining a word set describing the entity object of the feature type.

[0015] Optionally, the method further comprises:

[0016] characteristic information of a plurality of different entity objects is collected in advance, and a characteristic type of each entity object is determined according to the characteristic information.

[0017] Optionally, the method further comprises:

[0018] a corpus describing a specific scenario is collected in advance, and a word describing an entity object is extracted from the corpus;

[0019] a characteristic label is added to the word to obtain a word set with different characteristic labels, the characteristic label being used to represent a characteristic type of the entity object described by the word;

[0020] the obtaining of the word set describing the entity object of the characteristic type comprises:

[0021] determining a characteristic label corresponding to the characteristic type;

[0022] obtaining a word set with the characteristic label corresponding to the characteristic type.

[0023] Optionally, the foregoing is a word that has been on-screen and / or a word that has entered an editing box, or a word that has been selected by a user to be on-screen.

[0024] Optionally, the recommending of the candidate word to the user comprises:

[0025] displaying the candidate word; or

[0026] replacing text corresponding to the action information in the foregoing with the candidate word.

[0027] An input device, the device comprising:

[0028] a foregoing obtaining module, configured to obtain a foregoing input by a user;

[0029] an information extracting module, configured to extract an entity object and action information in the foregoing;

[0030] a word set obtaining module, configured to obtain a word set related to the entity object;

[0031] a screening module, configured to select a word matching the action information from the word set as a candidate word;

[0032] a recommending module, configured to recommend the candidate word to the user.

[0033] Optionally, the word set obtaining module comprises:

[0034] The feature information acquisition unit is configured to acquire a feature type of the entity object.

[0035] The word acquisition unit is configured to acquire a word set describing the entity object of the feature type.

[0036] Optionally, the apparatus further comprises:

[0037] The feature type determination module is configured to pre-collect feature information of a plurality of different entity objects, and determine a feature type of each entity object according to the feature information.

[0038] Optionally, the apparatus further comprises:

[0039] The word set generation module is configured to pre-generate a word set describing entity objects of different feature types.

[0040] The word set generation module comprises:

[0041] The corpus collection unit is configured to pre-collect a corpus describing a specific scenario.

[0042] The word extraction unit is configured to extract words describing entity objects from the corpus.

[0043] The label adding unit is configured to add a feature label to the words to obtain a word set with different feature labels, the feature label being used to represent a feature type of the entity object described by the word.

[0044] The word acquisition unit is specifically configured to determine a feature label corresponding to the feature type, and acquire a word set with the feature label corresponding to the feature type.

[0045] Optionally, the foregoing is a word that has been on-screen and / or a word that has entered an editing box, or a word that has been selected by a user to be on-screen.

[0046] Optionally, the recommendation module is specifically configured to display the candidate word; or replace text corresponding to the action information in the foregoing with the candidate word.

[0047] An electronic device, comprising: one or more processors, a memory;

[0048] The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the method described above.

[0049] A readable storage medium having instructions stored thereon, the instructions being executed to implement the method described above.

[0050] The input method and device provided by the embodiment of the present application extracts an entity object and action information from the user input, obtains a word set related to the entity object, selects a word matching the action information from the word set as a candidate word, and recommends the candidate word to the user, which not only facilitates the input of the user, but also makes the input content more vivid and rich.

[0051] The input method and device provided by the embodiment of the present application can be applied to user input in specific scenarios, such as live text broadcast of sports matches, live text broadcast of competitive game matches, and the like, different expressions can be recommended according to the characteristics of different athletes or competitive personnel, so that the live broadcast content is more vivid and rich, and the input method is more intelligent. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art according to these drawings.

[0053] Figure 1 is a flow chart of the input method of the embodiment of the present application;

[0054] Figure 2 is a structural block diagram of the input device of the embodiment of the present application;

[0055] Figure 3 is a structural block diagram of the word set generation module in the embodiment of the present application;

[0056] Figure 4 is a block diagram of a device for an input method according to an exemplary embodiment;

[0057] Figure 5 is a structural schematic diagram of the server in the embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the person skilled in the art better understand the scheme of the embodiment of the present application, the embodiment of the present application will be further described in detail below in combination with the drawings and embodiments.

[0059] In order to address the problem that the long words recommended to users in existing special-edition input methods have single content and insufficient expression, the embodiments of the present invention provide an input method and device that can provide users with more vivid and rich expressions based on user input in specific scenarios. For example, in various sports competition scenarios, athletes' movements have their own characteristics; for another example, in e-sports competition scenarios, players' operations usually also have their own characteristics; for another example, some singers have some specific singing techniques. In these scenarios, text broadcasters are required to input live commentary text efficiently and quickly, and vivid and rich language will also enhance the viewer experience.

[0060] Different sports have their own unique characteristics. For example, dribbling and dunking are highlights of basketball games, while passing and shooting are highlights of soccer games. Furthermore, different athletes in each sport also have their own unique characteristics. Therefore, in an embodiment of the present invention, relevant corpus can be pre-collected and words describing different entity objects can be extracted from them. This allows for the generation of word sets describing entity objects with different feature types. These word sets can be used to intelligently provide candidate words to the user during input, facilitating user input while also enriching the input content.

[0061] like Figure 1 FIG. 1 is a flow chart of an input method according to an embodiment of the present invention, comprising the following steps:

[0062] Step 101: Get the context currently input by the user.

[0063] The above context may be a word that has been selected by the user to be displayed on the screen. For example, an input method may provide a candidate long word to the user, and the user has clicked on the candidate long word, but the candidate long word has not yet been displayed on the screen. The candidate long word may be a candidate word generated by an existing input method. Different input methods may have different methods and rules for generating candidate words, and this is not limited in this embodiment of the present invention.

[0064] Of course, when the user inputs on a computer or laptop, the above context may also be all or part of the words that have been displayed on the screen; when the user inputs on a mobile phone, the above context may also include all or part of the words that have been displayed on the screen and / or entered into the edit box.

[0065] Step 102: extract the entity object and action information mentioned above.

[0066] The entity object mainly refers to a specific person, such as football players "Neymar" and "Messi", etc. The action information mainly refers to words that describe actions, such as shooting, dribbling, etc.

[0067] Specifically, for the obtained above text, the above text can be segmented first, and then a pre-established person name library and an action library are searched to determine whether there is entity object and action information. Of course, if there is no entity object and action information in the above text, that is, for the above text which is not of the structure of "entity object + action", subsequent processing is also not required.

[0068] In step 103, a set of words related to the entity object is obtained.

[0069] Specifically, the feature type of the entity object can be determined first, and then a set of words describing the entity object of the feature type is obtained.

[0070] The feature type of the entity object can be determined by searching a pre-established feature type library. The feature type library records the correspondence between each entity object and its feature type.

[0071] The establishment of the feature type library can be completed by manual calibration or automatically completed by clustering a large amount of feature information of different entity objects. For example, the relevant information of each athlete can be grabbed from a sports website, and for athletes of different projects, the feature type of the entity object in the project is obtained through clustering.

[0072] The feature information is used to represent some characteristics of the entity object, such as physique, technology, etc. These characteristics are classified, and different types are assigned different type labels. For example, small and flexible physique, strong and powerful physique, etc. It should be noted that different types of division can be used for different sports projects, and the embodiments of the present application are not limited thereto.

[0073] In addition, a corpus describing a specific scenario (such as a sports competition scenario, a game competition scenario, etc.) needs to be collected in advance, and words describing the entity object are extracted from the corpus. Since the entity objects described by these words are different, when using these words, it is also necessary to consider whether the entity object is suitable for using such words, otherwise not only it will not have a vivid effect, but also it will make the description inconsistent with the image and action of the entity object, which is counterproductive.

[0074] In order to facilitate the calling of different extracted words describing the entity object, a feature label can be added to the words to obtain a set of words with different feature labels, and the feature label is used to represent the feature type of the entity object described by the words. In this way, each set of words can be for a feature type, so that the entity object with the corresponding feature type can use the words in the set of words to describe its action, so that the language expression is more vivid and rich.

[0075] The word set can include one or more words, for example, the words in the word set with the characteristic label of "strong and powerful physique" are: bulldozing hard to the basket; one tiger jump, turn around and shoot. For another example, the words in the word set with the characteristic label of "short and flexible physique" are: sliding into the basket like a water snake; one big turn, left and right thrust.

[0076] Accordingly, after determining the characteristic type of the entity object in the foregoing, a characteristic label corresponding to the characteristic type can be determined, and then a word set with the characteristic label can be obtained according to the characteristic label, and the words in the word set are words describing the entity object with the characteristic type.

[0077] Step 104: selecting a word matching the action information from the word set as a candidate word.

[0078] Specifically, the action information in the foregoing can be matched with each word in the word set, and the matched word can be selected as a candidate word.

[0079] The method of matching the action information with the word can adopt prior art, for example, the matching degree of the word corresponding to the action information in the foregoing with each word in the word set can be calculated, and the word with a matching degree greater than a set value can be selected as a candidate word.

[0080] Of course, in actual application, each word in the word set can be added with a corresponding action label in advance, so that the action information in the foregoing can be matched with the action label when matching.

[0081] Step 105: recommending the candidate word to the user.

[0082] Specifically, the candidate word can be displayed, and specifically, the candidate word can be displayed in a candidate column or directly on the screen.

[0083] If the foregoing is a word on the screen or a word entering an editing box, the candidate word can also be used to replace the text corresponding to the action information in the foregoing, that is, the text corresponding to the action information in the foregoing is replaced with the candidate word.

[0084] For example, when a text commentator inputs "James dribbles to the basket", the method provided by the embodiment of the application can obtain all word sets related to the player "James", and then select a word similar to "dribbles to the basket" from the word set as a candidate word and recommend it to the user, such as selecting "bulldozing hard to the basket" and recommending it to the user, and the user selects the candidate word, and the input is displayed as "James bulldozes hard to the basket", so that the expression is more vivid and lifelike.

[0085] For example, when the live commentator inputs "Barry dribbles to the basket", the method provided by the embodiment of the application finds all the word sets related to the player "Barry" according to the player "Barry", and then selects a word similar to "dribbles to the basket" from the word sets as a candidate word to recommend to the user, such as "slips into the basket like a water snake", and the user selects the candidate word, and then the input is displayed as "Barry slips into the basket like a water snake", so that the expression is more vivid and lifelike.

[0086] The input method provided by the embodiment of the application extracts the entity object and the action information from the preceding text input by the user, acquires the word set related to the entity object, selects a word matching the action information from the word set as a candidate word, and recommends the candidate word to the user, so that the input of the user is facilitated, and the input content is more vivid and rich.

[0087] The input method provided by the embodiment of the application can be applied to the user input in a specific scenario, such as live commentary of a sports match, live commentary of a competitive game match, live commentary of a singer or dancer performance, and the like, different expressions can be recommended according to the characteristics of different players or competitive personnel or performers, so that the live commentary content is more vivid and rich, and the input method is more intelligent.

[0088] Since different scenarios have different characteristics, in actual application, a feature type library and a word set corresponding to different application categories can be further set, and when the input method is used, the current application category is selected by the user, so that when the user inputs subsequently, only the feature type library and the word set corresponding to the application category are called, and the words in the word set are used to provide vivid and rich expression words to the user, so that the accuracy of the candidate words recommended to the user can be better ensured.

[0089] Correspondingly, the embodiment of the application further provides an input device, as shown in Figure 2 is a structural schematic diagram of the device.

[0090] In the embodiment, the device comprises:

[0091] The preceding text acquisition module 201 is configured to acquire the preceding text input by the user currently;

[0092] The information extraction module 202 is configured to extract the entity object and the action information in the preceding text;

[0093] The word set acquisition module 203 is configured to acquire the word set related to the entity object;

[0094] A screening module 204 is configured to select a word matching the action information from the word set as a candidate word;

[0095] The recommendation module 105 is used to recommend the candidate words to the user, for example, the candidate words can be displayed, specifically the candidate words can be displayed in the candidate column or directly on the screen; or the text corresponding to the action information in the above text can be replaced with the candidate words.

[0096] The above context may be a word that has been selected by the user to be displayed on the screen, for example, a candidate long word provided to the user by an input method, and the user has clicked on the candidate long word, but the candidate long word has not yet been displayed on the screen. The candidate long word may be a candidate word generated by an existing input method. Different input methods may have different methods and rules for generating candidate words, which are not limited in this embodiment of the present invention. In addition, the above context may also be all or part of a word that has been displayed on the screen and / or all or part of a word that has been entered into an edit box.

[0097] Specifically, the information extraction module 202 may first segment the above text, and then search a pre-established person noun database and action vocabulary database to determine whether there are entity objects and action information therein.

[0098] The word set acquisition module 203 may specifically include:

[0099] A feature information acquisition unit, configured to acquire a feature type of the entity object, for example, by searching a pre-established feature type library to obtain the feature type of the entity object;

[0100] The word acquisition unit is used to acquire a word set that describes the entity object of the feature type.

[0101] The feature type library can be established manually or by a corresponding feature type determination module (not shown). For example, the feature type determination module collects feature information of multiple different entity objects in advance and determines the feature type of each entity object based on the feature information.

[0102] It should be noted that the feature type determination module may be a part of the device of the present invention or may be independent of the device, which is not limited in this embodiment of the present invention.

[0103] Likewise, a word set for describing entity objects of different feature types may be pre-established, and the word set may be established manually or by a corresponding word set generation module.

[0104] like Figure 3 FIG. 1 is a structural block diagram of a word set generation module in an embodiment of the present invention.

[0105] The word set generating module comprises the following units:

[0106] A corpus collecting unit 311 is configured to collect, in advance, a corpus describing a specific scenario, such as a sports match, a game match, or the like;

[0107] A word extracting unit 312 is configured to extract, from the corpus, words describing an entity object;

[0108] A label adding unit 313 is configured to add a feature label to the words, to obtain a word set with different feature labels, the feature label being used to represent a feature type of the entity object described by the words. That is, each word in the word set corresponding to a feature label can be used to describe an entity object with the feature type represented by the feature label, such as a shooting action, a dribbling action, or the like of such an entity object.

[0109] By using the pre-established word set with different feature labels, Figure 2 The word obtaining unit in the word set obtaining module 203 can first determine a feature label corresponding to the feature type of the entity object, and can obtain the corresponding word set according to the feature label, that is, obtain a word set with a feature label corresponding to the feature type.

[0110] The input device provided by the embodiment of the present application extracts the entity object and the action information from the foregoing user input, obtains a word set related to the entity object, selects a word matching the action information from the word set as a candidate word, and recommends the candidate word to the user, which not only facilitates the input of the user, but also makes the input content more vivid and rich.

[0111] The input device provided by the embodiment of the present application can be applied to user input in a specific scenario, such as live text broadcasting of a sports match, live text broadcasting of a competitive game match, live text broadcasting of a performance of a singer or dancer, or the like, and different expressions can be recommended according to different characteristics of athletes or competitive personnel or performers, so that the live broadcasting content is more vivid and rich, and the input method is more intelligent.

[0112] Figure 4 is a block diagram of an apparatus 800 for an input method according to an example embodiment. The apparatus 800 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, or the like, for example.

[0113] Referring to Figure 4The device 800 can include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0114] The processing component 802 generally controls the overall operation of the device 800 such as the operation of the display, the telephone call, the data communication, the camera operation and the recording operation. The processing component 802 can include one or more processors 820 to execute instructions to complete all or a part of steps of the methods described above. Furthermore, the processing component 802 can include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0115] The memory 804 is configured to store various categories of data to support the operation of the device 800. Examples of these data include instructions for any application or methods operating on the device 800, contact data, phonebook data, messages, pictures, videos, and so on. The memory 804 can be implemented by any class of volatile or nonvolatile storage devices 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 storage, flash memory, magnetic or optical disk.

[0116] The power supply component 806 supplies the various components of the device 800 with power. The power supply component 806 can include a power management system, one or more power supplies, and other components associated with generating, managing and distributing power for the device 800.

[0117] The multimedia component 808 includes a screen providing an output interface between the device 800 and a user. In some embodiments, the screen can 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 an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide and a gesture on the touch panel. The touch sensors can not only sense a boundary of a touching or a sliding action, but also detect duration and pressure related to the touching or sliding action. In some embodiments, the multimedia component 808 includes a front camera and / or a back camera. The front camera and / or the back camera can receive external multimedia data when the device 800 is in an operation mode, such as a shooting mode or a video mode. Each of the front and back cameras can be a fixed optical lens system or have a focal length and optical zoom capability.

[0118] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC) that is configured to receive an external audio signal when the device 800 is in an operation 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 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0119] The I / O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which can be a keypad, a click wheel, buttons, and the like. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0120] The sensor component 814 includes one or more sensors for providing status assessments of various aspects of the device 800. For example, the sensor component 814 can detect an open / closed position of the device 800, relative positioning of components, such as a display and a keypad of the device 800, a change of position of the device 800 or a component of the device 800, presence or absence of user contact with the device 800, changes in orientation or acceleration / deceleration

[0121] The communication component 816 is configured to facilitate wired or wireless communication between the device 800 and other devices. The device 800 can access a wireless network based on a corresponding communication standard, such as WiFi, 2G, or 3G, or a combination thereof. In an example embodiment, the communication component 816 receives broadcast signals or broadcast-related information from external broadcast management systems via a broadcast channel. In an example embodiment, the communication component 816 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) techniques, infrared data association (IrDA) techniques, ultra-wideband (UWB) techniques, Bluetooth (BT) techniques, and other techniques.

[0122] In exemplary embodiments, the apparatus 800 can be implemented using 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, micro-controllers, microprocessors or other electronic devices, to perform the above method.

[0123] In exemplary embodiments, a non-transitory computer readable storage medium including instructions, such as the memory 804 including instructions, is also provided, which can be executed by the processor 820 of the apparatus 800 to complete the above key error correction 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, and an optical data storage device, etc.

[0124] The present application also provides a non-transitory computer readable storage medium, when the instructions in the storage medium are executed by a processor of a mobile terminal, the mobile terminal is enabled to perform all or part of the steps in the above method embodiments of the present application.

[0125] Figure 5 is a structural schematic diagram of a server in embodiments of the present application. The server 1900 can have great differences due to different configurations or performances, and can include one or more central processing units (CPUs) 1922 (for example, one or more processors) and a memory 1932, 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 media 1930 can be temporary storage or persistent storage. The programs stored in the storage medium 1930 can include one or more modules (not shown in the figure), each of which can include a series of instruction operations in the server. Further, the central processing unit 1922 can 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.

[0126] The server 1900 can also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input / 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.

[0127] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

[0128] It is to be understood that the application is not limited to the precise construction herein described and as shown in the attached drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application is indicated only by the subjoined claims.

[0129] The above description is intended to be illustrative and not restrictive. Many other modifications within the scope of the application will be apparent to those of skill in the art upon reviewing the above description. The scope of the application should, therefore, be determined not with reference to the above description, but instead with reference to the appended claims.

Claims

1. An input method, characterized in that: Applied to the special edition input method, the method includes: Get the context currently entered by the user; Extracting the entity object and action information mentioned above, where the entity object refers to a specific person, and the action information refers to words describing the action; Obtaining a characteristic type of the entity object; Obtain a word set describing the entity object of the feature type; Selecting a word that matches the action information from the word set as a candidate word; Display the candidate words; or The text corresponding to the action information in the above text is replaced with the candidate word.

2. The method according to claim 1, characterized in that The method further comprises: Feature information of a plurality of different entity objects is collected in advance, and a feature type of each entity object is determined based on the feature information.

3. The method according to claim 1, characterized in that The method further comprises: Collect corpus describing specific scenarios in advance, and extract words describing entity objects from the corpus; Adding feature tags to the words to obtain a word set with different feature tags, wherein the feature tags are used to characterize the feature types of the entity objects described by the words; The acquiring of a word set describing the entity object of the feature type includes: Determining a feature label corresponding to the feature type; A word set having a feature label corresponding to the feature type is obtained.

4. The method according to claim 1, wherein The above text refers to words that have been displayed on the screen and / or words that have entered the editing box, or words that have been selected by the user to be displayed on the screen.

5. An input device, characterized in that: Applied to a special edition input method, the device includes: The previous text acquisition module is used to obtain the previous text currently input by the user; An information extraction module, configured to extract the entity objects and action information mentioned above, wherein the entity objects refer to specific people, and the action information refers to words describing the actions; A feature information acquisition unit, configured to acquire a feature type of the entity object; A word acquisition unit, configured to acquire a word set describing an entity object of the feature type; A screening module, configured to select words matching the action information from the word set as candidate words; The recommendation module is used to display the candidate words; or replace the text corresponding to the action information in the above text with the candidate words.

6. An electronic device, characterized in that: include: One or more processors, memory; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method according to any one of claims 1 to 4.

7. A readable storage medium having instructions stored thereon, wherein the instructions are executed to implement the method according to any one of claims 1 to 4.

Images