WO2020037921A1

WO2020037921A1 - Expression picture prompting method and apparatus, computer device, and storage medium

Info

Publication number: WO2020037921A1
Application number: PCT/CN2018/123558
Authority: WO
Inventors: 刘继鹏; 魏斌斌; 冯智斌; 伍朗; 安栋
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-08-23
Filing date: 2018-12-25
Publication date: 2020-02-27
Also published as: CN109408658A

Abstract

Disclosed in the present application are an expression picture prompting method and apparatus, a computer device, and a storage medium. The expression picture prompting method comprises: obtaining a user speech, and converting the user speech into a corresponding text; obtaining a preset keyword table, and extracting a target keyword from the text according to the preset keyword table; obtaining candidate expression pictures according to the target keyword; obtaining an expression picture selection instruction, selecting at least one target expression picture from the candidate expression pictures according to the expression picture selection instruction, and outputting the target expression picture. By using the expression picture prompting method, the target expression picture can be found quickly, and the efficiency of searching for the target expression picture and outputting the target expression picture is improved.

Description

Expression picture prompting method, device, computer equipment and storage medium

This application is based on a Chinese invention patent application filed on August 23, 2018 with application number 201810964494.3, entitled "Expression method, device, computer equipment, and storage medium for emoticons", and claims its priority.

Technical field

The present application relates to the field of computers, and in particular, to a method, a device, a computer device, and a storage medium for prompting an expression picture.

Background technique

At present, in the chat software of users, a variety of emoticons emerge endlessly, and the number of emoticons used by each user is increasing. With the increase of emoticons, when a user wants to find a specific emoticon picture, it usually requires multiple clicks, swipes, etc. to find a particular emoticon picture. In the case of too many emoticons, the user needs to spend more The time is used for the expression picture search, which affects the efficiency of finding and outputting the expression picture.

Summary of the Invention

The embodiments of the present application provide a method, a device, a computer device, and a storage medium for prompting an expression picture, so as to solve the problem of inefficient search for the expression picture.

An expression picture prompting method includes:

Obtaining a user voice, and converting the user voice into corresponding text;

Obtaining a preset keyword list, and extracting target keywords from the text according to the preset keyword list;

Obtaining candidate expression pictures according to the target keywords;

Acquire an expression picture selection instruction, select at least one target expression picture from the candidate expression pictures according to the expression picture selection instruction, and output the target expression picture.

An expression picture prompting device includes:

A text-to-text module, configured to obtain a user's voice and convert the user's voice into corresponding text;

A target keyword obtaining module, configured to obtain a preset keyword list, and extract a target keyword from the text according to the preset keyword list;

A candidate expression picture acquisition module, configured to acquire a candidate expression picture according to the target keyword;

A target expression picture selection module is configured to obtain an expression picture selection instruction, select at least one target expression picture from the candidate expression pictures according to the expression picture selection instruction, and output the target expression picture.

A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the following steps are implemented:

Obtaining a user voice, and converting the user voice into corresponding text;

Obtaining candidate expression pictures according to the target keywords;

A computer non-volatile readable storage medium stores computer readable instructions. When the computer readable instructions are executed by a processor, the following steps are implemented:

Obtaining a user voice, and converting the user voice into corresponding text;

Obtaining candidate expression pictures according to the target keywords;

In the method, device, computer equipment, and storage medium provided by the embodiment of the present application, a user's voice is first obtained, the user's voice is converted into corresponding text, and the meaning contained in the user's voice is obtained through the text. The text realizes the expression of the expression picture; then, a preset keyword list is obtained, and the target keywords are extracted from the text according to the preset keyword list. The target keyword in the text is extracted through the preset keyword list. The target keywords related to user needs are extracted from the text, and the target keywords are reflected by the keywords stored in the keyword table; then the candidate expression pictures are obtained according to the target keywords, and the corresponding candidate expression pictures can be determined by the target keywords. The candidate expression pictures are obtained based on the target keywords, which can ensure the correlation between the candidate expression pictures and the target keywords and reflect the internal connection with the target keywords, and can ensure that the obtained candidate expression pictures are more accurate, Appropriate; finally get the emoticon picture selection instruction, according to the emoticon picture The selection instruction selects at least one target expression picture from the candidate expression pictures and outputs the target expression picture. The user can realize the function of outputting at least one target expression picture from the candidate expression pictures through the expression picture selection instruction, which effectively improves the expression picture. Output efficiency.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solution of the embodiments of the present application more clearly, the drawings used in the description of the embodiments of the application will be briefly introduced below. Obviously, the drawings in the following description are just some embodiments of the application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a flowchart of a method for prompting an expression picture according to an embodiment of the present application; FIG.

FIG. 2 is a schematic diagram of an expression picture prompting device according to an embodiment of the present application; FIG.

FIG. 3 is a schematic diagram of a computer device according to an embodiment of the present application.

detailed description

In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

FIG. 1 shows a flowchart of a method for prompting an expression picture in this embodiment. The emoticon picture reminding method can be applied to a chat type application, and is used to implement the function of obtaining a candidate emoticon picture from a chat type application and selecting at least one target emoticon picture from the candidate emoticon picture. In a chat-type application on a computer device. The computer device is a device that can perform human-computer interaction with a user, including, but not limited to, a computer, a smart phone, and a tablet. As shown in FIG. 1, the method for prompting an expression picture includes the following steps:

S10: Acquire the user's voice, and convert the user's voice into corresponding text.

In an embodiment, acquiring the user's voice may be achieved by collecting the user's voice through a recording module integrated on the computer device or a recording device connected to the computer device. Specifically, it may be that the computer device collects the voice emitted by the user when the target application is running and the user uses the target application. Among them, the target application may refer to a chat-type application, such as WeChat, QQ, and Ali Wangwang. When the user is using the target application and emits the user's voice, the computer device will capture and acquire the user's voice in real time, and convert the user's voice into corresponding text. Understandably, the user's voice carries a corresponding meaning, and the computer device cannot directly recognize the user's voice and cannot know the meaning carried in the user's voice. Therefore, the user's voice needs to be converted to recognize it. Specifically, it can be implemented by converting the user's voice into corresponding text, so as to know the meaning in the user's voice, and realize a more accurate and appropriate expression picture prompt function according to the meaning in the user's voice.

S20: Obtain a preset keyword list, and extract target keywords from the text according to the preset keyword list.

The keyword table refers to a data table created based on keywords and storing keywords. You can find out which specific words belong to keywords through this keyword list. Understandably, the keyword list defines keywords, and words appearing in the keyword list are considered keywords.

In one embodiment, a preset keyword list is searched and obtained from a database, and the target keywords are extracted from the text according to the keywords recorded and stored in the keyword list. Understandably, the text obtained by the user's voice conversion contains information related to keywords and information not related to keywords, and it is necessary to find out information related to keywords (that is, target keywords) in the text through a keyword table. Normally, the keyword-related information appearing in the text is only a part of all the keywords. Therefore, the keywords extracted in the text are called target keywords. In this embodiment, the preset keyword list is used to extract the target keywords of the text. The target keywords related to the user's needs can be extracted from the text to obtain accurate and suitable candidate expression pictures based on the target keywords. Provide a favorable foundation.

S30: Obtain candidate expression pictures according to the target keywords.

In one embodiment, by using the target keywords extracted in the text, corresponding candidate expression pictures can be obtained according to the target keywords, where one or more candidate expression pictures can be obtained. For example, the text is "I'm tired, I'm going to sleep", and the target keywords extracted from the text are "I", "Fatigue", and "Sleep." "Correspondingly finds candidate expression pictures corresponding to the target keyword. The candidate expression pictures are obtained based on the target keywords, which can ensure the correlation between the candidate expression pictures and the target keywords and the internal connection between the candidate expression pictures and the target keywords, and can make the obtained candidate expression pictures more accurate and appropriate.

S40: Obtain an expression picture selection instruction, select at least one target expression picture from the candidate expression pictures according to the expression picture selection instruction, and output the target expression picture.

The expression picture selection instruction refers to an operation instruction for selecting an expression. The target expression picture refers to the expression that the user wants to obtain. In one embodiment, the computer device obtains an expression picture selection instruction input by the user, selects at least one target expression picture from the candidate expression pictures according to the expression picture selection instruction, and outputs the target expression picture. Specifically, the emoticon picture selection instruction can be obtained in different ways. It can be the user's voice to convert the voice into an emoticon picture selection instruction to select an emoticon, or the user can click and the computer device generates an emoticon picture based on the click trigger. Select the command for expression selection. In addition, there may be one or more candidate expression pictures, and the user may select one or more target expression pictures from the candidate expression pictures according to actual needs, and output the target expression pictures. In this embodiment, the function of outputting at least one target expression picture from the candidate expression pictures by the user through the expression picture selection instruction can be implemented, and the efficiency of the expression picture output can be effectively improved.

In steps S10-S40, the meaning contained in the user's voice is obtained by converting the user's voice into the corresponding text, and the expression picture prompt is realized based on the text; the target keyword in the text is extracted through a preset keyword list, which can Extract the target keywords related to user needs from the text, and provide a favorable basis for subsequent accurate and suitable candidate expression pictures based on the target keywords. The corresponding candidate expression pictures can be determined by the target keywords to ensure that the candidate expression pictures and The correlation between the target keywords and the internal relationship with the target keywords can make the obtained candidate expression pictures more accurate and appropriate; at least one target expression can be selected from the candidate expression pictures through the expression picture selection instruction The function of picture output effectively improves the efficiency of expression picture output.

In an embodiment, before step S10, that is, before the steps of obtaining the user's voice and converting the user's voice into corresponding text, the following steps are specifically included:

S111: Set the voice emission monitoring function and voice interception function according to the voice function setting instruction.

In an embodiment, it can be understood that obtaining user voice requires real-time user voice monitoring and user voice interception of the target application. Therefore, it is necessary to obtain a voice function setting instruction input by the user and set the corresponding voice to issue monitoring according to the instruction. Function and voice interception function. Specifically, the voice emission monitoring function is used to detect the emission and end of the user's voice, and the voice interception function is to intercept the corresponding user's voice within the time period when the user's voice is emitted and ended, and to monitor and intercept the user's voice can use the corresponding function The method function (or interface) is implemented and set in the target application, so that the user's voice issued by the user when using the target application can be obtained smoothly.

S112: Use the voice-out monitoring function to monitor whether the user emits user voice.

In one embodiment, the voice emission monitoring function should be activated before obtaining the user's voice in order to monitor the user's voice in real time. Specifically, the (voice) set voice activation monitoring function is used to use the function to monitor the user's voice. To monitor.

S113: If the user's voice is monitored, the voice interception function is activated. The voice interception function is used to obtain the user's voice.

In one embodiment, when the user's voice is monitored by the voice emission monitoring function, the voice interception function is activated accordingly to obtain the user voice. Understandably, the activation condition of the voice interception function is the emission of the user's voice. After the user's voice is monitored, the voice interception function can be activated immediately to obtain the user's voice in the first time.

Steps S111-S113 provide a better implementation for obtaining user's voice. It can monitor whether the user's voice is issued and ended in real time, and activate the voice interception function when the user's voice is monitored. Guarantee.

In an embodiment, in step S10, acquiring the user voice, acquiring the user voice, and converting the user voice into corresponding text, specifically includes the following steps:

S121: Acquire a user voice and convert the user voice into a corresponding file stream.

Among them, the file stream is also called a character stream or a byte stream.

In an embodiment, the acquired user voice includes, but is not limited to, audio files in a format such as wav, but the acquired user voice cannot be directly recognized, and an audio file in a format such as wav needs to be converted into a file stream to convert the user voice according to the file stream Converted to text. The file stream is essentially a carrier way to save the user's voice in a binary form. After reading the "file stream", the user's voice can be converted into corresponding text.

S122: Convert the file stream into text through the speech recognition interface.

In one embodiment, the file stream can be converted into text through a speech recognition interface, where the speech recognition interface refers to an interface that is encapsulated for converting a user's speech into corresponding text. Specifically, the speech recognition interface is made to decode a file stream by using acoustic characteristics, the relationship between each word in the user's voice in the context, and the mapping relationship between text and pronunciation, and obtain the text generated after the file stream is decoded. Among them, the acoustic characteristics include the transfer relationship between each pronunciation, and the relationship between the pronunciation and the acoustic characteristics, that is, after the file stream is decoded, a text corresponding to an audio file (user voice) is generated. Acoustic characteristics, the relationship of each word in the context, and the mapping relationship between words and pronunciation can be established through the establishment of corresponding mathematical models and continuous training to improve the model. For example, you can build an acoustic model based on the transfer relationship between pronunciations, and the relationship between pronunciation and sonic characteristics; build a language model based on the relationship of each word in the context; build a dictionary model based on the mapping relationship between text and pronunciation; thereafter , Training the established acoustic model, language model and dictionary model respectively, and then decoding the file stream through the trained acoustic model, language model and dictionary model to convert the file stream into text.

In steps S121-S122, the user's voice is converted into a file stream recognized by the computer, and then the file stream is converted into text through a voice recognition interface. The voice recognition interface uses acoustic features and the relationship between the words in the user's voice in the context The decoding relationship between the text and pronunciation decodes the file stream, which can effectively ensure that the user's speech is accurately converted to text, and provides an important implementation basis for subsequent extraction of target keywords from the text.

In one embodiment, before step S20, that is, the step of obtaining a preset keyword list and extracting the target keywords from the text according to the preset keyword list, specifically includes the following steps:

S21: Obtain an expression picture to be associated, and the expression picture to be associated includes an expression tag word.

Understandably, the user has more or less emoticon pictures in the target application, and some of the emoticon pictures are set with emoticon tag words. For example, each emoticon picture in some emoticons has a corresponding tag word For example, a set of emoticons contains expression tags corresponding to multiple emoticon pictures such as "happy", "angry", "sad", "sleeping" and "bye". For some expression pictures (such as self-made expressions, favorite expressions, etc.) without the expression tag words, the user can customize the settings and set a corresponding expression tag word for each expression picture. The emoticon pictures stored by the user in the target application can all be emoji pictures to be associated, and the emoji pictures to be associated are emoji pictures to be associated, and the specific association of the emoji pictures to be associated can be realized according to the expression tag words. In one embodiment, the expression pictures to be associated are obtained, that is, the expression pictures that the user wants to associate in the target application are obtained in advance.

S22: Use the expression tag words as keywords, and create a keyword list based on the keywords.

Understandably, the expression tag words actually represent the meaning of various expression pictures to be associated, so the expression tag words are used as keywords, and a keyword list is created based on the keywords (the keyword list corresponds to the preset in step S20) Keyword list), that is, keywords are determined based on the expression tag words. In particular, the keyword list here is specifically set according to the expression pictures to be associated stored in the target application. If you use the open source keyword list directly, the amount of data will be too large (more keywords), which will obviously cause The data is redundant and cannot be closely matched with the actual usage of the user, which will waste memory resources and reduce operating efficiency.

Steps S21-S22 obtain the emoticon pictures to be associated in the target application according to the actual situation of the user, and create a keyword list according to the actual situation of the user according to the expression tag words. The keyword list here is created relative to each different user, which can effectively improve the utilization of memory resources and the efficiency of operation.

In an embodiment, in step S30, obtaining candidate expression pictures according to the target keywords, specifically includes the following steps:

S311: Obtain a keyword standardized comparison table, and convert the target keywords into the target standard keywords according to the keyword standardized comparison table.

In one embodiment, a keyword standardized comparison table is obtained, wherein the keyword standardized comparison table refers to a data table storing a mapping relationship between keywords and standard keywords, and the table may be created in advance. For example, "88", "bye" and "bye" all express the same meaning. You can unify "88" and "bye" into the keyword "bye", and use "bye" as the standard keyword. It can be understood In actual scenarios, each user's terminology is different, which is prone to errors when creating a data table with a mapping relationship between keywords and expression pictures, and increases the redundancy of the data. Therefore, you can standardize different keywords with the same meaning and take one of the words with the same meaning as the standard word. At this time, regardless of the user's idiom, the keywords extracted in the user's voice will be standardized and converted first. Are standard keywords. In this embodiment, a target keyword is converted into a target standard keyword according to a keyword normalization comparison table. The target keyword is extracted from the text, and the target keyword is a subset of the keyword. The keyword range is relatively large. , Corresponds to all the expression label words to be associated with the expression picture, and the target keywords correspond to the keywords in the user's voice. After the target keywords are converted according to the mapping relationship between the keywords stored in the keyword standardized comparison table and the standard keywords, the target standard keywords are obtained.

S312: Obtain a standard keyword mapping table, and obtain a candidate expression picture corresponding to the target standard keyword according to the standard keyword mapping table.

In an embodiment, a standard keyword mapping table is obtained, wherein the standard keyword mapping table refers to a data table storing a mapping relationship between the standard keywords and the expression pictures to be associated, and the table may be created in advance. The target standard keywords are standard keywords, and the target standard keywords can obtain corresponding candidate expression pictures according to the keyword mapping table.

Steps S311-S312, respectively obtaining a keyword standardized comparison table and a standard keyword mapping table. First, the target keywords are converted into the target standard keywords through the keyword standardized comparison table, which can standardize the target keywords and effectively improve subsequent acquisition candidates. The accuracy of the expression pictures, and then the corresponding candidate expression pictures are obtained through the standard keyword mapping table. The candidate expression pictures can be quickly obtained according to the mapping relationship between the standard keywords and the expression pictures to be associated.

In an embodiment, before step S30, that is, before the step of obtaining the keyword standardized comparison table, the following steps are specifically included:

S321: Create a keyword standardized comparison table according to the meaning of keywords in the keyword table, and use the keyword standardized comparison table to standardize keywords to obtain standard keywords.

The keyword list includes keywords, and the keywords include keyword meanings. In one embodiment, a standardized keyword comparison table can be created according to the meaning of keywords. For example, different keywords with the same meaning are "sleep", "training" and "sleeping". The key word is "sleep", and "sleep" is the standard keyword. After the keyword normalization comparison table is created according to the meaning of the keywords, when "training" and "sleeping" are encountered again, the "training" and "sleeping" will be automatically standardized according to the mapping relationship stored in the table. Get the standard keyword "sleep".

S322: Create a mapping relationship between the standard keywords and the expression pictures to be associated, and obtain a standard keyword mapping table.

In an embodiment, a mapping relationship between a standard keyword and an expression picture to be associated is created. Specifically, a mapping relationship between the keyword and the expression picture to be associated can be implemented by using a HashMap, where the HashMap is Implementation of Map interface based on hash table. This implementation provides all optional mapping operations and allows the use of null values and null keys. (Except for asynchronous and null, HashMap is roughly the same as Hashtable.) In addition, in addition to the common one-to-one mapping relationship, you can also use the HashMap <Integer, List> format to achieve one-to-many mapping relationship. <Integer, List> represents the "key" and "value" of the key-value pair, where the key value can be an integer and used as an ID-like primary key. The value value can be used in the List collection. To save multiple pieces of data to achieve one-to-many mapping. After the mapping relationship between the standard keywords and the expression pictures to be associated is created, a standard keyword mapping table is obtained.

Further, it is possible to set regular refresh of the to-be-associated expression pictures in the target application and update the standard keyword mapping table. Of course, manual refresh is also supported to update the standard keyword mapping table.

In steps S321-S322, a standard keyword mapping table is created by creating a keyword standardized comparison table and using the standard keywords obtained from the keyword standardized comparison table to standardize the target keywords in steps S311-S312 and pass the standard key The acquisition of corresponding candidate expression pictures by the word mapping table provides an important technical basis, and both the keyword standardized comparison table and the standard keyword mapping table are based on the expression pictures stored in the target application (where (Emotions are to-be-associated expression pictures) data tables that are "tailored", which can improve the efficiency of obtaining candidate expression pictures and improve the accuracy of logic between keywords.

In an embodiment, after step S30, that is, after the step of obtaining a candidate expression picture corresponding to the target standard keyword according to the keyword mapping table, the method specifically includes the following steps:

S331: If the number of candidate expression pictures exceeds a preset number threshold, the preset names of the candidate expression pictures are displayed in the form of a list.

S332: If the number of candidate expression pictures does not exceed a preset number threshold, the candidate expression pictures are displayed.

In steps S331-S332, if the preset number threshold is 3, when the number of candidate expression pictures exceeds 3, the preset names of the candidate expression pictures are displayed in the form of a list, where the preset name refers to the preset The name that is related to the expression and is represented by a text bar. For example, the preset name can be a text bar: "Gang Xiaohu, shy", Jiang Xiaohu represents the name of this series of emoticons, and shyness is a standard keyword . This is just one of the design methods of the preset name, which is not limited here. When the number of candidate expression pictures does not exceed 3, the candidate expression pictures are directly displayed. Understandably, when the number of candidate expression pictures is small (not exceeding the preset number threshold), it is more intuitive to display the candidate expression pictures in the form of pictures, and when there are more candidate expression pictures (exceeding the preset number threshold) Using the preset name method can highlight more candidate expression pictures while highlighting the key points of the candidate expression pictures.

In particular, taking WeChat as an example, non-album expression packs (that is, favorite expression packs) can also be customized to make such expression pictures can also implement the function of expression picture prompts through user voice.

In the method for prompting an expression of an emoticon provided in this embodiment, real-time monitoring of whether a user's voice is issued and ended is set by setting a voice-out monitoring function and a voice-interception function according to a voice function setting instruction, and activating the voice-interception function when the user's voice is monitored, is Implementing the steps of obtaining user's voice provides effective guarantee; obtaining user's voice, converting the user's voice into the corresponding text, to get the meaning contained in the user's voice through the text, and implementing the emoticon picture prompt based on the text; obtaining the target application The to-be-associated emoticon pictures in the image, and a keyword list according to the actual situation of the user is created according to the emoji label words. The keyword list is created for each different user, which can effectively improve the utilization of memory resources and the efficiency of operation. Obtain a keyword list, extract target keywords from the text according to the keyword list, and use the keyword list to extract target keywords in the text. You can extract target keywords related to user needs from the text. The keyword expressions stored in the keyword table; obtain the keyword standardized comparison table and the standard keyword mapping table, and first convert the target keywords into the target standard keywords through the keyword standardized comparison table, which can standardize the target keywords. Effectively improve the accuracy of subsequent candidate expression pictures, and then obtain corresponding candidate expression pictures through the standard keyword mapping table. You can quickly obtain candidate expression pictures according to the mapping relationship between the standard keywords and the expression pictures to be associated; Obtain an emoticon picture selection instruction, select at least one target emoticon picture from the candidate emoticon pictures according to the emoticon picture selection instruction, and output the target emoticon picture, so that the user can achieve at least one target emoticon from the candidate emoticon picture through the emoticon picture selection instruction. Picture output function Effectively improve the efficiency of expression picture output.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

FIG. 2 shows a principle block diagram of an expression picture prompting device corresponding to the expression picture prompting method in the embodiment. As shown in FIG. 2, the expression picture prompting device includes a text conversion module 10, a target keyword acquisition module 20, a candidate expression picture acquisition module 30, and a target expression picture selection module 40. The implementation functions of the text conversion module 10, the target keyword acquisition module 20, the candidate expression picture acquisition module 30, and the target expression picture selection module 40 correspond to the steps corresponding to the expression picture prompting method in the embodiment. To avoid redundant description, this The examples are not detailed in detail.

The text-to-text module 10 is configured to obtain a user's voice and convert the user's voice into corresponding text.

The target keyword obtaining module 20 is configured to obtain a preset keyword list, and extract a target keyword from the text according to the preset keyword list.

The candidate expression picture acquiring module 30 is configured to acquire a candidate expression picture according to a target keyword.

The target expression picture selection module 40 is configured to obtain an expression picture selection instruction, select at least one target expression picture from the candidate expression pictures according to the expression picture selection instruction, and output the target expression picture.

Preferably, the expression picture prompting device further includes an expression tag word acquisition unit and a keyword list creation unit.

An expression tag word acquisition unit is configured to acquire an expression picture to be associated, and the expression picture to be associated includes an expression tag word.

A keyword list creation unit is configured to use the expression tag words as keywords and create a keyword list based on the keywords.

Preferably, the candidate expression picture acquisition module 30 includes a target standard keyword conversion unit and a candidate expression picture acquisition unit.

The target standard keyword conversion unit is configured to obtain a keyword standardized comparison table, and convert the target keyword into a target standard keyword according to the keyword standardized comparison table.

The candidate expression picture obtaining unit is configured to obtain a standard keyword mapping table, and obtain a candidate expression picture corresponding to the target standard keyword according to the standard keyword mapping table.

Preferably, the keyword list includes keywords.

Preferably, the expression picture prompting device further includes a standard keyword acquisition unit and a standard keyword mapping table acquisition unit.

A standard keyword obtaining unit is configured to create a keyword standardized comparison table according to the meaning of keywords in the keyword table, and use the keyword standardized comparison table to standardize keywords to obtain standard keywords.

The standard keyword mapping table acquisition unit is used to create a mapping relationship between the standard keywords and the expression pictures to be associated, and obtain a standard keyword mapping table.

Preferably, the expression picture prompting device further includes a name display unit and a picture display unit.

A name display unit is configured to display the preset names of the candidate expression pictures in a list form if the number of the candidate expression pictures exceeds a preset number threshold.

The picture display unit is configured to display the candidate expression pictures if the number of the candidate expression pictures does not exceed a preset number threshold.

Preferably, the expression picture prompting device further includes a function setting unit, a monitoring unit, and an interception function starting unit.

The function setting unit is configured to set a voice emission monitoring function and a voice interception function according to the voice function setting instruction.

The monitoring unit is used to monitor whether a user makes a user voice by using a voice output monitoring function.

The interception function activation unit is used to activate the voice interception function if the user's voice is monitored, and the voice interception function is used to obtain the user's voice.

Preferably, the text conversion module 10 includes a file stream conversion unit and a text conversion unit.

The file stream conversion unit obtains a user voice and converts the user voice into a corresponding file stream.

Text-to-text unit, which converts a file stream into text via a speech recognition interface.

This embodiment provides a computer nonvolatile readable storage medium. The computer nonvolatile readable storage medium stores computer readable instructions. When the computer readable instructions are executed by a processor, the emoticon pictures in the embodiment are prompted. Methods, to avoid repetition, we will not repeat them here. Alternatively, when the computer-readable instructions are executed by the processor, the functions of the modules / units in the expression picture prompting device in the embodiment are implemented. To avoid repetition, details are not described here one by one.

FIG. 3 is a schematic diagram of a computer device according to an embodiment of the present application. As shown in FIG. 3, the computer device 50 of this embodiment includes a processor 51, a memory 52, and computer-readable instructions 53 stored in the memory 52 and executable on the processor 51. The computer-readable instructions 53 are processed When the device 51 is executed, the method for prompting expressions in the embodiment is implemented. To avoid repetition, details are not described herein. Alternatively, when the computer-readable instructions are executed by the processor 51, the functions of each model / unit in the expression picture prompting device in the embodiment are implemented. To avoid repetition, details are not described here one by one.

The computer device 50 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The computer device may include, but is not limited to, a processor 51 and a memory 52. Those skilled in the art can understand that FIG. 3 is only an example of the computer device 50, and does not constitute a limitation on the computer device 50. It may include more or less components than shown in the figure, or combine some components or different components For example, computer equipment can also include input and output equipment, network access equipment, and buses.

The so-called processor 51 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 52 may be an internal storage unit of the computer device 50, such as a hard disk or a memory of the computer device 50. The memory 52 may also be an external storage device of the computer device 50, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, or a flash memory card (Flash) provided on the computer device 50. Card) and so on. Further, the memory 52 may include both an internal storage unit of the computer device 50 and an external storage device. The memory 52 is used to store computer-readable instructions and other programs and data required by the computer device. The memory 52 may also be used to temporarily store data that has been output or is to be output.

Those skilled in the art can clearly understand that, for the convenience and brevity of the description, only the above-mentioned division of functional units and modules is used as an example. In practical applications, the above functions can be allocated by different functional units according to needs. Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.

The above-mentioned embodiments are only used to describe the technical solution of the present application, but are not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still implement the foregoing implementations. The technical solutions described in the examples are modified, or some technical features are equivalently replaced; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included Within the scope of this application.

Claims

An expression picture prompting method, comprising:

Obtaining a user voice, and converting the user voice into corresponding text;

Obtaining a preset keyword list, and extracting target keywords from the text according to the preset keyword list;

Obtaining candidate expression pictures according to the target keywords;

Acquire an expression picture selection instruction, select at least one target expression picture from the candidate expression pictures according to the expression picture selection instruction, and output the target expression picture.
The method for prompting an expression picture according to claim 1, wherein before the step of obtaining a preset keyword list, the method for prompting an expression picture further comprises:

Obtaining an expression picture to be associated, where the expression picture to be associated includes an expression tag word;

Use the expression tag word as a keyword, and create the keyword list according to the keyword.
The method for prompting an expression picture according to claim 2, wherein the obtaining an expression picture candidate according to the target keyword comprises:

Obtaining a keyword standardized comparison table, and converting the target keyword into a target standard keyword according to the keyword standardized comparison table;

A standard keyword mapping table is acquired, and the candidate expression pictures corresponding to the target standard keyword are acquired according to the standard keyword mapping table.
The method according to claim 3, wherein the keyword list includes the keywords, and before the step of obtaining a keyword standardized comparison table, the method further includes:

Creating the keyword standardized comparison table according to the meaning of the keywords in the keyword table, and using the keyword standardized comparison table to standardize the keywords to obtain standard keywords;

Create a mapping relationship between the standard keywords and the expression pictures to be associated, and obtain the standard keyword mapping table.
The method according to claim 3, wherein after the step of obtaining the candidate expression picture corresponding to the target standard keyword according to the standard keyword mapping table, the expression Picture prompting methods also include:

If the number of candidate expression pictures exceeds a preset number threshold, displaying the preset names of the candidate expression pictures in a list form;

If the number of the candidate expression pictures does not exceed a preset number threshold, the candidate expression pictures are displayed.
The method according to claim 1, wherein before the step of acquiring a user's voice, the method for prompting an expression picture further comprises:

Set the voice sending monitoring function and voice interception function according to the voice function setting instruction;

Adopting the voice emission monitoring function to monitor whether a user issues the user voice;

If the user voice is monitored, the voice interception function is activated, and the voice interception function is used to obtain the user voice.
The method according to any one of claims 1 to 6, wherein the acquiring a user's voice and converting the user's voice into corresponding text comprises:

Acquiring the user voice, and converting the user voice into a corresponding file stream;

The file stream is converted into the text through a speech recognition interface.
An expression picture prompting device, comprising:

A text-to-text module, configured to obtain a user's voice and convert the user's voice into corresponding text;

A target keyword obtaining module, configured to obtain a preset keyword list, and extract a target keyword from the text according to the preset keyword list;

A candidate expression picture acquisition module, configured to acquire a candidate expression picture according to the target keyword;

A target expression picture selection module is configured to obtain an expression picture selection instruction, select at least one target expression picture from the candidate expression pictures according to the expression picture selection instruction, and output the target expression picture.
The apparatus according to claim 8, further comprising:

An expression tag word acquisition unit, configured to acquire an expression picture to be associated, where the expression picture to be associated includes an expression tag word;

A keyword list creation unit is configured to use the expression tag word as a keyword, and create the keyword list according to the keyword.
The apparatus according to claim 9, wherein the candidate expression picture obtaining module comprises:

A target standard keyword conversion unit, configured to obtain a keyword standardized comparison table, and convert the target keyword into a target standard keyword according to the keyword standardized comparison table;

A candidate expression picture obtaining unit is configured to obtain a standard keyword mapping table, and obtain the candidate expression picture corresponding to the target standard keyword according to the standard keyword mapping table.
A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the computer-readable instructions as follows: step:

Obtaining a user voice, and converting the user voice into corresponding text;

Obtaining a preset keyword list, and extracting target keywords from the text according to the preset keyword list;

Obtaining candidate expression pictures according to the target keywords;

Acquire an expression picture selection instruction, select at least one target expression picture from the candidate expression pictures according to the expression picture selection instruction, and output the target expression picture.
The computer device according to claim 11, wherein the processor further implements the following steps when executing the computer-readable instructions:

Obtaining an expression picture to be associated, where the expression picture to be associated includes an expression tag word;

Use the expression tag word as a keyword, and create the keyword list according to the keyword.
The computer device according to claim 12, wherein the processor further implements the following steps when executing the computer-readable instructions:

Obtaining a keyword standardized comparison table, and converting the target keyword into a target standard keyword according to the keyword standardized comparison table;

A standard keyword mapping table is acquired, and the candidate expression pictures corresponding to the target standard keyword are acquired according to the standard keyword mapping table.
The computer device according to claim 13, wherein the keyword list includes the keywords, and the processor further implements the following steps when executing the computer-readable instructions:

Creating the keyword standardized comparison table according to the meaning of the keywords in the keyword table, and using the keyword standardized comparison table to standardize the keywords to obtain standard keywords;

Create a mapping relationship between the standard keywords and the expression pictures to be associated, and obtain the standard keyword mapping table.
The computer device according to claim 13, wherein the keyword list includes the keywords, and the processor further implements the following steps when executing the computer-readable instructions:

If the number of candidate expression pictures exceeds a preset number threshold, displaying the preset names of the candidate expression pictures in a list form;

If the number of candidate expression pictures does not exceed a preset number threshold, the candidate expression pictures are displayed.
A computer non-volatile readable storage medium stores computer-readable instructions, and is characterized in that, when the computer-readable instructions are executed by a processor, the following steps are implemented:

Obtaining an expression picture to be associated, where the expression picture to be associated includes an expression tag word;

Use the expression tag word as a keyword, and create the keyword list according to the keyword.
The computer non-volatile readable storage medium according to claim 16, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors further implement the following steps: :

Obtaining an expression picture to be associated, where the expression picture to be associated includes an expression tag word;

Use the expression tag word as a keyword, and create the keyword list according to the keyword.
The computer non-volatile readable storage medium according to claim 17, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors further implement the following steps: :

Obtaining a keyword standardized comparison table, and converting the target keyword into a target standard keyword according to the keyword standardized comparison table;

A standard keyword mapping table is acquired, and the candidate expression pictures corresponding to the target standard keyword are acquired according to the standard keyword mapping table.
The computer non-volatile readable storage medium according to claim 18, wherein the keyword list includes the keywords, and when the computer-readable instructions are executed by one or more processors, the Said one or more processors also implement the following steps:

Creating the keyword standardized comparison table according to the meaning of the keywords in the keyword table, and using the keyword standardized comparison table to standardize the keywords to obtain standard keywords;

Create a mapping relationship between the standard keywords and the expression pictures to be associated, and obtain the standard keyword mapping table.
The computer non-volatile readable storage medium according to claim 18, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors further implement the following steps: :

If the number of candidate expression pictures exceeds a preset number threshold, displaying the preset names of the candidate expression pictures in a list form;

If the number of candidate expression pictures does not exceed a preset number threshold, the candidate expression pictures are displayed.