WO2011075972A1 - Method for adding word stock of mobile terminal and mobile terminal - Google Patents

Method for adding word stock of mobile terminal and mobile terminal Download PDF

Info

Publication number
WO2011075972A1
WO2011075972A1 PCT/CN2010/072204 CN2010072204W WO2011075972A1 WO 2011075972 A1 WO2011075972 A1 WO 2011075972A1 CN 2010072204 W CN2010072204 W CN 2010072204W WO 2011075972 A1 WO2011075972 A1 WO 2011075972A1
Authority
WO
WIPO (PCT)
Prior art keywords
vocabulary
self
created
mobile terminal
thesaurus
Prior art date
Application number
PCT/CN2010/072204
Other languages
French (fr)
Chinese (zh)
Inventor
刘佳
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2011075972A1 publication Critical patent/WO2011075972A1/en

Links

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/06Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice

Definitions

  • the present invention relates to the technical field of mobile terminal design, and in particular, to a vocabulary adding method and a mobile terminal of a mobile terminal. Background technique
  • mobile terminals such as mobile phones, PHS, personal digital assistants, etc.
  • the input method system of the existing mobile terminal generally includes a system vocabulary and a user vocabulary.
  • the system vocabulary is used to satisfy the habits of most users, usually including people's commonly used vocabulary, such as "today”, “happy”, “eat” and so on.
  • User vocabulary used to meet the usage habits of specific users, to better improve the input efficiency of the specific user, usually including some special vocabulary (such as game nouns, movie or song names, company internal vocabulary, etc.), these special Vocabulary is often entered for very small groups, such as World of Warcraft players, literary enthusiasts, engineers, etc., but these special vocabulary is used in a low proportion of the overall user, and the existing lexicon is impossible to put these special The vocabulary is all included, which will result in very low efficiency and accuracy when users input these special words, which seriously affects the user experience.
  • special vocabulary such as game nouns, movie or song names, company internal vocabulary, etc.
  • the existing thesaurus adding methods mainly include pinyin input method, handwriting input method and automatic thesaurus synchronization method.
  • the Pinyin input method is very difficult for users who are not familiar with Pinyin;
  • the handwriting input method is useless for users who can't write and mobile phone users who don't support touch screen;
  • the automatic thesaurus synchronization method is mainly The combination of computer and mobile terminal for the addition of thesaurus, this method for mobile end The area where the network signal is not ideal is not up to the expected standard.
  • the embodiments of the present invention provide a method for adding a vocabulary of a mobile terminal and a mobile terminal, which are used to solve the problem that the existing mobile terminal vocabulary adding technology is not applicable to various users and mobile terminals.
  • the method further includes: receiving a start instruction.
  • the voice information is call information
  • determining the self-created vocabulary in the voice information is specifically:
  • the method further includes: monitoring to meet the added trigger condition; the adding the trigger condition is that the current time reaches the preset time, and the self-created vocabulary appears The number of times reaches the preset threshold or receives an add command.
  • the identifying the vocabulary in the call information further includes:
  • the method also includes: When the self-created vocabulary is incorrect, the input vocabulary is received, and the input vocabulary is stored in the vocabulary.
  • the method further includes:
  • the method also includes:
  • the number of uses of the respective vocabulary in the vocabulary in the preset time period is separately counted, and the self-created vocabulary whose usage times is less than the preset threshold number is deleted from the vocabulary.
  • a mobile terminal includes at least:
  • a voice receiving module configured to receive the input voice information and cache the same
  • a self-created vocabulary determining module configured to determine a self-created vocabulary in the voice information
  • An output module configured to output prompt information for determining whether the self-created vocabulary is correct to the display; and a result receiving module, configured to receive the determination result;
  • a storage operation module configured to store the self-created vocabulary into the thesaurus when the judgment result indicates that the self-created vocabulary is correct.
  • the instruction receiving module is configured to receive a start instruction before the voice receiving module receives the input voice information and buffers the voice information.
  • the self-made vocabulary determining module further includes:
  • An identification submodule configured to identify a vocabulary in the call information when the voice information is call information
  • the mobile terminal further includes: a monitoring module, configured to monitor whether the added triggering condition is met, where the adding triggering condition is that the current time reaches a preset time, the number of occurrences of the self-created vocabulary reaches a preset threshold value, or an adding instruction is received;
  • the output module further includes:
  • an output submodule configured to output, when the trigger condition is satisfied, a prompt message for determining whether the self-created vocabulary is correct to the display.
  • the mobile terminal further includes:
  • a statistics module configured to count the number of occurrences of the self-created vocabulary, and send the number of occurrences to the output module.
  • the storage operation module is further configured to: when the self-created vocabulary is incorrect, receive the input vocabulary, and store the input vocabulary into the thesaurus.
  • the mobile terminal further includes:
  • An eigenvalue determining module configured to determine a voice feature value of the self-created vocabulary
  • the storage operation module is further configured to store the voice feature value in the thesaurus after the self-created vocabulary is stored.
  • the mobile terminal further includes:
  • a first deleting module configured to receive an instruction for deleting a very self-created vocabulary, and deleting the very self-created vocabulary from the thesaurus;
  • the second deleting module is configured to separately count the number of times the respective vocabulary in the vocabulary is used within a preset time period, and delete the self-created vocabulary whose usage number is lower than the preset threshold number from the vocabulary.
  • the technical solution provided by the embodiment of the present invention adopts a voice adding manner, that is, identifying a vocabulary in the received voice information, and adding the recognized vocabulary to the vocabulary, and the manner of adding the voice is not only universally applicable to each Users and mobile terminals, and make the process of adding the thesaurus more flexible and convenient.
  • FIG. 1 is a flowchart of an embodiment of a method for adding a thesaurus of a mobile terminal according to the present invention
  • FIG. 3 is a flowchart of a method according to a second embodiment of the present invention.
  • FIG. 4A is a schematic diagram of a structural embodiment of a mobile terminal according to the present invention.
  • FIG. 4B is a schematic diagram of another structural embodiment of a mobile terminal according to the present invention.
  • FIG. 4C is a schematic diagram of a structural embodiment of a mobile terminal including a statistic module according to the present invention
  • FIG. 4D is a schematic diagram of a structural embodiment of a mobile terminal including an instruction receiving module according to the present invention
  • FIG. 4E is a mobile terminal including a feature value determining module according to the present invention
  • FIG. 4F is a schematic diagram of a structural embodiment of a mobile terminal including a first deletion module and/or a second deletion module according to the present invention.
  • DETAILED DESCRIPTION OF THE INVENTION In order to solve the problems existing in the prior art, embodiments of the present invention provide a vocabulary adding method and a mobile terminal for a mobile terminal.
  • the technical solution provided by the embodiment of the present invention adopts a voice adding manner, that is, determining a self-created vocabulary (ie, a vocabulary that does not exist in the vocabulary) in the received voice information, and adding the self-created vocabulary to the vocabulary.
  • This way of adding voice is not only universally applicable to various users and mobile terminals, but also makes the process of adding the thesaurus more flexible and convenient.
  • the method for adding a thesaurus of a mobile terminal includes the following steps:
  • Step 101 Receive the input voice information and cache it.
  • the voice information may be call information (such as voice call information or video call information), or the user may control the input voice information according to his or her own will (for example, if the user wants to add "victory” to the thesaurus, the user may The voice information of "victory" is input to the mobile terminal autonomously. If the user autonomously controls the input voice information as he wishes, then move Before executing step 101, the terminal should also receive a start instruction input by the user, that is, when the user wants to add a vocabulary to the vocabulary, the user can input a start instruction to the mobile terminal to instruct the mobile terminal to start the vocabulary adding process.
  • a start instruction input by the user that is, when the user wants to add a vocabulary to the vocabulary
  • the user can input a start instruction to the mobile terminal to instruct the mobile terminal to start the vocabulary adding process.
  • Step 102 Determine a self-created vocabulary in the voice information.
  • step 102 further includes the following steps:
  • Step 103 Output a prompt message for determining whether the self-created vocabulary is correct to the display.
  • step 103 the step of monitoring the addition of the trigger condition is also monitored.
  • the triggering condition may be that the current time reaches the preset time, the number of occurrences of the self-created vocabulary reaches the preset threshold, or an add instruction is received.
  • the preset time can be set by the user, which can be every 3 hours, 12 noon or 6 pm.
  • the preset threshold value may be set by the user, and may be 3 times, 5 times, 10 times, and the like. Moreover, when the trigger condition is that the number of occurrences of the self-created vocabulary reaches the preset threshold, after the step A1 is performed, the step of counting the number of occurrences of the vocabulary in the call information should also be performed.
  • the add instruction refers to an instruction generated by the user by triggering a specific button on the mobile terminal or by triggering the touch screen mobile terminal by a touch pen or a finger, instructing the mobile terminal to start performing the add vocabulary operation.
  • Step 104 Receive the judgment result, when the self-created vocabulary is correct, perform step 105; If the vocabulary is incorrect, go to step 106.
  • the user can input a judgment result to the mobile terminal by triggering a specific button on the mobile terminal or triggering the touch screen mobile terminal by a touch pen or a finger.
  • Step 105 Store the self-created vocabulary into the thesaurus when the self-created vocabulary is correct. End this process.
  • the mobile terminal can also determine the voice feature value of the self-created vocabulary, and store the voice feature value corresponding to the self-created vocabulary and store it in the lexicon.
  • the method for determining the voice feature value of the self-created vocabulary includes: a feature extraction method that may be used to abstract the user's voice into features in the fields of speech recognition and artificial intelligence.
  • the phonetic feature value can be a self-created vocabulary or other form of feature value, such as the "victory" voice feature value is "shl".
  • the advantage of storing the voice feature value corresponding to the self-created vocabulary and storing it in the thesaurus is that when the user wants to use the vocabulary in the thesaurus, the mobile terminal can output the corresponding corresponding voice feature value on the display terminal.
  • the vocabulary is available to the user, making it easier for users to use the thesaurus.
  • the above-mentioned thesaurus adding method further includes: receiving an instruction for deleting the self-created vocabulary, and deleting the self-created vocabulary from the vocabulary; and/or separately counting the vocabulary The number of times the vocabulary in the library is used within a preset time period, and the self-created vocabulary that is used less than the preset threshold number is deleted from the thesaurus.
  • the preset time period can be set by the user, including but not limited to 1 month, 3 months, etc.; the preset threshold number can also be set by the user, including but not limited to 20 times, 50 times, 100 times.
  • the advantage of deleting self-created vocabulary is that when there are many self-created vocabularies in the thesaurus, deleting a small number of uncommon self-created words will release part of the system resources of the mobile terminal.
  • the above-mentioned thesaurus adding method provided by the embodiment of the present invention adopts a voice adding manner, that is, identifying a vocabulary in the received voice information, and adding the recognized vocabulary to the vocabulary, the manner of adding the voice is not only universal It is suitable for a variety of users and mobile terminals, and makes the process of adding the thesaurus more flexible and convenient.
  • the voice information is used as the call information.
  • the specific embodiment 1 of the present invention includes the following steps:
  • Step 201 Receive the input call information and cache it.
  • the call information may be voice call information, video call information, and the like.
  • Step 202 Identify the vocabulary in the call information.
  • Step 203 Determine the self-created vocabulary in the above vocabulary.
  • Step 204 When it is monitored that the added trigger condition is met, output a prompt message for determining whether the self-created vocabulary is correct to the display.
  • the triggering condition may be that the current time reaches the preset time, the number of occurrences of the self-created vocabulary reaches the preset threshold, or an add instruction is received.
  • the step 202 When the trigger condition is that the number of occurrences of the self-created vocabulary reaches the preset threshold, after the step 202 is performed, the step of counting the number of occurrences of the vocabulary in the call information should also be performed.
  • Step 205 Receive the judgment result, when the self-created vocabulary is correct, perform step 206; when the self-created vocabulary is incorrect, perform step 207.
  • Step 206 Store the self-created vocabulary into the thesaurus when the self-created vocabulary is correct. End this process.
  • the mobile terminal can also determine the voice feature values of the self-created vocabulary, and store the voice feature values corresponding to the self-created vocabulary and store them in the thesaurus. Moreover, after storing the self-created vocabulary into the thesaurus, the mobile terminal can also receive the instruction to delete the self-created vocabulary, and delete the self-created vocabulary from the vocabulary; and/or separately calculate the respective vocabulary The number of times the vocabulary is used within a preset time period, and the self-created vocabulary that is used less than the preset threshold number is deleted from the thesaurus.
  • the mobile terminal obtains a self-created vocabulary from the call information, and adds the self-created vocabulary to the vocabulary.
  • the manner of adding the voice is very flexible and convenient, as long as the user mentions self-created in the call information. Vocabulary, the mobile terminal can add it to the thesaurus, without the user spending time and effort, the process of adding the thesaurus is more flexible and convenient, greatly improving the efficiency of the addition of the thesaurus, and is generally applicable to various users and mobile terminals.
  • the voice information is used as an example for the user to control the input voice information according to the user's will.
  • the second embodiment of the present invention includes the following steps:
  • Step 301 Receive a start instruction.
  • the user can input a start command to the mobile terminal by triggering a button on the mobile terminal. It can be seen that the vocabulary addition method is controlled by the user. When the user wants to add vocabulary to the vocabulary, the user can input a start instruction to the mobile terminal to start the vocabulary adding process.
  • Step 302 Receive the input voice information and cache it.
  • the mobile terminal may prompt the user to input voice information, and after the user sees the prompt information, the voice information may be input to the mobile terminal.
  • Step 303 Determine a self-created vocabulary in the voice information.
  • Step 304 Output prompt information for determining whether the self-created vocabulary is correct to the display.
  • Step 305 Receive the judgment result.
  • step 306 When the self-created vocabulary is correct, go to step 306; when the self-created vocabulary is incorrect, go to step 307.
  • Step 306 When the above vocabulary is self-created, the self-created vocabulary is stored in the thesaurus. End this process.
  • Step 307 When the self-created vocabulary is incorrect, the input vocabulary is received, and the input vocabulary is stored in the thesaurus.
  • the mobile terminal can also determine the voice feature value of the self-created vocabulary, and store the voice feature value corresponding to the self-created vocabulary and store it in the lexicon.
  • the mobile terminal can also receive the instruction to delete the self-created vocabulary, and delete the self-created vocabulary from the vocabulary; and/or separately calculate the respective vocabulary The number of times the vocabulary is used within a preset time period, and the self-created vocabulary that is used less than the preset threshold number is deleted from the thesaurus.
  • the above-mentioned thesaurus adding method provided by the embodiment of the present invention adopts a voice adding manner, that is, identifying a vocabulary in the received voice information, and adding the recognized vocabulary to the vocabulary, the manner of adding the voice is not only universal It is suitable for a variety of users and mobile terminals, and makes the process of adding the thesaurus more flexible and convenient.
  • the user can control the self-created vocabulary into the vocabulary according to his/her own will, and the voice adding method is flexible and convenient, and is generally applicable to various users and mobile terminals.
  • an embodiment of the present invention provides a mobile terminal, including:
  • a voice receiving module 401 configured to receive input voice information and cache it;
  • the self-created vocabulary determining module 402 is configured to determine a self-created vocabulary in the voice information
  • the output module 403 is configured to output prompt information for determining whether the self-created vocabulary is correct to the display; and the result receiving module 404 is configured to receive the determination result;
  • the storage operation module 405 is configured to store the self-created vocabulary into the thesaurus when the judgment result shows that the self-created vocabulary is correct.
  • the mobile terminal provided by the embodiment of the present invention adds a vocabulary to the vocabulary by means of voice input, and the vocabulary adding process is more flexible and convenient, and is generally applicable to various users.
  • the self-created vocabulary determining module 402 further includes:
  • the identification submodule 4021 is configured to identify a vocabulary in the call information when the voice information is call information;
  • a determining sub-module 4022 configured to determine a self-created vocabulary in the vocabulary
  • the above mobile terminal further includes:
  • the monitoring module 411 is configured to monitor whether the trigger condition is added, the trigger condition is that the current time reaches the preset time, the number of occurrences of the self-created vocabulary reaches a preset threshold, or an add instruction is received;
  • the output module 403 further includes:
  • the output sub-module 4031 is configured to output, when the trigger condition is added, a prompt message for determining whether the self-created vocabulary is correct to the display.
  • the mobile terminal shown in FIG. 4B (or FIG. 4A) further includes:
  • the statistics module 406 is configured to count the number of occurrences of the self-created vocabulary, and send the number of occurrences to the output module 403.
  • the mobile terminal shown in FIG. 4A further includes:
  • the instruction receiving module 407 is configured to receive a start instruction before the voice receiving module 401 receives the input voice information and buffers it.
  • the storage operation module 405 is further configured to receive the input vocabulary when the self-created vocabulary is incorrect, and store the input vocabulary into the thesaurus.
  • the user can input the correct vocabulary to the mobile terminal through editing, so that it is avoided that some self-created vocabulary cannot be added to the lexicon.
  • the mobile terminal shown in FIG. 4A (or FIG. 4B, or FIG. 4C, or FIG. 4D) further includes:
  • the feature value determining module 408 is configured to determine a voice feature value of the self-created vocabulary
  • the storage operation module 405 is further configured to store the voice feature value into the vocabulary corresponding to the self-created vocabulary.
  • the mobile terminal shown in FIG. 4A (or FIG. 4B, or FIG. 4C, or FIG. 4D, or FIG. 4E) further includes:
  • a first deletion module 409 configured to receive an instruction for deleting a very self-created vocabulary, and deleting the self-created vocabulary from the vocabulary;
  • the second deleting module 410 is configured to separately count the number of times the respective vocabulary in the vocabulary is used within a preset time period, and delete the self-created vocabulary whose usage times are less than the preset threshold number from the vocabulary.

Abstract

A method for adding word stock of mobile terminal and a mobile terminal. The invention uses way of voice adding which is identifying the vocabulary of the received voice information, and adding the identified vocabulary into a word stock. The way of voice adding may be generally applied to various user and mobile terminal.

Description

一种移动终端的词库添加方法和移动终端 技术领域  Method for adding vocabulary of mobile terminal and mobile terminal
本发明涉及移动终端设计技术领域, 特别涉及一种移动终端的词库添 加方法和移动终端。 背景技术  The present invention relates to the technical field of mobile terminal design, and in particular, to a vocabulary adding method and a mobile terminal of a mobile terminal. Background technique
随着技术的飞速发展, 不同专业领域、 不同兴趣以及使用习惯的用户 对于移动终端 (如手机、 小灵通、 个人数字助理等) 的输入法系统的智能 性要求越来越高。  With the rapid development of technology, users of different professional fields, different interests and usage habits have increasingly higher requirements for the input system of mobile terminals (such as mobile phones, PHS, personal digital assistants, etc.).
现有移动终端的输入法系统一般包括一个系统词库和一个用户词库。 其中, 系统词库用于满足大多数用户的使用习惯, 通常包括人们常用 的词汇, 比如 "今天"、 "快乐 "、 "吃饭" 等。  The input method system of the existing mobile terminal generally includes a system vocabulary and a user vocabulary. Among them, the system vocabulary is used to satisfy the habits of most users, usually including people's commonly used vocabulary, such as "today", "happy", "eat" and so on.
用户词库, 用于满足特定用户的使用习惯, 以更好地提高该特定用户 的输入效率, 通常包括一些特殊的词汇 (比如游戏名词、 电影或歌曲名、 公司内部词汇等), 这些特殊的词汇对非常小的群体来说会经常输入, 例如 魔兽世界玩家、 文艺爱好者、 工程师等, 但是这些特殊的词汇在总体用户 中的使用比例比较低, 现有词库是不可能把这些特殊的词汇全部包括进去 的, 这样就会导致用户在输入这些特殊的词汇时的效率和准确率非常低, 严重影响用户的使用体验。  User vocabulary, used to meet the usage habits of specific users, to better improve the input efficiency of the specific user, usually including some special vocabulary (such as game nouns, movie or song names, company internal vocabulary, etc.), these special Vocabulary is often entered for very small groups, such as World of Warcraft players, literary enthusiasts, engineers, etc., but these special vocabulary is used in a low proportion of the overall user, and the existing lexicon is impossible to put these special The vocabulary is all included, which will result in very low efficiency and accuracy when users input these special words, which seriously affects the user experience.
为了使词库能包括尽可能多的词汇, 便出现了词库添加方法。 现有的 词库添加方法主要包括拼音输入法、 手写输入法和自动词库同步法。 其中, 拼音输入法对不熟悉拼音的用户来说会有很大的困难; 手写输入法对于不 会写字的用户和不支持触摸屏的手机用户, 则全无用武之地; 自动词库同 步法主要是计算机和移动终端相结合进行词库添加, 这种方法对于移动终 端的网络信号不理想的区域则达不到期望的标准。 In order to make the thesaurus include as many words as possible, the method of adding the thesaurus appears. The existing thesaurus adding methods mainly include pinyin input method, handwriting input method and automatic thesaurus synchronization method. Among them, the Pinyin input method is very difficult for users who are not familiar with Pinyin; the handwriting input method is useless for users who can't write and mobile phone users who don't support touch screen; the automatic thesaurus synchronization method is mainly The combination of computer and mobile terminal for the addition of thesaurus, this method for mobile end The area where the network signal is not ideal is not up to the expected standard.
可见, 现有的移动终端词库添加技术不能普遍的适用于各种用户和移 动终端。 发明内容  It can be seen that the existing mobile terminal vocabulary addition technology cannot be universally applied to various users and mobile terminals. Summary of the invention
本发明实施例提供了一种移动终端的词库添加方法和移动终端, 用以 解决现有的移动终端词库添加技术不能普遍的适用于各种用户和移动终端 的问题。  The embodiments of the present invention provide a method for adding a vocabulary of a mobile terminal and a mobile terminal, which are used to solve the problem that the existing mobile terminal vocabulary adding technology is not applicable to various users and mobile terminals.
本发明实施例提供的一种移动终端的词库添加方法, 包括:  A method for adding a thesaurus of a mobile terminal according to an embodiment of the present invention includes:
接收输入的语音信息并将其緩存;  Receiving input voice information and buffering it;
确定所述语音信息中的自造词汇;  Determining a self-created vocabulary in the voice information;
输出判断所述自造词汇是否正确的提示信息至显示器;  Outputting prompt information for determining whether the self-created vocabulary is correct to the display;
接收判断结果, 并当所述自造词汇正确时, 将所述自造词汇存储至所 述词库中。  Receiving the judgment result, and storing the self-created vocabulary into the thesaurus when the self-created vocabulary is correct.
所述接收输入的语音信息并将其緩存之前, 还包括: 接收开始指令。 当所述语音信息为通话信息时, 所述确定所述语音信息中的自造词汇 具体为:  Before receiving the input voice information and buffering the same, the method further includes: receiving a start instruction. When the voice information is call information, determining the self-created vocabulary in the voice information is specifically:
识别所述通话信息中的词汇;  Identifying words in the call information;
在所述词汇中确定自造词汇;  Determining a self-made vocabulary in the voca
所述输出判断所述自造词汇是否正确的提示信息至显示器之前, 该方 法还包括: 监控到满足添加触发条件; 所述添加触发条件为当前时间达到 预置时间、 所述自造词汇的出现次数达到预设门限值或者接收到添加指令。  Before the outputting the information indicating whether the self-created vocabulary is correct to the display, the method further includes: monitoring to meet the added trigger condition; the adding the trigger condition is that the current time reaches the preset time, and the self-created vocabulary appears The number of times reaches the preset threshold or receives an add command.
当所述添加触发条件为所述自造词汇的出现次数达到预设门限值时, 所述识别所述通话信息中的词汇之后还包括:  After the adding the triggering condition is that the number of occurrences of the self-created vocabulary reaches a preset threshold, the identifying the vocabulary in the call information further includes:
统计所述词汇的出现次数。  Count the number of occurrences of the vocabulary.
该方法还包括: 当所述自造词汇不正确时, 接收输入的词汇, 并将所述输入的词汇存 储至所述词库中。 The method also includes: When the self-created vocabulary is incorrect, the input vocabulary is received, and the input vocabulary is stored in the vocabulary.
所述将所述自造词汇存储至所述词库中之后还包括:  After the storing the self-created vocabulary into the thesaurus, the method further includes:
确定所述自造词汇的语音特征值;  Determining a voice feature value of the self-created vocabulary;
将所述语音特征值对应所述自造词汇后存储至所述词库中。  And storing the voice feature value in the thesaurus after the self-created vocabulary is stored.
该方法还包括:  The method also includes:
接收删除非常用自造词汇的指令, 并将所述非常用自造词汇从所述词 库中删除; 和 /或,  Receiving an instruction to delete a self-created vocabulary and deleting the very self-created vocabulary from the vocabulary; and/or,
分别统计所述词库中各自造词汇在预设时间段内的使用次数, 并将使 用次数低于预设门限次数的自造词汇从所述词库中删除。  The number of uses of the respective vocabulary in the vocabulary in the preset time period is separately counted, and the self-created vocabulary whose usage times is less than the preset threshold number is deleted from the vocabulary.
一种移动终端, 至少包括:  A mobile terminal includes at least:
语音接收模块, 用于接收输入的语音信息并将其緩存;  a voice receiving module, configured to receive the input voice information and cache the same;
自造词汇确定模块, 用于确定所述语音信息中的自造词汇;  a self-created vocabulary determining module, configured to determine a self-created vocabulary in the voice information;
输出模块, 用于输出判断所述自造词汇是否正确的提示信息至显示器; 结果接收模块, 用于接收判断结果;  An output module, configured to output prompt information for determining whether the self-created vocabulary is correct to the display; and a result receiving module, configured to receive the determination result;
存储操作模块, 用于当所述判断结果显示所述自造词汇正确时, 将所 述自造词汇存储至词库中。  And a storage operation module, configured to store the self-created vocabulary into the thesaurus when the judgment result indicates that the self-created vocabulary is correct.
还包括:  Also includes:
指令接收模块, 用于在所述语音接收模块接收输入的语音信息并将其 緩存之前, 接收开始指令。  The instruction receiving module is configured to receive a start instruction before the voice receiving module receives the input voice information and buffers the voice information.
所述自造词汇确定模块, 进一步包括:  The self-made vocabulary determining module further includes:
识别子模块, 用于当所述语音信息为通话信息时, 识别所述通话信息 中的词汇;  An identification submodule, configured to identify a vocabulary in the call information when the voice information is call information;
确定子模块, 用于在所述词汇中确定自造词汇;  Determining a sub-module for determining a self-made vocabulary in the vocabulary;
所述移动终端还包括: 监控模块, 用于监控是否满足所述添加触发条件, 所述添加触发条件 为当前时间达到预置时间、 所述自造词汇的出现次数达到预设门限值或者 接收到添加指令; The mobile terminal further includes: a monitoring module, configured to monitor whether the added triggering condition is met, where the adding triggering condition is that the current time reaches a preset time, the number of occurrences of the self-created vocabulary reaches a preset threshold value, or an adding instruction is received;
所述输出模块, 进一步包括:  The output module further includes:
输出子模块, 用于当满足所述添加触发条件时, 输出判断所述自造词 汇是否正确的提示信息至显示器。  And an output submodule, configured to output, when the trigger condition is satisfied, a prompt message for determining whether the self-created vocabulary is correct to the display.
所述移动终端还包括:  The mobile terminal further includes:
统计模块, 用于统计所述自造词汇的出现次数, 并将所述出现次数发 送给所述输出模块。  And a statistics module, configured to count the number of occurrences of the self-created vocabulary, and send the number of occurrences to the output module.
所述存储操作模块, 还用于当所述自造词汇不正确时, 接收输入的词 汇, 并将所述输入的词汇存储至所述词库中。  The storage operation module is further configured to: when the self-created vocabulary is incorrect, receive the input vocabulary, and store the input vocabulary into the thesaurus.
所述移动终端还包括:  The mobile terminal further includes:
特征值确定模块, 用于确定所述自造词汇的语音特征值;  An eigenvalue determining module, configured to determine a voice feature value of the self-created vocabulary;
所述存储操作模块, 还用于将所述语音特征值对应所述自造词汇后存 储至所述词库中。  The storage operation module is further configured to store the voice feature value in the thesaurus after the self-created vocabulary is stored.
所述移动终端还包括:  The mobile terminal further includes:
第一删除模块, 用于接收删除非常用自造词汇的指令, 并将所述非常 用自造词汇从所述词库中删除; 和 /或,  a first deleting module, configured to receive an instruction for deleting a very self-created vocabulary, and deleting the very self-created vocabulary from the thesaurus; and/or,
第二删除模块, 用于分别统计所述词库中各自造词汇在预设时间段内 的使用次数, 并将使用次数低于预设门限次数的自造词汇从所述词库中删 除。  The second deleting module is configured to separately count the number of times the respective vocabulary in the vocabulary is used within a preset time period, and delete the self-created vocabulary whose usage number is lower than the preset threshold number from the vocabulary.
本发明实施例提供的技术方案采用的是语音添加的方式, 即识别接收 到的语音信息中的词汇, 并将识别出的词汇添加到词库中, 这种语音添加 的方式不仅普遍适用于各种用户和移动终端, 而且使得词库的添加过程更 加灵活方便。 附图说明 The technical solution provided by the embodiment of the present invention adopts a voice adding manner, that is, identifying a vocabulary in the received voice information, and adding the recognized vocabulary to the vocabulary, and the manner of adding the voice is not only universally applicable to each Users and mobile terminals, and make the process of adding the thesaurus more flexible and convenient. DRAWINGS
图 1为本发明移动终端的词库添加方法的实施例的流程图;  1 is a flowchart of an embodiment of a method for adding a thesaurus of a mobile terminal according to the present invention;
图 2为本发明具体实施例一的方法流程图;  2 is a flowchart of a method according to a first embodiment of the present invention;
图 3为本发明具体实施例二的方法流程图;  3 is a flowchart of a method according to a second embodiment of the present invention;
图 4A为本发明移动终端的结构实施例的示意图;  4A is a schematic diagram of a structural embodiment of a mobile terminal according to the present invention;
图 4B为本发明移动终端的另一结构实施例的示意图;  4B is a schematic diagram of another structural embodiment of a mobile terminal according to the present invention;
图 4C为本发明包括统计模块的移动终端的结构实施例的示意图; 图 4D为本发明包括指令接收模块的移动终端的结构实施例的示意图; 图 4E 为本发明包括特征值确定模块的移动终端的结构实施例的示意 图;  4C is a schematic diagram of a structural embodiment of a mobile terminal including a statistic module according to the present invention; FIG. 4D is a schematic diagram of a structural embodiment of a mobile terminal including an instruction receiving module according to the present invention; FIG. 4E is a mobile terminal including a feature value determining module according to the present invention; Schematic diagram of a structural embodiment;
图 4F 为本发明包括第一删除模块和 /或第二删除模块的移动终端的结 构实施例的示意图。 具体实施方式 为了解决现有技术存在的问题, 本发明实施例提供了移动终端的词库 添加方法和移动终端。 本发明实施例提供的技术方案采用的是语音添加的 方式,即确定接收到的语音信息中的自造词汇(即不存在于词库中的词汇), 将自造词汇添加到词库中, 这种语音添加的方式不仅普遍适用于各种用户 和移动终端, 而且使得词库的添加过程更加灵活方便。  4F is a schematic diagram of a structural embodiment of a mobile terminal including a first deletion module and/or a second deletion module according to the present invention. DETAILED DESCRIPTION OF THE INVENTION In order to solve the problems existing in the prior art, embodiments of the present invention provide a vocabulary adding method and a mobile terminal for a mobile terminal. The technical solution provided by the embodiment of the present invention adopts a voice adding manner, that is, determining a self-created vocabulary (ie, a vocabulary that does not exist in the vocabulary) in the received voice information, and adding the self-created vocabulary to the vocabulary. This way of adding voice is not only universally applicable to various users and mobile terminals, but also makes the process of adding the thesaurus more flexible and convenient.
如图 1 所示, 本发明实施例提供的移动终端的词库添加方法包括如下 步骤:  As shown in FIG. 1, the method for adding a thesaurus of a mobile terminal according to an embodiment of the present invention includes the following steps:
步骤 101 : 接收输入的语音信息并将其緩存。  Step 101: Receive the input voice information and cache it.
其中,语音信息可以是通话信息(如语音通话信息或者视频通话信息 ), 也可以是用户按照自己的意愿自主控制输入的语音信息(比如用户想将 "胜 利" 添加到词库中, 则用户可以自主控制地向移动终端输入 "胜利" 这一 语音信息)。 如果是用户按照自己的意愿自主控制输入的语音信息, 则移动 终端在执行步骤 101之前, 还应接收用户输入的开始指令, 即当用户想向 词库中添加词汇时, 用户便可以向移动终端输入开始指令, 指示移动终端 开始词汇添加过程。 The voice information may be call information (such as voice call information or video call information), or the user may control the input voice information according to his or her own will (for example, if the user wants to add "victory" to the thesaurus, the user may The voice information of "victory" is input to the mobile terminal autonomously. If the user autonomously controls the input voice information as he wishes, then move Before executing step 101, the terminal should also receive a start instruction input by the user, that is, when the user wants to add a vocabulary to the vocabulary, the user can input a start instruction to the mobile terminal to instruct the mobile terminal to start the vocabulary adding process.
步骤 102: 确定语音信息中的自造词汇。  Step 102: Determine a self-created vocabulary in the voice information.
当语音信息是通话信息时, 步骤 102进一步包括如下步骤:  When the voice information is call information, step 102 further includes the following steps:
Al、 识别通话信息中的词汇;  Al, identifying the vocabulary in the call information;
A2、 在上述词汇中确定自造词汇。  A2. Determine the self-made vocabulary in the above vocabulary.
步骤 103: 输出判断自造词汇是否正确的提示信息至显示器。  Step 103: Output a prompt message for determining whether the self-created vocabulary is correct to the display.
由于语言中常出现不同的词汇具有相同的拼音, 比如 "白露" 和 "白 鹭", 因此, 需要用户判断自造词汇是否是用户在语音信息中提到的词汇, 这样可以保证词汇添加的准确性。  Since different words in the language often have the same pinyin, such as "Bailu" and "White Heron", it is necessary for the user to judge whether the self-created vocabulary is the vocabulary mentioned by the user in the voice information, so as to ensure the accuracy of vocabulary addition.
当语音信息是通话信息时, 执行步骤 103之前还包括监控到满足添加 触发条件的步骤。  When the voice information is the call information, before step 103 is performed, the step of monitoring the addition of the trigger condition is also monitored.
其中, 添加触发条件可以是当前时间达到预置时间、 自造词汇的出现 次数达到预设门限值或者接收到添加指令等。  The triggering condition may be that the current time reaches the preset time, the number of occurrences of the self-created vocabulary reaches the preset threshold, or an add instruction is received.
当添加触发条件是当前时间达到预置时间时, 预置时间可以由用户设 置, 可以是每隔 3小时、 中午 12点或者下午 6点等。  When the trigger condition is added, when the current time reaches the preset time, the preset time can be set by the user, which can be every 3 hours, 12 noon or 6 pm.
当添加触发条件是自造词汇的出现次数达到预设门限值时, 预设门限 值可以由用户设置, 可以是 3次、 5次、 10次等。 并且, 当添加触发条件 是自造词汇的出现次数达到预设门限值时, 在执行步骤 A1之后, 还应执行 统计通话信息中的词汇的出现次数的步骤。  When the trigger condition is that the number of occurrences of the self-created vocabulary reaches the preset threshold, the preset threshold value may be set by the user, and may be 3 times, 5 times, 10 times, and the like. Moreover, when the trigger condition is that the number of occurrences of the self-created vocabulary reaches the preset threshold, after the step A1 is performed, the step of counting the number of occurrences of the vocabulary in the call information should also be performed.
当添加触发条件是接收到添加指令时, 添加指令是指用户通过触发移 动终端上的特定按键或者通过触摸笔或手指触发触摸屏移动终端而生成 的、 指示移动终端开始执行添加词汇操作的指令。  When the addition trigger condition is that an add instruction is received, the add instruction refers to an instruction generated by the user by triggering a specific button on the mobile terminal or by triggering the touch screen mobile terminal by a touch pen or a finger, instructing the mobile terminal to start performing the add vocabulary operation.
步骤 104: 接收判断结果, 当自造词汇正确时, 执行步骤 105; 当自造 词汇不正确时, 执行步骤 106。 Step 104: Receive the judgment result, when the self-created vocabulary is correct, perform step 105; If the vocabulary is incorrect, go to step 106.
用户可以通过触发移动终端上的特定按键或者通过触摸笔或手指触发 触摸屏移动终端来向移动终端输入判断结果。  The user can input a judgment result to the mobile terminal by triggering a specific button on the mobile terminal or triggering the touch screen mobile terminal by a touch pen or a finger.
步骤 105: 当自造词汇正确时,将自造词汇存储至词库中。结束本流程。 步骤 106: 当自造词汇不正确时, 接收输入的词汇, 并将输入的词汇存 储至词库中。 也就是说, 当自造词汇不正确时, 用户可以通过编辑向移动 终端输入正确的词汇, 这样可以避免无法将某些自造词汇添加到词库的情 况发生。  Step 105: Store the self-created vocabulary into the thesaurus when the self-created vocabulary is correct. End this process. Step 106: When the self-created vocabulary is incorrect, the input vocabulary is received, and the input vocabulary is stored in the thesaurus. That is to say, when the self-created vocabulary is incorrect, the user can input the correct vocabulary to the mobile terminal through editing, so that the situation that some self-created vocabulary cannot be added to the lexicon can be avoided.
在将自造词汇添加进词库中后, 移动终端还可以确定自造词汇的语音 特征值, 并将语音特征值对应自造词汇后存储至词库中。  After the self-created vocabulary is added into the vocabulary, the mobile terminal can also determine the voice feature value of the self-created vocabulary, and store the voice feature value corresponding to the self-created vocabulary and store it in the lexicon.
其中, 确定自造词汇的语音特征值的方法包括: 在语音识别及人工智 能等领域可能使用的、 将用户的语音抽象成特征的特征提取方法。 语音特 征值可以是自造词汇的筒拼或者其它形式的特征值, 比如 "胜利" 的语音 特征值为 "shl"。 将语音特征值对应自造词汇后存储至词库中的好处是:当 用户要使用词库中的词汇时, 只要向移动终端输入对应的语音特征值, 移 动终端就可以在显示器上输出对应的词汇以供用户使用, 使用户可以更加 方便的使用词库。  The method for determining the voice feature value of the self-created vocabulary includes: a feature extraction method that may be used to abstract the user's voice into features in the fields of speech recognition and artificial intelligence. The phonetic feature value can be a self-created vocabulary or other form of feature value, such as the "victory" voice feature value is "shl". The advantage of storing the voice feature value corresponding to the self-created vocabulary and storing it in the thesaurus is that when the user wants to use the vocabulary in the thesaurus, the mobile terminal can output the corresponding corresponding voice feature value on the display terminal. The vocabulary is available to the user, making it easier for users to use the thesaurus.
另外, 将自造词汇存储至词库中之后, 上述词库添加方法还包括: 接收删除非常用自造词汇的指令, 并将非常用自造词汇从词库中删除; 和 /或分别统计词库中各自造词汇在预设时间段内的使用次数, 并将使用次 数低于预设门限次数的自造词汇从词库中删除。  In addition, after storing the self-created vocabulary into the thesaurus, the above-mentioned thesaurus adding method further includes: receiving an instruction for deleting the self-created vocabulary, and deleting the self-created vocabulary from the vocabulary; and/or separately counting the vocabulary The number of times the vocabulary in the library is used within a preset time period, and the self-created vocabulary that is used less than the preset threshold number is deleted from the thesaurus.
其中, 预设时间段可以由用户设置, 包括但不限于 1个月、 3个月等; 预设门限次数也可以由用户设置, 包括但不限于 20次、 50次、 100次等值。 删除自造词汇的好处是, 当词库中的自造词汇很多时, 删除少量不常用的 自造词汇会释放移动终端的一部分系统资源。 本发明实施例提供的上述词库添加方法采用的是语音添加的方式, 即 识别接收到的语音信息中的词汇, 并将识别出的词汇添加到词库中, 这种 语音添加的方式不仅普遍适用于各种用户和移动终端, 而且使得词库的添 加过程更加灵活方便。 The preset time period can be set by the user, including but not limited to 1 month, 3 months, etc.; the preset threshold number can also be set by the user, including but not limited to 20 times, 50 times, 100 times. The advantage of deleting self-created vocabulary is that when there are many self-created vocabularies in the thesaurus, deleting a small number of uncommon self-created words will release part of the system resources of the mobile terminal. The above-mentioned thesaurus adding method provided by the embodiment of the present invention adopts a voice adding manner, that is, identifying a vocabulary in the received voice information, and adding the recognized vocabulary to the vocabulary, the manner of adding the voice is not only universal It is suitable for a variety of users and mobile terminals, and makes the process of adding the thesaurus more flexible and convenient.
下面以两个具体实施例来说明本发明实施例技术方案。  The technical solutions of the embodiments of the present invention are described in the following two specific embodiments.
具体实施例一  Specific embodiment 1
本发明具体实施例一以语音信息为通话信息为例, 如图 2所示, 本发 明具体实施例一包括如下步骤:  In the specific embodiment of the present invention, the voice information is used as the call information. As shown in FIG. 2, the specific embodiment 1 of the present invention includes the following steps:
步骤 201 : 接收输入的通话信息并将其緩存。 其中, 通话信息可以是语 音通话信息、 视频通话信息等。  Step 201: Receive the input call information and cache it. The call information may be voice call information, video call information, and the like.
步骤 202: 识别通话信息中的词汇。  Step 202: Identify the vocabulary in the call information.
步骤 203: 在上述词汇中确定自造词汇。  Step 203: Determine the self-created vocabulary in the above vocabulary.
步骤 204: 监控到满足添加触发条件时, 输出判断自造词汇是否正确的 提示信息至显示器。  Step 204: When it is monitored that the added trigger condition is met, output a prompt message for determining whether the self-created vocabulary is correct to the display.
其中, 添加触发条件可以是当前时间达到预置时间、 自造词汇的出现 次数达到预设门限值或者接收到添加指令等。  The triggering condition may be that the current time reaches the preset time, the number of occurrences of the self-created vocabulary reaches the preset threshold, or an add instruction is received.
当添加触发条件是自造词汇的出现次数达到预设门限值时, 在执行步 骤 202之后, 还应执行统计通话信息中的词汇的出现次数的步骤。  When the trigger condition is that the number of occurrences of the self-created vocabulary reaches the preset threshold, after the step 202 is performed, the step of counting the number of occurrences of the vocabulary in the call information should also be performed.
步骤 205: 接收判断结果, 当自造词汇正确时, 执行步骤 206; 当自造 词汇不正确时, 执行步骤 207。  Step 205: Receive the judgment result, when the self-created vocabulary is correct, perform step 206; when the self-created vocabulary is incorrect, perform step 207.
步骤 206: 当自造词汇正确时,将自造词汇存储至词库中。结束本流程。 步骤 207: 当自造词汇不正确时, 接收输入的词汇, 并将输入的词汇存 储至词库中。  Step 206: Store the self-created vocabulary into the thesaurus when the self-created vocabulary is correct. End this process. Step 207: When the self-created vocabulary is incorrect, the input vocabulary is received, and the input vocabulary is stored in the thesaurus.
在将自造词汇添加进词库中后, 移动终端还可以确定自造词汇的语音 特征值, 并将语音特征值对应自造词汇后存储至词库中。 并且, 将自造词汇存储至词库中之后, 移动终端还可以接收删除非常 用自造词汇的指令, 并将非常用自造词汇从词库中删除; 和 /或分别统计词 库中各自造词汇在预设时间段内的使用次数, 并将使用次数低于预设门限 次数的自造词汇从词库中删除。 After the self-created vocabulary is added into the thesaurus, the mobile terminal can also determine the voice feature values of the self-created vocabulary, and store the voice feature values corresponding to the self-created vocabulary and store them in the thesaurus. Moreover, after storing the self-created vocabulary into the thesaurus, the mobile terminal can also receive the instruction to delete the self-created vocabulary, and delete the self-created vocabulary from the vocabulary; and/or separately calculate the respective vocabulary The number of times the vocabulary is used within a preset time period, and the self-created vocabulary that is used less than the preset threshold number is deleted from the thesaurus.
本发明具体实施例一中, 移动终端将从通话信息中获取自造词汇, 将 自造词汇添加到词库中, 这种语音添加的方式非常灵活方便, 只要用户在 通话信息中提到自造词汇, 移动终端就可以将其添加到词库中, 不需要用 户花费时间和精力, 词库的添加过程更加灵活方便, 大大提高了词库添加 的效率, 普遍适用于各种用户和移动终端。  In a specific embodiment 1 of the present invention, the mobile terminal obtains a self-created vocabulary from the call information, and adds the self-created vocabulary to the vocabulary. The manner of adding the voice is very flexible and convenient, as long as the user mentions self-created in the call information. Vocabulary, the mobile terminal can add it to the thesaurus, without the user spending time and effort, the process of adding the thesaurus is more flexible and convenient, greatly improving the efficiency of the addition of the thesaurus, and is generally applicable to various users and mobile terminals.
具体实施例二  Specific embodiment 2
本发明具体实施例二以语音信息为用户按照自己的意愿自主控制输入 的语音信息为例, 如图 3所示, 本发明具体实施例二包括如下步骤:  In the second embodiment of the present invention, the voice information is used as an example for the user to control the input voice information according to the user's will. As shown in FIG. 3, the second embodiment of the present invention includes the following steps:
步骤 301 : 接收开始指令。 其中, 用户可以通过触发移动终端上的一个 按键来向移动终端输入开始指令。 由此可见, 该词库添加方法是由用户自 主控制的, 当用户想向词库中添加词汇时, 用户便可以向移动终端输入开 始指令, 开始词汇添加过程。  Step 301: Receive a start instruction. The user can input a start command to the mobile terminal by triggering a button on the mobile terminal. It can be seen that the vocabulary addition method is controlled by the user. When the user wants to add vocabulary to the vocabulary, the user can input a start instruction to the mobile terminal to start the vocabulary adding process.
步骤 302: 接收输入的语音信息并将其緩存。  Step 302: Receive the input voice information and cache it.
具体地, 移动终端可以提示用户输入语音信息, 用户看到提示信息后, 便可以向移动终端输入语音信息。  Specifically, the mobile terminal may prompt the user to input voice information, and after the user sees the prompt information, the voice information may be input to the mobile terminal.
步骤 303: 确定语音信息中的自造词汇。  Step 303: Determine a self-created vocabulary in the voice information.
步骤 304: 输出判断上述自造词汇是否正确的提示信息至显示器。  Step 304: Output prompt information for determining whether the self-created vocabulary is correct to the display.
步骤 305: 接收判断结果, 当上述自造词汇正确时, 执行步骤 306; 当 上述自造词汇不正确时, 执行步骤 307。  Step 305: Receive the judgment result. When the self-created vocabulary is correct, go to step 306; when the self-created vocabulary is incorrect, go to step 307.
步骤 306: 当上述词汇自造正确时, 将上述自造词汇存储至词库中。 结 束本流程。 步骤 307: 当上述自造词汇不正确时, 接收输入的词汇, 并将输入的词 汇存储至词库中。 Step 306: When the above vocabulary is self-created, the self-created vocabulary is stored in the thesaurus. End this process. Step 307: When the self-created vocabulary is incorrect, the input vocabulary is received, and the input vocabulary is stored in the thesaurus.
在将自造词汇添加进词库中后, 移动终端还可以确定自造词汇的语音 特征值, 并将语音特征值对应自造词汇后存储至词库中。  After the self-created vocabulary is added into the vocabulary, the mobile terminal can also determine the voice feature value of the self-created vocabulary, and store the voice feature value corresponding to the self-created vocabulary and store it in the lexicon.
并且, 将自造词汇存储至词库中之后, 移动终端还可以接收删除非常 用自造词汇的指令, 并将非常用自造词汇从词库中删除; 和 /或分别统计词 库中各自造词汇在预设时间段内的使用次数, 并将使用次数低于预设门限 次数的自造词汇从词库中删除。  Moreover, after storing the self-created vocabulary into the thesaurus, the mobile terminal can also receive the instruction to delete the self-created vocabulary, and delete the self-created vocabulary from the vocabulary; and/or separately calculate the respective vocabulary The number of times the vocabulary is used within a preset time period, and the self-created vocabulary that is used less than the preset threshold number is deleted from the thesaurus.
本发明实施例提供的上述词库添加方法采用的是语音添加的方式, 即 识别接收到的语音信息中的词汇, 并将识别出的词汇添加到词库中, 这种 语音添加的方式不仅普遍适用于各种用户和移动终端, 而且使得词库的添 加过程更加灵活方便。  The above-mentioned thesaurus adding method provided by the embodiment of the present invention adopts a voice adding manner, that is, identifying a vocabulary in the received voice information, and adding the recognized vocabulary to the vocabulary, the manner of adding the voice is not only universal It is suitable for a variety of users and mobile terminals, and makes the process of adding the thesaurus more flexible and convenient.
本发明具体实施例二中, 用户可以按照自己的意愿自主控制向词库中 添加自造词汇, 这种语音添加的方式灵活方便, 普遍适用于各种用户和移 动终端。  In the second embodiment of the present invention, the user can control the self-created vocabulary into the vocabulary according to his/her own will, and the voice adding method is flexible and convenient, and is generally applicable to various users and mobile terminals.
如图 4A所示, 本发明实施例提供了一种移动终端, 包括:  As shown in FIG. 4A, an embodiment of the present invention provides a mobile terminal, including:
语音接收模块 401 , 用于接收输入的语音信息并将其緩存;  a voice receiving module 401, configured to receive input voice information and cache it;
自造词汇确定模块 402, 用于确定语音信息中的自造词汇;  The self-created vocabulary determining module 402 is configured to determine a self-created vocabulary in the voice information;
输出模块 403 , 用于输出判断自造词汇是否正确的提示信息至显示器; 结果接收模块 404, 用于接收判断结果;  The output module 403 is configured to output prompt information for determining whether the self-created vocabulary is correct to the display; and the result receiving module 404 is configured to receive the determination result;
存储操作模块 405 , 用于当判断结果显示自造词汇正确时, 将自造词汇 存储至词库中。  The storage operation module 405 is configured to store the self-created vocabulary into the thesaurus when the judgment result shows that the self-created vocabulary is correct.
本发明实施例提供的上述移动终端, 采用语音输入的方式将词汇添加 到词库中, 其词库添加过程更加灵活方便, 且普遍适用于各种用户。  The mobile terminal provided by the embodiment of the present invention adds a vocabulary to the vocabulary by means of voice input, and the vocabulary adding process is more flexible and convenient, and is generally applicable to various users.
如图 4B所示, 自造词汇确定模块 402 , 进一步包括: 识别子模块 4021 , 用于当语音信息为通话信息时, 识别通话信息中的 词汇; As shown in FIG. 4B, the self-created vocabulary determining module 402 further includes: The identification submodule 4021 is configured to identify a vocabulary in the call information when the voice information is call information;
确定子模块 4022, 用于在词汇中确定自造词汇;  a determining sub-module 4022, configured to determine a self-created vocabulary in the vocabulary;
上述移动终端还包括:  The above mobile terminal further includes:
监控模块 411 , 用于监控是否满足添加触发条件, 添加触发条件为当前 时间达到预置时间、 所述自造词汇的出现次数达到预设门限值或者接收到 添加指令;  The monitoring module 411 is configured to monitor whether the trigger condition is added, the trigger condition is that the current time reaches the preset time, the number of occurrences of the self-created vocabulary reaches a preset threshold, or an add instruction is received;
输出模块 403 , 进一步包括:  The output module 403 further includes:
输出子模块 4031 , 用于当满足添加触发条件时, 输出判断自造词汇是 否正确的提示信息至显示器。  The output sub-module 4031 is configured to output, when the trigger condition is added, a prompt message for determining whether the self-created vocabulary is correct to the display.
如图 4C所示, 图 4B (或图 4A )所示的移动终端还包括:  As shown in FIG. 4C, the mobile terminal shown in FIG. 4B (or FIG. 4A) further includes:
统计模块 406, 用于统计自造词汇的出现次数, 并将出现次数发送给输 出模块 403。  The statistics module 406 is configured to count the number of occurrences of the self-created vocabulary, and send the number of occurrences to the output module 403.
如图 4D所示, 图 4A所示的移动终端还包括:  As shown in FIG. 4D, the mobile terminal shown in FIG. 4A further includes:
指令接收模块 407,用于在语音接收模块 401接收输入的语音信息并将 其緩存之前, 接收开始指令。  The instruction receiving module 407 is configured to receive a start instruction before the voice receiving module 401 receives the input voice information and buffers it.
另外, 存储操作模块 405 , 还用于当自造词汇不正确时, 接收输入的词 汇, 并将输入的词汇存储至词库中。  In addition, the storage operation module 405 is further configured to receive the input vocabulary when the self-created vocabulary is incorrect, and store the input vocabulary into the thesaurus.
即当自造词汇不正确时, 用户可以通过编辑向移动终端输入正确的词 汇, 这样可以避免无法将某些自造词汇添加到词库的情况发生。  That is, when the self-created vocabulary is incorrect, the user can input the correct vocabulary to the mobile terminal through editing, so that it is avoided that some self-created vocabulary cannot be added to the lexicon.
如图 4E所示, 图 4A (或图 4B、 或图 4C、 或图 4D )所示的移动终端, 还包括:  As shown in FIG. 4E, the mobile terminal shown in FIG. 4A (or FIG. 4B, or FIG. 4C, or FIG. 4D) further includes:
特征值确定模块 408 , 用于确定自造词汇的语音特征值;  The feature value determining module 408 is configured to determine a voice feature value of the self-created vocabulary;
此时,存储操作模块 405 ,还用于将语音特征值对应自造词汇后存储至 词库中。 如图 4F所示, 图 4A (或图 4B、 或图 4C、 或图 4D、 或图 4E )所示的 移动终端, 还包括: At this time, the storage operation module 405 is further configured to store the voice feature value into the vocabulary corresponding to the self-created vocabulary. As shown in FIG. 4F, the mobile terminal shown in FIG. 4A (or FIG. 4B, or FIG. 4C, or FIG. 4D, or FIG. 4E) further includes:
第一删除模块 409, 用于接收删除非常用自造词汇的指令, 并将非常用 自造词汇从词库中删除; 和 /或  a first deletion module 409, configured to receive an instruction for deleting a very self-created vocabulary, and deleting the self-created vocabulary from the vocabulary; and/or
第二删除模块 410,用于分别统计词库中各自造词汇在预设时间段内的 使用次数, 并将使用次数低于预设门限次数的自造词汇从词库中删除。  The second deleting module 410 is configured to separately count the number of times the respective vocabulary in the vocabulary is used within a preset time period, and delete the self-created vocabulary whose usage times are less than the preset threshold number from the vocabulary.
以上所述是本发明的优选实施方式, 应当指出, 对于本技术领域的普 通技术人员来说, 在不脱离本发明所述原理的前提下, 还可以做出若干改 进和润饰, 这些改进和润饰也应视为本发明的保护范围。  The above is a preferred embodiment of the present invention, and it should be noted that those skilled in the art can make several improvements and retouchings without departing from the principles of the present invention. It should also be considered as the scope of protection of the present invention.

Claims

权利要求书 Claim
1、 一种移动终端的词库添加方法, 其特征在于, 包括:  A method for adding a thesaurus of a mobile terminal, comprising:
接收输入的语音信息并将其緩存;  Receiving input voice information and buffering it;
确定所述语音信息中的自造词汇;  Determining a self-created vocabulary in the voice information;
输出判断所述自造词汇是否正确的提示信息至显示器;  Outputting prompt information for determining whether the self-created vocabulary is correct to the display;
接收判断结果, 并当所述自造词汇正确时, 将所述自造词汇存储至所 述词库中。  Receiving the judgment result, and storing the self-created vocabulary into the thesaurus when the self-created vocabulary is correct.
2、 根据权利要求 1所述的词库添加方法, 其特征在于, 所述接收输入 的语音信息并将其緩存之前, 还包括: 接收开始指令。  2. The vocabulary adding method according to claim 1, wherein the receiving the input voice information and buffering the same further comprises: receiving a start instruction.
3、 根据权利要求 1所述的词库添加方法, 其特征在于, 当所述语音信 息为通话信息时, 所述确定所述语音信息中的自造词汇具体为:  The vocabulary adding method according to claim 1, wherein when the voice information is call information, determining the self-created vocabulary in the voice information is:
识别所述通话信息中的词汇;  Identifying words in the call information;
在所述词汇中确定自造词汇;  Determining a self-made vocabulary in the voca
所述输出判断所述自造词汇是否正确的提示信息至显示器之前, 该方 法还包括: 监控到满足添加触发条件; 所述添加触发条件为当前时间达到 预置时间、 所述自造词汇的出现次数达到预设门限值或者接收到添加指令。  Before the outputting the information indicating whether the self-created vocabulary is correct to the display, the method further includes: monitoring to meet the added trigger condition; the adding the trigger condition is that the current time reaches the preset time, and the self-created vocabulary appears The number of times reaches the preset threshold or receives an add command.
4、 根据权利要求 3所述的词库添加方法, 其特征在于, 当所述添加触 发条件为所述自造词汇的出现次数达到预设门限值时,  The method for adding a thesaurus according to claim 3, wherein, when the adding trigger condition is that the number of occurrences of the self-created vocabulary reaches a preset threshold value,
所述识别所述通话信息中的词汇之后还包括:  After the vocabulary in the call information is identified, the method further includes:
统计所述词汇的出现次数。  Count the number of occurrences of the vocabulary.
5、根据权利要求 1所述的词库添加方法,其特征在于,该方法还包括: 当所述自造词汇不正确时, 接收输入的词汇, 并将所述输入的词汇存 储至所述词库中。  The method of adding a thesaurus according to claim 1, wherein the method further comprises: receiving the input vocabulary when the self-created vocabulary is incorrect, and storing the input vocabulary to the word In the library.
6、 根据权利要求 1-5中任一所述的词库添加方法, 其特征在于, 所述 将所述自造词汇存储至所述词库中之后还包括: 确定所述自造词汇的语音特征值; The method for adding a thesaurus according to any one of claims 1 to 5, wherein the storing the self-created vocabulary into the thesaurus further comprises: Determining a voice feature value of the self-created vocabulary;
将所述语音特征值对应所述自造词汇后存储至所述词库中。  And storing the voice feature value in the thesaurus after the self-created vocabulary is stored.
7、 根据权利要求 1-5中任一所述的词库添加方法, 其特征在于, 该方 法还包括:  7. The method of adding a thesaurus according to any one of claims 1 to 5, wherein the method further comprises:
接收删除非常用自造词汇的指令, 并将所述非常用自造词汇从所述词 库中删除; 和 /或,  Receiving an instruction to delete a self-created vocabulary and deleting the very self-created vocabulary from the vocabulary; and/or,
分别统计所述词库中各自造词汇在预设时间段内的使用次数, 并将使 用次数低于预设门限次数的自造词汇从所述词库中删除。  The number of uses of the respective vocabulary in the vocabulary in the preset time period is separately counted, and the self-created vocabulary whose usage times is less than the preset threshold number is deleted from the vocabulary.
8、 一种移动终端, 其特征在于, 至少包括:  8. A mobile terminal, comprising: at least:
语音接收模块, 用于接收输入的语音信息并将其緩存;  a voice receiving module, configured to receive the input voice information and cache the same;
自造词汇确定模块, 用于确定所述语音信息中的自造词汇;  a self-created vocabulary determining module, configured to determine a self-created vocabulary in the voice information;
输出模块, 用于输出判断所述自造词汇是否正确的提示信息至显示器; 结果接收模块, 用于接收判断结果;  An output module, configured to output prompt information for determining whether the self-created vocabulary is correct to the display; and a result receiving module, configured to receive the determination result;
存储操作模块, 用于当所述判断结果显示所述自造词汇正确时, 将所 述自造词汇存储至词库中。  And a storage operation module, configured to store the self-created vocabulary into the thesaurus when the judgment result indicates that the self-created vocabulary is correct.
9、 根据权利要求 8所述的移动终端, 其特征在于, 还包括:  The mobile terminal according to claim 8, further comprising:
指令接收模块, 用于在所述语音接收模块接收输入的语音信息并将其 緩存之前, 接收开始指令。  The instruction receiving module is configured to receive a start instruction before the voice receiving module receives the input voice information and buffers the voice information.
10、 根据权利要求 8所述的移动终端, 其特征在于,  10. The mobile terminal of claim 8, wherein
所述自造词汇确定模块, 进一步包括:  The self-made vocabulary determining module further includes:
识别子模块, 用于当所述语音信息为通话信息时, 识别所述通话信息 中的词汇;  An identification submodule, configured to identify a vocabulary in the call information when the voice information is call information;
确定子模块, 用于在所述词汇中确定自造词汇;  Determining a sub-module for determining a self-made vocabulary in the vocabulary;
所述移动终端还包括:  The mobile terminal further includes:
监控模块, 用于监控是否满足所述添加触发条件, 所述添加触发条件 为当前时间达到预置时间、 所述自造词汇的出现次数达到预设门限值或者 接收到添加指令; a monitoring module, configured to monitor whether the added trigger condition is met, and the adding trigger condition The preset time is reached for the current time, the number of occurrences of the self-created vocabulary reaches a preset threshold, or an add instruction is received;
所述输出模块, 进一步包括:  The output module further includes:
输出子模块, 用于当满足所述添加触发条件时, 输出判断所述自造词 汇是否正确的提示信息至显示器。  And an output submodule, configured to output, when the trigger condition is satisfied, a prompt message for determining whether the self-created vocabulary is correct to the display.
11、 根据权利要求 8所述的移动终端, 其特征在于, 所述移动终端还 包括:  The mobile terminal according to claim 8, wherein the mobile terminal further comprises:
统计模块, 用于统计所述自造词汇的出现次数, 并将所述出现次数发 送给所述输出模块。  And a statistics module, configured to count the number of occurrences of the self-created vocabulary, and send the number of occurrences to the output module.
12、 根据权利要求 8所述的移动终端, 其特征在于,  12. The mobile terminal of claim 8, wherein
所述存储操作模块, 还用于当所述自造词汇不正确时, 接收输入的词 汇, 并将所述输入的词汇存储至所述词库中。  The storage operation module is further configured to: when the self-created vocabulary is incorrect, receive the input vocabulary, and store the input vocabulary into the thesaurus.
13、 根据权利要求 8-12中任一所述的移动终端, 其特征在于, 所述移 动终端还包括:  The mobile terminal according to any one of claims 8 to 12, wherein the mobile terminal further comprises:
特征值确定模块, 用于确定所述自造词汇的语音特征值;  An eigenvalue determining module, configured to determine a voice feature value of the self-created vocabulary;
所述存储操作模块, 还用于将所述语音特征值对应所述自造词汇后存 储至所述词库中。  The storage operation module is further configured to store the voice feature value in the thesaurus after the self-created vocabulary is stored.
14、 根据权利要求 8-12中任一所述的移动终端, 其特征在于, 所述移 动终端还包括:  The mobile terminal according to any one of claims 8 to 12, wherein the mobile terminal further comprises:
第一删除模块, 用于接收删除非常用自造词汇的指令, 并将所述非常 用自造词汇从所述词库中删除; 和 /或,  a first deleting module, configured to receive an instruction for deleting a very self-created vocabulary, and deleting the very self-created vocabulary from the thesaurus; and/or,
第二删除模块, 用于分别统计所述词库中各自造词汇在预设时间段内 的使用次数, 并将使用次数低于预设门限次数的自造词汇从所述词库中删 除。  The second deleting module is configured to separately count the number of times the respective vocabulary in the vocabulary is used within a preset time period, and delete the self-created vocabulary whose usage number is lower than the preset threshold number from the vocabulary.
PCT/CN2010/072204 2009-12-21 2010-04-26 Method for adding word stock of mobile terminal and mobile terminal WO2011075972A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN200910258778A CN101739459A (en) 2009-12-21 2009-12-21 Method for adding word bank of mobile terminal and mobile terminal
CN200910258778.1 2009-12-21

Publications (1)

Publication Number Publication Date
WO2011075972A1 true WO2011075972A1 (en) 2011-06-30

Family

ID=42462942

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2010/072204 WO2011075972A1 (en) 2009-12-21 2010-04-26 Method for adding word stock of mobile terminal and mobile terminal

Country Status (2)

Country Link
CN (1) CN101739459A (en)
WO (1) WO2011075972A1 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102298644A (en) * 2011-09-20 2011-12-28 宇龙计算机通信科技(深圳)有限公司 Filter method and system for self-created word and mobile terminal
CN105760084B (en) * 2016-01-25 2019-01-25 百度在线网络技术(北京)有限公司 The control method and device of voice input
CN107305769B (en) * 2016-04-20 2020-06-23 斑马网络技术有限公司 Voice interaction processing method, device, equipment and operating system
CN106873956B (en) * 2016-06-17 2020-09-11 阿里巴巴集团控股有限公司 Code completion method and device based on continuous keywords
CN107610695B (en) * 2017-08-08 2021-07-06 大众问问(北京)信息科技有限公司 Dynamic adjustment method for driver voice awakening instruction word weight

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1399191A (en) * 2002-09-09 2003-02-26 北京南山高科技有限公司 Processing method for Chinese phonetic recognition word library
CN1604187A (en) * 1997-04-10 2005-04-06 微软公司 Extensible speech recognition system that provides user audio feedback
CN1815557A (en) * 2005-02-04 2006-08-09 台达电子工业股份有限公司 Method and device for configuring Chinese new words utilizing voice input

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1604187A (en) * 1997-04-10 2005-04-06 微软公司 Extensible speech recognition system that provides user audio feedback
CN1399191A (en) * 2002-09-09 2003-02-26 北京南山高科技有限公司 Processing method for Chinese phonetic recognition word library
CN1815557A (en) * 2005-02-04 2006-08-09 台达电子工业股份有限公司 Method and device for configuring Chinese new words utilizing voice input

Also Published As

Publication number Publication date
CN101739459A (en) 2010-06-16

Similar Documents

Publication Publication Date Title
JP6811758B2 (en) Voice interaction methods, devices, devices and storage media
EP2291987B1 (en) Method and device for launching an application upon speech recognition during a communication
JP6415554B2 (en) Nuisance telephone number determination method, apparatus and system
US8413050B2 (en) Information entry mechanism for small keypads
EP2864980B1 (en) Mixed model speech recognition
CN103841268A (en) Information processing method and information processing device
EP2677518A2 (en) Method for providing voice recognition function and electronic device thereof
US20180013718A1 (en) Account adding method, terminal, server, and computer storage medium
JP7166294B2 (en) Audio processing method, device and storage medium
JP2011150682A (en) Multi-dimensional disambiguation of voice command
WO2011075972A1 (en) Method for adding word stock of mobile terminal and mobile terminal
KR101962774B1 (en) Method and apparatus for processing new messages associated with an application
KR20130068303A (en) Apparatus for performing voice command, mobile terminal having the same and method for performing voice command
CN107424612B (en) Processing method, apparatus and machine-readable medium
KR101584887B1 (en) Method and system of supporting multitasking of speech recognition service in in communication device
CN104301486A (en) Electronic equipment and conversation control method
KR101520896B1 (en) Apparatus and method for managing data in portable terminal
CN106453910A (en) Call communication recording method and device
CN110062276A (en) Processing method, device and the electronic equipment and storage medium of audio, video data
KR101643808B1 (en) Method and system of providing voice service using interoperation between application and server
JP6814604B2 (en) Meeting information display system, meeting information display method and meeting information display program
WO2014180362A1 (en) Terminal and method thereof for managing multimedia notepad
WO2020051881A1 (en) Information prompt method and related product
CN112988956A (en) Method and device for automatically generating conversation and method and device for detecting information recommendation effect
CN109360570A (en) Audio recognition method, speech ciphering equipment and the readable storage medium storing program for executing of speech ciphering equipment

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 10838538

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 10838538

Country of ref document: EP

Kind code of ref document: A1