WO2013189342A2 - Information processing method and mobile terminal - Google Patents

Information processing method and mobile terminal Download PDF

Info

Publication number
WO2013189342A2
WO2013189342A2 PCT/CN2013/081612 CN2013081612W WO2013189342A2 WO 2013189342 A2 WO2013189342 A2 WO 2013189342A2 CN 2013081612 W CN2013081612 W CN 2013081612W WO 2013189342 A2 WO2013189342 A2 WO 2013189342A2
Authority
WO
WIPO (PCT)
Prior art keywords
lattice
representation
text information
lattice representation
mobile terminal
Prior art date
Application number
PCT/CN2013/081612
Other languages
French (fr)
Chinese (zh)
Other versions
WO2013189342A3 (en
Inventor
刘伟
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 WO2013189342A2 publication Critical patent/WO2013189342A2/en
Publication of WO2013189342A3 publication Critical patent/WO2013189342A3/en

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/1822—Parsing for meaning understanding
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Definitions

  • the present invention relates to the field of mobile communications, and in particular, to an information processing method and a mobile terminal.
  • the grammar method is characterized by the construction of analytic results centered on verbs. Although the grammar rules only describe the syntax, the structure resulting from the analysis corresponds to the semantic relationship rather than the strict syntactic relationship. For example, English sentences:
  • This representation structure is called a lattice representation.
  • the lattice representation the noun phrase and the prepositional phrase contained in a statement are represented by their relationship with the verb in the sentence, called the lattice.
  • Agent and Dative are both lattices
  • basic representations like "(Agent Mary)" are called lattice structures.
  • the lattice representation is easy to describe in semantic network representation, so that the lattice representations of multiple sentences are related to each other to form a large semantic network, in order to develop the relationship between sentences, understand the context of multiple sentences, and be used to answer questions.
  • the grammar method is very scalable, and some common grids can be listed:
  • Agent the main body of the action
  • 'Dative the object given by the action
  • .Locative the place where the event occurred
  • .Goal end point
  • destination the destination
  • the natural language grammar itself also has a concept of lattice.
  • lattice For example, in English, " ⁇ is the main grid, and "me” is the accusative, but it does not have a sound lattice definition like the grammar method, so that the sentence can be completely analyzed by the grid. Distinguish, the lattice in the natural language grammar is the grammar (or shallow), and the lattice defined in the grammar is the semantic lattice (or deep lattice).
  • the definition of the semantic lattice makes the analysis result of the statement - the lattice representation contains a large Semantic information, which becomes an effective semantic analysis method.
  • Lexical analysis is the process of converting a sequence of characters into a sequence of words in computer science.
  • a program or function that performs lexical analysis is called a lexical analyzer, also called a scanner.
  • the lexical analyzer typically exists as a function for the parser to call.
  • syntactic analysis is performed by a specially designed parser.
  • the result analyzer based on the lexical analyzer analyzes the input sentences by relying on the grammar (grammar) of natural language compliance, and transforms each legal sentence into an analysis tree.
  • the technical problem to be solved by the present invention is to provide an information processing method and a mobile terminal, and use the key techniques of syntactic analysis and semantic analysis of the grammar method to perform natural language understanding analysis in the field of mobile terminal tasks, so as to achieve The purpose of the mobile terminal to understand the user's manipulation intention.
  • the present invention provides an information processing method, including: after receiving voice information, converting the voice information into text information, analyzing the text information, and generating a lattice representation;
  • the lattice representation is matched with the lattice representation in the pre-stored knowledge base. If the matching is successful, the lattice representation is generated to generate a corresponding manipulation instruction.
  • the above method further has the following features: analyzing the text information, and generating a lattice representation includes:
  • the foregoing method further has the following features: the process of generating the lattice representation includes: converting the content corresponding to the central verb and/or the semantic grid into predetermined synonyms.
  • the foregoing method further has the following features: analyzing the text information includes: analyzing keywords in the text information, and establishing an application operation type corresponding to the keyword; Matching the lattice representation with the lattice representation in the pre-stored knowledge base includes: matching the lattice representation with a lattice representation of a pre-stored knowledge base of the same type as the application operation type.
  • the present invention further provides a mobile terminal, including:
  • the first module is configured to: after receiving the voice information, convert the voice information into text information, analyze the text information, and generate a grid representation;
  • the second module is configured to: match the lattice representation with the lattice representation in the pre-stored knowledge base, and if the matching is successful, the grid representation generates a corresponding manipulation instruction.
  • the mobile terminal further has the following features:
  • the first module includes:
  • the first unit is configured to: perform syntactic analysis on the text information, and mark the central verb and the semantic grid;
  • the second unit is configured to: fill the content of the text information into a corresponding semantic lattice, and generate a lattice representation.
  • the mobile terminal further has the following features:
  • the second unit is configured to: convert the content corresponding to the central verb and/or the semantics into a predetermined synonym in the process of generating the lattice representation.
  • the mobile terminal further has the following features: the first module includes
  • the third unit is configured to: analyze keywords in the statement information, and establish an application operation type corresponding to the keyword;
  • the second module is configured to: match the lattice representation with a lattice representation of a pre-stored knowledge base of the same type as the application operation type.
  • the embodiment of the invention provides an information processing method and a mobile terminal.
  • the mobile phone can convert a sentence spoken by a person into text information through a voice recognition technology, and combines the syntax analysis and semantic analysis of the sentence grammar statement.
  • the key technology is to conduct natural language understanding analysis in the field of mobile terminal tasks to achieve the purpose of letting the mobile terminal understand the user's manipulation intention.
  • FIG. 1 is a flowchart of an information processing method according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of a syntax tree after syntactic analysis according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram of a mobile terminal according to an embodiment of the present invention.
  • FIG. 1 is a flowchart of an information processing method according to an embodiment of the present invention. As shown in FIG. 1, the method in this embodiment includes the following steps:
  • the grammar method is very suitable for the use of the semantic analysis understanding stage in the field of mobile phone manipulation.
  • the central verb is the core action of the manipulation, and the semantic lattice in the sentence clarifies the relevant information needed for manipulation. If there is a core action and enough relevant information in one sentence It is possible to let the mobile phone understand the user's control intention and make corresponding actions according to the understood intention.
  • Step 101 After receiving the voice information, converting the voice information into text statement information, analyzing the keywords in the statement, and establishing related application topics to establish the user to manipulate the intention center content; for example, “phone” appears When “ , “ dialing " and other keywords , the sentence processing can be divided into operations such as telephone. Similarly, when "keywords" and other keywords appear, the processing of the sentence can be divided into short messages.
  • Step 102 Perform syntactic analysis on the statement, mark the central verb and the semantic lattice, whether through the analysis of the syntax tree or the matching of the sentence template, mark the central verb and the semantic lattice in the syntax analysis result, and the sentence in the sentence
  • the content is filled into the corresponding semantic lattice, and the lattice representation is generated, and the matching of the lattice representation is performed.
  • Fig. 2 there is a syntactic tree after syntactic analysis as shown in Fig. 2: The circle is circled in the figure to mark the node as a semantic lattice.
  • N-phone Object grid
  • Step 103 The synonym can be stipulated, and the central verb can be stipulated.
  • the content of the gram can also be stipulated, and the content corresponding to the central verb and/or the semantic genre is respectively converted into a predetermined synonym : to facilitate the matching of the knowledge base and improve The efficiency of semantic analysis.
  • the action of making a call can be attributed to dialing such an action, taking the result of step 102 as an example.
  • the intention of the sentence is a telephone class, so the synonym of "hit” can be converted into “call”, the same intention is Another sentence of the telephone class, the center verb, can also be converted to "dial” if it is "call”. Therefore, after processing, the grid representation is converted to:
  • the content can also be stipulated as needed.
  • Step 104 Matching the generated lattice representation with the lattice representation in the knowledge base according to the structure type represented by the lattice and the lattice representation of the same type. If the matching succeeds, the semantic analysis is successful, and the mobile phone can according to the lattice with the correct semantics. Indicates that the corresponding manipulation command is generated.
  • Step 103 The processed result is based on its structure in the knowledge base (central verb: dial [Contact: Zhang San] [Object: phone]) should be followed by (center verb: [Contact:] [Object]:)
  • the cell indicates that the match is made, and the following cell condition is found in the phone class:
  • step 103 Contrary to the phrase "Take Zhang to call the tiger", the results of step 103 are as follows: (Center verb: dial [Contact: Zhang San] [Object: Tiger]),
  • step 103 the results of step 103 are as follows: (Center verb: dial [Contact: computer] [Object: phone]),
  • the computer does not have a Contact semantic tag in the knowledge base, and the semantic analysis fails and ends.
  • FIG. 3 is a schematic diagram of a mobile terminal according to an embodiment of the present invention. As shown in FIG. 3, the mobile terminal of this embodiment includes:
  • a first module after receiving the voice information, converting the voice information into text information, analyzing the text information, and generating a grid representation
  • the second module is configured to match the lattice representation with the lattice representation in the pre-stored knowledge base. If the matching is successful, the grid representation generates a corresponding manipulation instruction.
  • the first module includes:
  • a first unit configured to perform syntax analysis on the text information, and mark a central verb and a semantic grid
  • a second unit is configured to fill the content of the text information into a corresponding semantic grid to generate a lattice representation.
  • the second unit is specifically configured to convert the content corresponding to the central verb and/or the semantic lattice into a predetermined synonym in the process of generating the lattice representation.
  • the first module includes
  • a third unit configured to analyze a keyword in the statement information, and establish an application operation type corresponding to the keyword
  • the second module is specifically configured to match the cell representation with a lattice representation of a pre-stored knowledge base of the same type as the application operation type.
  • An embodiment of the present invention provides an information processing method and a mobile terminal.
  • a mobile phone can convert a sentence spoken by a person into text information through a voice recognition technology, and syntactic analysis and semantics of the statement using the grammar method. Analyze the key technologies combined and conduct natural language understanding analysis in the field of mobile terminal tasks to achieve the purpose of letting the mobile terminal understand the user's control intention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Machine Translation (AREA)
  • Telephonic Communication Services (AREA)

Abstract

An information processing method and a mobile terminal. The method comprises: after voice information is received, converting the voice information to text information, and analyzing the text information to generate a lattice representation; and matching the lattice representation with a prestored lattice representation in a knowledge base, and if the matching is successful, enabling the lattice representation to generate a corresponding operation control instruction.In the voice application aspect, the abovementioned solution can convert a sentence which a person says to text information through voice recognition technology, and conduct natural language understanding and analysis in the field of mobile terminal tasks using a case grammar, i.e. the key technology of the combination of syntactic analysis and semantic analysis of a sentence, so as to achieve the purpose of enabling a mobile terminal to understand a user's operation control intention.

Description

一种信息处理方法和移动终端  Information processing method and mobile terminal
技术领域 Technical field
本发明涉及移动通讯领域， 特别是涉及一种信息处理方法和移动终端。  The present invention relates to the field of mobile communications, and in particular, to an information processing method and a mobile terminal.
背景技术 Background technique
格文法的特点是许以动词为中心构造分析结果， 尽管文法规则只描述句 法， 但分析结果产生的结构却相应于语义关系， 而非严格的句法关系。 例如 英语句子：  The grammar method is characterized by the construction of analytic results centered on verbs. Although the grammar rules only describe the syntax, the structure resulting from the analysis corresponds to the semantic relationship rather than the strict syntactic relationship. For example, English sentences:
Mary hit Bill.的格文法分析结果可表示为：  The result of the grammar analysis of Mary hit Bill. can be expressed as:
Hit (Agent Mary)( Dative Bill)  Hit (Agent Mary)( Dative Bill)
这种表示结构称为格表示。 在格表示中， 一个语句包含的名词词组和介 词词组均以它们与句子中动词的关系来表示， 称为格。 上例中的 Agent和 Dative均是格， 而像"（ Agent Mary) "这样的基本表示则称为格结构。 格表示 易于以语义网络表示法描述， 从而多个句子的格表示相互关联而形成大的语 义网络，以便开发句子间的关系，理解多句构成的上下文，并用于回答问题。 究竟要定义哪些格才合适， 目前并无一致的意见， 因此格文法的可扩展性很 强， 可以列举一些常见的格：  This representation structure is called a lattice representation. In the lattice representation, the noun phrase and the prepositional phrase contained in a statement are represented by their relationship with the verb in the sentence, called the lattice. In the above example, Agent and Dative are both lattices, and basic representations like "(Agent Mary)" are called lattice structures. The lattice representation is easy to describe in semantic network representation, so that the lattice representations of multiple sentences are related to each other to form a large semantic network, in order to develop the relationship between sentences, understand the context of multiple sentences, and be used to answer questions. There is no consensus on what kind of grid to define, so the grammar method is very scalable, and some common grids can be listed:
•Agent—动作主体， 'Dative—动作给与的对象，  • Agent—the main body of the action, 'Dative—the object given by the action,
.Locative—事件发生的地点， .Goal—终点， 目的地，  .Locative—the place where the event occurred, .Goal—end point, destination,
•Time—事件发生的地点， •Instrument—动作实施的工具或手段， •Time—the place where the event occurred, •Instrument—the tool or means of action implementation,
•Factitive-事件中主体使役的对象， .Source-物体移动的起点，•Factitive-the object of the subject in the event, .Source - the starting point of the object movement,
•Beneficiary—事件中的受益者， · Object—动作的施加对象。 • Beneficiary—the beneficiary of the event, • Object—the object to which the action is applied.
自然语言文法本身也有格概念，例如，英语中的 "Γ为主格， "me"为宾格， 但并不像格文法那样具有健全的格定义， 以至于可完全用格来分析句子。 为 了作区分， 称自然语言文法中的格为文法格（或浅格） ， 而格文法中定义的 格为语义格（或深格） 。 语义格的定义使语句的分析结果 -格表示包含了大 量语义信息， 从而成为有效的语义分析方法。 The natural language grammar itself also has a concept of lattice. For example, in English, "Γ is the main grid, and "me" is the accusative, but it does not have a sound lattice definition like the grammar method, so that the sentence can be completely analyzed by the grid. Distinguish, the lattice in the natural language grammar is the grammar (or shallow), and the lattice defined in the grammar is the semantic lattice (or deep lattice). The definition of the semantic lattice makes the analysis result of the statement - the lattice representation contains a large Semantic information, which becomes an effective semantic analysis method.
词法分析， 是计算机科学中将字符序列转换为单词序列的过程。 进行词 法分析的程序或者函数称为词法分析器， 也叫扫描器。 词法分析器一般以函 数的形式存在， 供语法分析器调用。  Lexical analysis is the process of converting a sequence of characters into a sequence of words in computer science. A program or function that performs lexical analysis is called a lexical analyzer, also called a scanner. The lexical analyzer typically exists as a function for the parser to call.
句法分析， 句法分析由专门设计的分析器进行， 基于词法分析器的结果 分析器依赖自然语言遵从的文法（语法）分析输入的句子， 并把每个合法句 转变为一颗分析树。  Syntactic analysis, syntactic analysis is performed by a specially designed parser. The result analyzer based on the lexical analyzer analyzes the input sentences by relying on the grammar (grammar) of natural language compliance, and transforms each legal sentence into an analysis tree.
目前， 普通的手机并不能够主动理解用户的操控意图。 发明内容  At present, ordinary mobile phones are not able to actively understand the user's intention to control. Summary of the invention
本发明要解决的技术问题是提供一种信息处理方法和移动终端， 用格文 法这一语句的句法分析和语义分析组合起来的关键技术， 进行移动终端任务 领域的自然语言理解分析， 以达到让移动终端理解用户的操控意图的目的。  The technical problem to be solved by the present invention is to provide an information processing method and a mobile terminal, and use the key techniques of syntactic analysis and semantic analysis of the grammar method to perform natural language understanding analysis in the field of mobile terminal tasks, so as to achieve The purpose of the mobile terminal to understand the user's manipulation intention.
为了解决上述技术问题， 本发明提供了一种信息处理方法， 包括： 接收到语音信息后， 将所述语音信息转换成文本信息， 对所述文本信息 进行分析， 生成格表示；  In order to solve the above technical problem, the present invention provides an information processing method, including: after receiving voice information, converting the voice information into text information, analyzing the text information, and generating a lattice representation;
将所述格表示与预存的知识库中的格表示进行匹配， 如匹配成功， 则将 所述格表示生成对应的操控指令。  The lattice representation is matched with the lattice representation in the pre-stored knowledge base. If the matching is successful, the lattice representation is generated to generate a corresponding manipulation instruction.
优选地， 上述方法还具有下面特点： 对所述文本信息进行分析， 生成格 表示包括：  Preferably, the above method further has the following features: analyzing the text information, and generating a lattice representation includes:
对所述文本信息进行句法分析， 标注出中心动词和语义格；  Syntactic analysis of the text information, marking the central verb and semantic grid;
将所述文本信息的中内容填充到对应的语义格中， 生成格表示。  Filling the content of the text information into a corresponding semantic grid to generate a lattice representation.
优选地， 上述方法还具有下面特点： 所述生成格表示的过程中包括： 将中心动词和 /或语义格对应的内容分别转化为预定的同义语。 优选地， 上述方法还具有下面特点： 对所述文本信息进行分析包括： 对所述文本信息中的关键词进行分析， 确立与所述关键词对应的应用操 作类型； 将所述格表示与预存的知识库中的格表示进行匹配， 包括： 将所述格表示与预存的知识库中与所述应用操作类型相同类型的格表示 进行匹配。 为了解决上述问题， 本发明还提供了一种移动终端， 包括： Preferably, the foregoing method further has the following features: the process of generating the lattice representation includes: converting the content corresponding to the central verb and/or the semantic grid into predetermined synonyms. Preferably, the foregoing method further has the following features: analyzing the text information includes: analyzing keywords in the text information, and establishing an application operation type corresponding to the keyword; Matching the lattice representation with the lattice representation in the pre-stored knowledge base includes: matching the lattice representation with a lattice representation of a pre-stored knowledge base of the same type as the application operation type. In order to solve the above problem, the present invention further provides a mobile terminal, including:
第一模块， 设置为： 接收到语音信息后， 将所述语音信息转换成文本信 息， 对所述文本信息进行分析， 生成格表示；  The first module is configured to: after receiving the voice information, convert the voice information into text information, analyze the text information, and generate a grid representation;
第二模块，设置为：将所述格表示与预存的知识库中的格表示进行匹配， 如匹配成功， 则将所述格表示生成对应的操控指令。  The second module is configured to: match the lattice representation with the lattice representation in the pre-stored knowledge base, and if the matching is successful, the grid representation generates a corresponding manipulation instruction.
优选地， 上述移动终端还具有下面特点： 所述第一模块包括：  Preferably, the mobile terminal further has the following features: The first module includes:
第一单元， 设置为： 对所述文本信息进行句法分析， 标注出中心动词和 语义格；  The first unit is configured to: perform syntactic analysis on the text information, and mark the central verb and the semantic grid;
第二单元， 设置为： 将所述文本信息的中内容填充到对应的语义格中， 生成格表示。  The second unit is configured to: fill the content of the text information into a corresponding semantic lattice, and generate a lattice representation.
优选地， 上述移动终端还具有下面特点：  Preferably, the mobile terminal further has the following features:
所述第二单元， 设置为： 在生成格表示的过程中， 将中心动词和 /或语义 格对应的内容分别转化为预定的同义语。  The second unit is configured to: convert the content corresponding to the central verb and/or the semantics into a predetermined synonym in the process of generating the lattice representation.
优选地， 上述移动终端还具有下面特点： 所述第一模块包括，  Preferably, the mobile terminal further has the following features: the first module includes
第三单元， 设置为： 对所述语句信息中的关键词进行分析， 确立与所述 关键词对应的应用操作类型；  The third unit is configured to: analyze keywords in the statement information, and establish an application operation type corresponding to the keyword;
所述第二模块， 设置为： 将所述格表示与预存的知识库中与所述应用操 作类型相同类型的格表示进行匹配。  The second module is configured to: match the lattice representation with a lattice representation of a pre-stored knowledge base of the same type as the application operation type.
本发明实施例提供一种信息处理方法和移动终端， 在语音应用方面， 手 机通过语音识别技术可以将人说的一句话转化为文本信息， 用格文法这一语 句的句法分析和语义分析组合起来的关键技术， 进行移动终端任务领域的自 然语言理解分析， 以达到让移动终端理解用户的操控意图的目的。  The embodiment of the invention provides an information processing method and a mobile terminal. In terms of voice application, the mobile phone can convert a sentence spoken by a person into text information through a voice recognition technology, and combines the syntax analysis and semantic analysis of the sentence grammar statement. The key technology is to conduct natural language understanding analysis in the field of mobile terminal tasks to achieve the purpose of letting the mobile terminal understand the user's manipulation intention.
附图概述 图 1为本发明实施例的一种信息处理方法的流程图； BRIEF abstract FIG. 1 is a flowchart of an information processing method according to an embodiment of the present invention;
图 2为本发明实施例的句法分析好后的句法树的示意图；  2 is a schematic diagram of a syntax tree after syntactic analysis according to an embodiment of the present invention;
图 3为本发明实施例的移动终端的示意图。  FIG. 3 is a schematic diagram of a mobile terminal according to an embodiment of the present invention.
本发明的较佳实施方式 Preferred embodiment of the invention
下文中将结合附图对本发明的实施例进行详细说明。 需要说明的是， 在 不冲突的情况下， 本申请中的实施例及实施例中的特征可以相互任意组合。  Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that, in the case of no conflict, the features in the embodiments and the embodiments in the present application may be arbitrarily combined with each other.
为了更好地理解本发明， 下面结合附图和具体实施例对本发明作进一步 地描述。  For a better understanding of the invention, the invention will be further described in conjunction with the drawings and specific embodiments.
图 1为本发明实施例的一种信息处理方法的流程图， 如图 1所示， 本实 施例的方法包括以下步骤：  FIG. 1 is a flowchart of an information processing method according to an embodiment of the present invention. As shown in FIG. 1, the method in this embodiment includes the following steps:
511、 接收到语音信息后， 将所述语音信息转换成文本信息， 对所述文 本信息进行分析， 生成格表示；  511. After receiving the voice information, converting the voice information into text information, analyzing the text information, and generating a grid representation;
512、将所述格表示与预存的知识库中的格表示进行匹配，如匹配成功， 则将所述格表示生成对应的操控指令。  512. Match the lattice representation with the lattice representation in the pre-stored knowledge base. If the matching is successful, the grid representation generates a corresponding manipulation instruction.
格文法很适合手机操控领域的语义分析理解阶段的使用， 中心动词即为 操控的核心动作， 句子中的语义格则明确了操控所需要的相关信息， 一句话 如果具有核心动作和足够的相关信息就能够让手机理解用户的操控意图， 并 根据理解到的意图做出相应的操作。  The grammar method is very suitable for the use of the semantic analysis understanding stage in the field of mobile phone manipulation. The central verb is the core action of the manipulation, and the semantic lattice in the sentence clarifies the relevant information needed for manipulation. If there is a core action and enough relevant information in one sentence It is possible to let the mobile phone understand the user's control intention and make corresponding actions according to the understood intention.
具体实施例  Specific embodiment
步骤 101 :接收到语音信息后，将所述语音信息转换为文本的语句信息， 可以对语句中的关键词进行分析， 确立相关的应用主题， 以确立用户操控意 图中心内容； 例如， 出现 "电话" ， "拨打" 等关键词的时候则可以将该句处理划分 为电话这一类操作， 同理出现 "短信" 等关键词的时候则可以将该句处理划 分为短信这一类操作。  Step 101: After receiving the voice information, converting the voice information into text statement information, analyzing the keywords in the statement, and establishing related application topics to establish the user to manipulate the intention center content; for example, “phone” appears When " , " dialing " and other keywords , the sentence processing can be divided into operations such as telephone. Similarly, when "keywords" and other keywords appear, the processing of the sentence can be divided into short messages.
以 "给张三打电话" 为例， 该句子中出现了 "打电话" 因此该句的意图 可确立为 "电话" 类。 Taking "calling Zhang San" as an example, there is a "call" in the sentence, so the intention of the sentence Can be established as a "telephone" class.
步骤 102: 对所述语句进行句法分析， 标注好中心动词和语义格， 无论 是通过句法树的分析还是句子模板匹配的方式， 在句法分析结果中标注好中 心动词和语义格， 将句子中的内容填充到对应的语义格中， 生成格表示， 供 格表示的匹配。  Step 102: Perform syntactic analysis on the statement, mark the central verb and the semantic lattice, whether through the analysis of the syntax tree or the matching of the sentence template, mark the central verb and the semantic lattice in the syntax analysis result, and the sentence in the sentence The content is filled into the corresponding semantic lattice, and the lattice representation is generated, and the matching of the lattice representation is performed.
这里以句法树为例子， 有如图 2所示的句法分析好后的句法树： 图中用 圓圈圈住部分为语义格标注节点。  Here, taking the syntax tree as an example, there is a syntactic tree after syntactic analysis as shown in Fig. 2: The circle is circled in the figure to mark the node as a semantic lattice.
V-打： 中心动词  V-打: Central verb
N-张三： Contact格  N-Zhang San: Contact
N-电话： Object格  N-phone: Object grid
根据语义格标注节点分别获取到相关内容以后生成如下格表示：  According to the semantic grid labeling node, after obtaining the relevant content respectively, the following lattice representation is generated:
(中心动词：打 [Contact格:张三] [Object格:电话])。  (Center verb: hit [Contact: Zhang San] [Object: Phone]).
步骤 103 : 可以规约同义词， 可以对中心动词进行规约， 同样可以对格 内容进行规约，将中心动词和 /或语义格对应的内容分别转化为预定的同义语 : 以方便知识库的匹配， 提高语义分析的效率。 Step 103: The synonym can be stipulated, and the central verb can be stipulated. The content of the gram can also be stipulated, and the content corresponding to the central verb and/or the semantic genre is respectively converted into a predetermined synonym : to facilitate the matching of the knowledge base and improve The efficiency of semantic analysis.
例如， 打电话的动作都可以归结为拨打这样一个动作， 以步骤 102的结 果为例进行处理，该句的意图为电话类， 因此 "打"的同义词可以转化为 "拨 打" ， 同理意图为电话类的另一句话中心动词如果为 "呼叫" 同样可以转化 为 "拨打" 。 因此处理好以后的格表示转化为：  For example, the action of making a call can be attributed to dialing such an action, taking the result of step 102 as an example. The intention of the sentence is a telephone class, so the synonym of "hit" can be converted into "call", the same intention is Another sentence of the telephone class, the center verb, can also be converted to "dial" if it is "call". Therefore, after processing, the grid representation is converted to:
(中心动词：拨打 [Contact格:张三] [Object格:电话])  (Center verb: dial [Contact: Zhang San] [Object: Phone])
除中心动词外格内容也可以根据需要进行规约。  In addition to the central verb content, the content can also be stipulated as needed.
步骤 104: 将生成好的格表示与知识库中的格表示按格表示的结构类型 跟同类型的格表示进行语义的匹配， 匹配成功则语义分析成功， 手机就可以 根据该有正确语义的格表示生成对应的操控指令。  Step 104: Matching the generated lattice representation with the lattice representation in the knowledge base according to the structure type represented by the lattice and the lattice representation of the same type. If the matching succeeds, the semantic analysis is successful, and the mobile phone can according to the lattice with the correct semantics. Indicates that the corresponding manipulation command is generated.
知识库中格表示按照意图进行分类存储示例如下 (这里只用了三个意图 类型作为示例)：  An example of a grid in the knowledge base that stores classifications by intent is as follows (only three intent types are used here as examples):
电话类: (中心动词：拨打 [Object格:电话]) Telephone class: (Center verb: dial [Object: Phone])
(中心动词：拨打 [Contact格: *] [Object格:电话])  (Center verb: dial [Contact: *] [Object: Phone])
短信类： SMS class:
(中心动词：发送 [Object格:短信])  (Center verb: send [Object: SMS])
(中心动词：发送 [Contact格: *][0bject格:短信])  (Center verb: send [Contact: *] [0bject: SMS])
(中心动词：发送 [Contact格: *][0bject格:短信] [Content格： *])  (Center verb: send [Contact: *][0bject: SMS] [Content: *])
导航类： Navigation class:
(中心动词：定位 [Destination格: *])  (Center verb: positioning [Destination: *])
(中心动词：导航 [Destination格: *] [Source格: *])  (Center verb: navigation [Destination grid: *] [Source grid: *])
步骤 103 处理好的结果在知识库中根据其结构（中心动词:拨打 [Contact 格:张三] [Object格:电话])应该跟（中心动词： [Contact格:] [Object格：])这样的 格表示进行匹配， 电话类中搜到了如下满足条件的格表示： Step 103 The processed result is based on its structure in the knowledge base (central verb: dial [Contact: Zhang San] [Object: phone]) should be followed by (center verb: [Contact:] [Object]:) The cell indicates that the match is made, and the following cell condition is found in the phone class:
(中心动词：拨打 [Contact格: *] [Object格:电话])  (Center verb: dial [Contact: *] [Object: Phone])
比较后中心动词满足， Object格满足， 但是可以看到知识库中存储的 Contact格有缺省内容 "*" , 这个时候还要做的就是进行词义匹配， 可以在 知识库中构建词的各种标签， 用以进行语义分析， 这里 "张三" 可以附带 "Contact" 语义标签，因此张三就满足了 Contact格，该句子意图分析完成， 在知识库中有相关的语义， 用户的意图就能理解为是想要给张三这个联系人 拨打电话， 语义分析成功并结束。  After the comparison, the central verb is satisfied, the Object is satisfied, but you can see that the Contact box stored in the knowledge base has the default content "*". At this time, what you have to do is to match the meaning of the word. You can build various words in the knowledge base. Label, used for semantic analysis, here "Zhang San" can be attached with the "Contact" semantic tag, so Zhang San satisfies the Contact lattice, the sentence is intended to be analyzed, the relevant semantics in the knowledge base, the user's intention can It is understood that I want to call Zhang San, the contact, and the semantic analysis is successful and ends.
相反 "给张三拨打老虎" 这样一句话， 步骤 103分析出的结果如下： (中心动词：拨打 [Contact格:张三] [Object格:老虎]) ,  Contrary to the phrase "Take Zhang to call the tiger", the results of step 103 are as follows: (Center verb: dial [Contact: Zhang San] [Object: Tiger]),
此时 Object格匹配不成功， 语义分析失败并结束。  At this point, the Object cell match is unsuccessful, and the semantic analysis fails and ends.
亦或者 "给电脑拨打电话" 这样一句话， 步骤 103分析出的结果如下： (中心动词：拨打 [Contact格:电脑] [Object格:电话]) , Or "call the computer" In this sentence, the results of step 103 are as follows: (Center verb: dial [Contact: computer] [Object: phone]),
电脑在知识库中没有 Contact语义标签， 同样语义分析失败并结束。  The computer does not have a Contact semantic tag in the knowledge base, and the semantic analysis fails and ends.
图 3为本发明实施例的移动终端的示意图， 如图 3所示， 本实施例的移 动终端包括： FIG. 3 is a schematic diagram of a mobile terminal according to an embodiment of the present invention. As shown in FIG. 3, the mobile terminal of this embodiment includes:
第一模块， 用于接收到语音信息后， 将所述语音信息转换成文本信息， 对所述文本信息进行分析， 生成格表示；  a first module, after receiving the voice information, converting the voice information into text information, analyzing the text information, and generating a grid representation;
第二模块， 用于将所述格表示与预存的知识库中的格表示进行匹配， 如 匹配成功， 则将所述格表示生成对应的操控指令。  The second module is configured to match the lattice representation with the lattice representation in the pre-stored knowledge base. If the matching is successful, the grid representation generates a corresponding manipulation instruction.
其中， 所述第一模块包括：  The first module includes:
第一单元， 用于对所述文本信息进行句法分析， 标注出中心动词和语义 格；  a first unit, configured to perform syntax analysis on the text information, and mark a central verb and a semantic grid;
第二单元， 用于将所述文本信息的中内容填充到对应的语义格中， 生成 格表示。  a second unit is configured to fill the content of the text information into a corresponding semantic grid to generate a lattice representation.
其中， 所述第二单元， 在生成格表示的过程中具体用于， 将中心动词和 / 或语义格对应的内容分别转化为预定的同义语。  The second unit is specifically configured to convert the content corresponding to the central verb and/or the semantic lattice into a predetermined synonym in the process of generating the lattice representation.
其中， 所述第一模块包括，  Wherein the first module includes
第三单元， 用于对所述语句信息中的关键词进行分析， 确立与所述关键 词对应的应用操作类型；  a third unit, configured to analyze a keyword in the statement information, and establish an application operation type corresponding to the keyword;
所述第二模块， 具体用于将所述格表示与预存的知识库中与所述应用操 作类型相同类型的格表示进行匹配。  The second module is specifically configured to match the cell representation with a lattice representation of a pre-stored knowledge base of the same type as the application operation type.
本领域普通技术人员可以理解上述方法中的全部或部分步骤可通过程序 来指令相关硬件完成， 所述程序可以存储于计算机可读存储介质中， 如只读 存储器、 磁盘或光盘等。 可选地， 上述实施例的全部或部分步骤也可以使用 一个或多个集成电路来实现。 相应地， 上述实施例中的各模块 /单元可以釆用 硬件的形式实现， 也可以釆用软件功能模块的形式实现。 本发明不限制于任 何特定形式的硬件和软件的结合。 One of ordinary skill in the art will appreciate that all or a portion of the above steps may be performed by a program to instruct the associated hardware, such as a read only memory, a magnetic disk, or an optical disk. Alternatively, all or part of the steps of the above embodiments may also be implemented using one or more integrated circuits. Correspondingly, each module/unit in the foregoing embodiment may be implemented in the form of hardware, or may be implemented in the form of a software function module. The invention is not limited to any What is the combination of specific forms of hardware and software.
以上仅为本发明的优选实施例， 当然， 本发明还可有其他多种实施例， 在不背离本发明精神及其实质的情况下， 熟悉本领域的技术人员当可根据本 发明作出各种相应的改变和变形， 但这些相应的改变和变形都应属于本发明 所附的权利要求的保护范围。 The above is only a preferred embodiment of the present invention, and of course, the present invention may be embodied in various other embodiments without departing from the spirit and scope of the invention. Corresponding changes and modifications are intended to be included within the scope of the appended claims.
工业实用性 本发明实施例提供一种信息处理方法和移动终端， 在语音应用方面， 手 机通过语音识别技术可以将人说的一句话转化为文本信息， 用格文法这一语 句的句法分析和语义分析组合起来的关键技术， 进行移动终端任务领域的自 然语言理解分析， 以达到让移动终端理解用户的操控意图的目的。 INDUSTRIAL APPLICABILITY An embodiment of the present invention provides an information processing method and a mobile terminal. In a voice application, a mobile phone can convert a sentence spoken by a person into text information through a voice recognition technology, and syntactic analysis and semantics of the statement using the grammar method. Analyze the key technologies combined and conduct natural language understanding analysis in the field of mobile terminal tasks to achieve the purpose of letting the mobile terminal understand the user's control intention.

Claims

权 利 要 求 书 Claim
1、 一种信息处理方法， 包括：  1. An information processing method, comprising:
接收到语音信息后， 将所述语音信息转换成文本信息， 对所述文本信息 进行分析， 生成格表示；  After receiving the voice information, converting the voice information into text information, analyzing the text information, and generating a grid representation;
将所述格表示与预存的知识库中的格表示进行匹配， 如匹配成功， 则将 所述格表示生成对应的操控指令。  The lattice representation is matched with the lattice representation in the pre-stored knowledge base. If the matching is successful, the lattice representation is generated to generate a corresponding manipulation instruction.
2、 如权利要求 1所述的方法， 其中， 对所述文本信息进行分析， 生成格 表示包括：  2. The method according to claim 1, wherein the text information is analyzed, and the generated lattice representation comprises:
对所述文本信息进行句法分析， 标注出中心动词和语义格；  Syntactic analysis of the text information, marking the central verb and semantic grid;
将所述文本信息的中内容填充到对应的语义格中， 生成格表示。  Filling the content of the text information into a corresponding semantic grid to generate a lattice representation.
3、 如权利要求 2所述的方法， 其中， 所述生成格表示的过程中包括： 将中心动词和 /或语义格对应的内容分别转化为预定的同义语。  3. The method according to claim 2, wherein the process of generating the lattice representation comprises: converting the content corresponding to the central verb and/or the semantic grid into a predetermined synonym.
4、 如权利要求 1-3任一项所述的方法， 其中， 对所述文本信息进行分析 包括： 4. The method according to any one of claims 1-3, wherein analyzing the text information comprises:
对所述文本信息中的关键词进行分析， 确立与所述关键词对应的应用操 作类型；  Parsing keywords in the text information to establish an application operation type corresponding to the keyword;
将所述格表示与预存的知识库中的格表示进行匹配， 包括：  Matching the lattice representation to the lattice representation in the pre-stored knowledge base, including:
将所述格表示与预存的知识库中与所述应用操作类型相同类型的格表示 进行匹配。  The lattice representation is matched to a lattice representation of the pre-stored knowledge base of the same type as the application operation type.
5、 一种移动终端， 包括：  5. A mobile terminal, comprising:
第一模块， 设置为： 接收到语音信息后， 将所述语音信息转换成文本信 息， 对所述文本信息进行分析， 生成格表示；  The first module is configured to: after receiving the voice information, convert the voice information into text information, analyze the text information, and generate a grid representation;
第二模块，设置为：将所述格表示与预存的知识库中的格表示进行匹配， 如匹配成功， 则将所述格表示生成对应的操控指令。  The second module is configured to: match the lattice representation with the lattice representation in the pre-stored knowledge base, and if the matching is successful, the grid representation generates a corresponding manipulation instruction.
6、 如权利要求 5所述的移动终端， 其中， 所述第一模块包括： 第一单元， 设置为： 对所述文本信息进行句法分析， 标注出中心动词和 语义格； 第二单元， 设置为： 将所述文本信息的中内容填充到对应的语义格中， 生成格表示。 The mobile terminal according to claim 5, wherein the first module comprises: a first unit, configured to: perform syntax analysis on the text information, and mark a central verb and a semantic grid; The second unit is configured to: fill the content of the text information into a corresponding semantic lattice, and generate a lattice representation.
7、 如权利要求 6所述的移动终端， 其中，  7. The mobile terminal of claim 6, wherein
所述第二单元， 设置为： 在生成格表示的过程中， 将中心动词和 /或语义 格对应的内容分别转化为预定的同义语。  The second unit is configured to: convert the content corresponding to the central verb and/or the semantics into a predetermined synonym in the process of generating the lattice representation.
8、 如权利要求 5-7任一项所述的移动终端， 其中， 所述第一模块包括， 第三单元， 设置为： 对所述语句信息中的关键词进行分析， 确立与所述 关键词对应的应用操作类型；  The mobile terminal according to any one of claims 5 to 7, wherein the first module includes: a third unit, configured to: analyze keywords in the sentence information, establish and key The type of application operation corresponding to the word;
所述第二模块， 设置为： 将所述格表示与预存的知识库中与所述应用操 作类型相同类型的格表示进行匹配。  The second module is configured to: match the lattice representation with a lattice representation of a pre-stored knowledge base of the same type as the application operation type.
PCT/CN2013/081612 2013-01-22 2013-08-16 Information processing method and mobile terminal WO2013189342A2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201310021569.1 2013-01-22
CN201310021569.1A CN103945044A (en) 2013-01-22 2013-01-22 Information processing method and mobile terminal

Publications (2)

Publication Number Publication Date
WO2013189342A2 true WO2013189342A2 (en) 2013-12-27
WO2013189342A3 WO2013189342A3 (en) 2014-02-13

Family

ID=49769504

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/081612 WO2013189342A2 (en) 2013-01-22 2013-08-16 Information processing method and mobile terminal

Country Status (2)

Country Link
CN (1) CN103945044A (en)
WO (1) WO2013189342A2 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103888606A (en) * 2014-03-11 2014-06-25 上海乐今通信技术有限公司 Mobile terminal and unlocking method thereof
CN104574246A (en) * 2014-12-22 2015-04-29 百度在线网络技术（北京）有限公司 Intelligent medical triage method, device and equipment
CN106847279A (en) * 2017-01-10 2017-06-13 西安电子科技大学 Man-machine interaction method based on robot operating system ROS
CN111373473A (en) * 2018-03-05 2020-07-03 华为技术有限公司 Electronic equipment and method for performing voice recognition by using same

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104462186A (en) * 2014-10-17 2015-03-25 百度在线网络技术（北京）有限公司 Method and device for voice search
CN104485106B (en) * 2014-12-08 2018-08-28 畅捷通信息技术股份有限公司 Audio recognition method, speech recognition system and speech recognition apparatus
US9661105B2 (en) * 2014-12-11 2017-05-23 Wand Labs, Inc. Virtual assistant system to enable actionable messaging
CN104598192B (en) * 2014-12-29 2018-08-07 联想(北京)有限公司 Information processing method and electronic equipment
US10460720B2 (en) 2015-01-03 2019-10-29 Microsoft Technology Licensing, Llc. Generation of language understanding systems and methods
JP6669073B2 (en) * 2015-03-31 2020-03-18 ソニー株式会社 Information processing apparatus, control method, and program
CN105446146B (en) * 2015-11-19 2019-05-28 深圳创想未来机器人有限公司 Intelligent terminal control method, system and intelligent terminal based on semantic analysis
CN105609104A (en) * 2016-01-22 2016-05-25 北京云知声信息技术有限公司 Information processing method and apparatus, and intelligent voice router controller
CN107800895A (en) * 2016-08-31 2018-03-13 南京中兴软件有限责任公司 A kind of interactive voice answering method and device
CN106384594A (en) * 2016-11-04 2017-02-08 湖南海翼电子商务股份有限公司 On-vehicle terminal for voice recognition and method thereof
CN107403619B (en) * 2017-06-30 2021-05-28 武汉泰迪智慧科技有限公司 Voice control method and system applied to bicycle environment
CN107315737B (en) * 2017-07-04 2021-03-23 北京奇艺世纪科技有限公司 Semantic logic processing method and system
CN109841210B (en) * 2017-11-27 2024-02-20 西安中兴新软件有限责任公司 Intelligent control implementation method and device and computer readable storage medium
CN110322873B (en) 2019-07-02 2022-03-01 百度在线网络技术（北京）有限公司 Voice skill quitting method, device, equipment and storage medium
CN113076397A (en) * 2021-03-29 2021-07-06 Oppo广东移动通信有限公司 Intention recognition method and device, electronic equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102622342A (en) * 2011-01-28 2012-08-01 上海肇通信息技术有限公司 Interlanguage system and interlanguage engine and interlanguage translation system and corresponding method
CN102629246A (en) * 2012-02-10 2012-08-08 北京百纳信息技术有限公司 Server used for recognizing browser voice commands and browser voice command recognition system
CN102880649A (en) * 2012-08-27 2013-01-16 北京搜狗信息服务有限公司 Individualized information processing method and system

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100347741C (en) * 2005-09-02 2007-11-07 清华大学 Mobile speech synthesis method
CN102609189A (en) * 2012-01-13 2012-07-25 百度在线网络技术（北京）有限公司 Method and client side for processing content of messages of mobile terminal
CN102636171A (en) * 2012-04-27 2012-08-15 深圳市凯立德科技股份有限公司 Voice navigation method and device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102622342A (en) * 2011-01-28 2012-08-01 上海肇通信息技术有限公司 Interlanguage system and interlanguage engine and interlanguage translation system and corresponding method
CN102629246A (en) * 2012-02-10 2012-08-08 北京百纳信息技术有限公司 Server used for recognizing browser voice commands and browser voice command recognition system
CN102880649A (en) * 2012-08-27 2013-01-16 北京搜狗信息服务有限公司 Individualized information processing method and system

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103888606A (en) * 2014-03-11 2014-06-25 上海乐今通信技术有限公司 Mobile terminal and unlocking method thereof
CN104574246A (en) * 2014-12-22 2015-04-29 百度在线网络技术（北京）有限公司 Intelligent medical triage method, device and equipment
CN106847279A (en) * 2017-01-10 2017-06-13 西安电子科技大学 Man-machine interaction method based on robot operating system ROS
CN111373473A (en) * 2018-03-05 2020-07-03 华为技术有限公司 Electronic equipment and method for performing voice recognition by using same
CN111373473B (en) * 2018-03-05 2023-10-20 华为技术有限公司 Method for voice recognition of electronic equipment and electronic equipment

Also Published As

Publication number Publication date
CN103945044A (en) 2014-07-23
WO2013189342A3 (en) 2014-02-13

Similar Documents

Publication Publication Date Title
WO2013189342A2 (en) Information processing method and mobile terminal
KR102494643B1 (en) Automated assistant invocation of appropriate agent
KR101042119B1 (en) Semantic object synchronous understanding implemented with speech application language tags
KR101066741B1 (en) Semantic object synchronous understanding for highly interactive interface
KR102342172B1 (en) Tailoring creator-provided content-based interactive conversational applications
US8364487B2 (en) Speech recognition system with display information
KR20220027198A (en) Pinning of Artifacts for Expansion of Search Keys and Search Spaces in a Natural Language Understanding (NLU) Framework
EP1638081B1 (en) Creating a speech recognition grammar for alphanumeric concepts
US7818166B2 (en) Method and apparatus for intention based communications for mobile communication devices
WO2015096564A1 (en) On-line voice translation method and device
KR20220028038A (en) Derivation of multiple semantic expressions for utterances in a natural language understanding framework
KR102429407B1 (en) User-configured and customized interactive dialog application
US7257529B2 (en) Apparatus and method for an automated grammar file expansion tool
KR20190074508A (en) Method for crowdsourcing data of chat model for chatbot
KR101207435B1 (en) Interactive speech recognition server, interactive speech recognition client and interactive speech recognition method thereof
WO2014161301A1 (en) Terminal control method and device, and terminal
JP5300576B2 (en) SEARCH DEVICE, SEARCH METHOD, AND SEARCH PROGRAM
KR101090554B1 (en) Wireless Internet Access Method Based on Conversational Interface
JP2003345800A (en) Communication system using daily language, transmission client secretary unit, reception client secretary unit, language application device, transmission client secretary method, reception client secretary method, language application method, and program

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: 13807129

Country of ref document: EP

Kind code of ref document: A2

122 Ep: pct application non-entry in european phase

Ref document number: 13807129

Country of ref document: EP

Kind code of ref document: A2