KR20150045177A - Conversational service apparatus and method based on user utterance - Google Patents

Abstract

The present invention relates to an apparatus and method for providing a conversational service according to user speech styles. The apparatus analyzes the meaning of a sentence spoken by a user to identify a user utterance intention, analyzes semantic features of the sentence to generate an utterance style profile of the user according to the user′s utterance style, and generates a response sentence according to the user′s utterance style based on the generated utterance style profile, thereby providing the user with a more friendly and natural response sentence according to the user′s utterance style, not a set response sentence.

Description

Technical Field [0001] The present invention relates to an interactive service apparatus and method according to a user utterance style,

The present invention relates to an interactive service, and more particularly, to an interactive service apparatus and method according to a user utterance style for providing a response sentence generated by generating a natural response sentence according to a user utterance style.

The contents described in this section merely provide background information on the present embodiment and do not constitute the prior art.

In recent years, products and services using interfaces based on language, which was a tool for communicating the will of human beings before the development of civilization, are emerging.

Research on language-based interfaces has evolved from a method of answering an initial one-way voice question with a dial or a button, to a method of answering a voice word as a limited word, and ultimately aiming at an interface through natural voice conversation.

In the case of the interactive service using the interface through natural voice conversation, it is necessary to understand the language to grasp the user's utterance intention, to manage the dialogue to decide the conversation strategy according to the flow of the conversation and the intention, Do.

However, in the conventional interactive service, since it provides a framed response according to the voice question, there is a limit to providing a natural interactive service. Therefore, in order to provide a natural interactive service, a technique for generating a friendly and natural response sentence according to a conversation strategy is required.

Korean Registered Patent No. 0829401, May 07, 2008 Registered (name: device and method for recognizing the detailed classification object name)

The present invention has been proposed in order to solve the inconvenience of the prior art, and it is an object of the present invention to analyze the meaning of a user utterance sentence to understand a user utterance intention, analyze the meaning qualities of the user utterance sentence, And an interactive service apparatus and method according to a user utterance style for generating a response sentence according to a user utterance style based on the generated personal user utterance style profile to provide a friendly and natural response sentence to a user .

According to an aspect of the present invention, there is provided an interactive service apparatus comprising: an interface unit receiving a user utterance sentence according to user utterance; And analyzing the meaning of the user uttered sentence, analyzing the meaning of the user uttered sentence, analyzing the user uttered style according to the meaning of the analyzed user uttered sentence, Generates and stores a speech style profile, and generates a response sentence corresponding to the user speech based on the stored personalized speech style profile.

The interactive service apparatus according to the preferred embodiment of the present invention may further include a storage unit for storing the generated personalized speech style profile and storing a predetermined response sentence template used in the response sentence.

In the interactive service apparatus according to the preferred embodiment of the present invention, the controller analyzes the meaning of the user utterance sentence, grasps the user utterance style according to the meaning of the analyzed user utterance sentence, A personalized utterance style profile generation module for generating a personal utterance style profile according to the personalized utterance style profile; And a response sentence generation module for generating a response sentence according to the user utterance based on the personalized utterance style profile generated by the user utterance style profile generation module.

In the interactive service apparatus according to the preferred embodiment of the present invention, the user utterance style profile generation module applies a lexical pattern (LSP) expressing sentence patterns having the same meaning to each analyzed morpheme The meaning of the user utterance sentence can be analyzed.

In the interactive service apparatus according to the preferred embodiment of the present invention, the phrase pattern includes at least one of information on an object name, a semantic feature, a lexicon and a part of speech tag according to the concept of the user's utterance sentence, .

In an interactive service apparatus according to a preferred embodiment of the present invention, the user utterance style profile generation module includes: an analyzer for analyzing a morpheme of the user utterance sentence; A morpheme tag that assigns part mark tags to each analyzed morpheme; And analyzing the meaning of the user utterance sentence by applying a recognized utterance pattern to the recognized entity name and the recognized one or more sense qualities, An object name and a semantic qualifier for analyzing a user utterance style according to one or more recognized semantic qualities; And a personalized utterance style profile generator for generating and storing a personal utterance style profile according to the analyzed user utterance style based on the recognized entity name and the substantial morpheme and formal morpheme of the recognized meaning qualification.

In the interactive service apparatus according to the preferred embodiment of the present invention, the response sentence generation module reads out a previously stored speech sentence template corresponding to the recognized entity name and semantic qualities, A response sentence can be generated by reading the actual morpheme and morpheme corresponding to the response semantic qualification from the stored personal speech style profile DB and applying the actual morpheme and morpheme of the read semantic feature to the response semantic feature.

In the interactive service apparatus according to the preferred embodiment of the present invention, the response sentence generation module generates a response sentence by combining the recognized entity name with the actual morpheme and type morpheme of the read out semantic feature, A final response sentence to be presented to the user can be generated by adding an additional response sentence to the sentence.

According to another aspect of the present invention, there is provided an interactive service method according to a user utterance style in an interactive service apparatus, comprising: grasping an inputted user utterance sentence; Analyzing the meaning of the identified user utterance sentence; Determining a user utterance style according to the meaning of the analyzed user utterance sentence; Generating a personalized utterance style profile according to the identified user utterance style; And generating a response sentence corresponding to the user utterance based on the stored personal utterance style profile.

In an interactive service method according to a user utterance style in an interactive service apparatus according to a preferred embodiment of the present invention, analyzing the meaning of the user utterance sentence includes analyzing a morpheme of a user utterance sentence; Assigning speech tags to each analyzed morpheme; Recognizing an entity name and at least one semantic feature for each analyzed morpheme; And analyzing the meaning of the user utterance sentence by applying a recognized utterance pattern to the recognized entity name and the recognized one or more sense qualities.

In an interactive service method according to a user utterance style in an interactive service apparatus according to a preferred embodiment of the present invention, the step of generating a response sentence corresponding to the user utterance based on the stored personal utterance style profile comprises: Reading out a pre-stored speech sentence template corresponding to the object name and the semantic feature; Reading the actual morpheme and morpheme morpheme corresponding to the response semantic qualities used in the read speech sentence template from the stored personal speech style profile DB; And generating a response sentence by applying the substantial morpheme and formal morpheme of the read out semantic feature to the response semantic feature.

In an interactive service method according to a user utterance style in an interactive service apparatus according to a preferred embodiment of the present invention, the step of generating a response sentence corresponding to the user utterance based on the stored personal utterance style profile comprises: And outputting a response sentence to the user.

In the interactive service method according to the user utterance style in the interactive service apparatus according to the preferred embodiment of the present invention, the step of generating the response sentence corresponding to the user utterance based on the stored personal utterance style profile, Reading a response sentence template for generating a sentence; And generating an additional response sentence using the response sentence template for generating the readout added response sentence.

According to an aspect of the present invention, there is provided a computer-readable recording medium storing a program for executing an interactive service method according to a user utterance style.

The present invention analyzes a meaning of a user utterance sentence to grasp a user utterance intention, generates a personal utterance style profile by grasping a user utterance style according to various semantic qualities for expressing a user utterance intention in a user utterance sentence, It is possible to generate a response sentence by applying the most commonly used speech style at the time of creation, thereby providing a more friendly and natural response sentence to the user in accordance with the user utterance style rather than a framed response sentence.

The effects obtained in the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the following description .

1 is a diagram illustrating a configuration of an interactive service apparatus according to a user utterance style according to an embodiment of the present invention.
2 is a diagram illustrating a specific configuration of a personalized utterance style profile generation module of an interactive service apparatus according to an embodiment of the present invention.
3 is a diagram illustrating a concrete configuration for showing the operation of the response sentence generation module of the interactive service apparatus according to the embodiment of the present invention.
4 is a diagram illustrating an interactive service authentication method according to a user utterance style according to an embodiment of the present invention.
5 is a diagram illustrating an example of generating a response sentence according to a user utterance style according to an embodiment of the present invention.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following detailed description, together with the accompanying drawings, is intended to illustrate exemplary embodiments of the invention and is not intended to represent the only embodiments in which the invention may be practiced. The following detailed description includes specific details in order to provide a thorough understanding of the present invention. However, those skilled in the art will appreciate that the present invention may be practiced without these specific details.

In some instances, well-known structures and devices may be omitted or may be shown in block diagram form, centering on the core functionality of each structure and device, to avoid obscuring the concepts of the present invention.

Throughout the specification, when an element is referred to as "comprising" or " including ", it is meant that the element does not exclude other elements, do. Also, the terms " part, "" module," and " module ", etc. in the specification mean a unit for processing at least one function or operation and may be implemented by hardware or software or a combination of hardware and software have. Also, the terms " a or ", "one "," the ", and the like are synonyms in the context of describing the invention (particularly in the context of the following claims) May be used in a sense including both singular and plural, unless the context clearly dictates otherwise.

The specific terminology used in the following description is provided to aid understanding of the present invention, and the use of such specific terminology may be changed into other forms without departing from the technical idea of the present invention.

Prior to the description, an example referred to in the present invention refers to an example in which the specific word is used in the linguistic field. In particular, the examples referred to in the present invention include not only a corpus composed of sentences according to a formal grammar structure but also sentences deviating from regular rules and used in real life, and sentences including various styles.

Hereinafter, an interactive service apparatus and method for providing a natural response sentence according to a user utterance style according to an embodiment of the present invention will be described. First, an interactive service apparatus according to a user utterance style according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating a configuration of an interactive service apparatus according to a user utterance style according to an embodiment of the present invention.

Referring to FIG. 1, the interactive service apparatus 100 may include a controller 110, an interface unit 120, and a storage unit 130.

The control unit 110 performs overall control of the interactive service apparatus 100 and is functionally connected to the interface unit 120 and the storage unit 130 to perform control of signal flow for performing functions. At this time, the control unit 130 may include an operating system (OS), an application program, and a process unit for driving each configuration, for example, a central processing unit (CPU).

In particular, the controller 110 according to the embodiment of the present invention generates a natural response sentence according to a user's utterance style and performs control to provide the response sentence to the user. To this end, the controller 110 generates a personal utterance style profile And a response sentence generation module 112. The response sentence generation module 112 generates a response sentence.

The personalized utterance style profile generation module 111 receives an input signal for the user utterance input from the user through the interface unit 120, checks the user utterance sentence according to the input signal for the user utterance, Analyze the meaning of the utterance sentence, identify the user utterance style according to the meaning of the analyzed user utterance sentence, and generate a personal utterance style profile according to the grasped user utterance style. To this end, the personalized utterance style profile generation module 111 includes a morpheme analyzer 111-1, a morpheme tag 111-2, an entity name and semantic feature recognizer 111-3, a personalized utterance style profile generator 111-4 ). ≪ / RTI >

Specifically, the personal utterance style profile generation module 111 can analyze the user utterance sentence through a morpheme analyzer 111-1 into a small unit of morpheme having a minimum meaning. Here, a morpheme refers to the smallest unit that presupposes meaning, whether a lexical or a grammatical sentence composed of a large number of grammatical units, and can be classified into a substantial morpheme and a morpheme morpheme. The actual morpheme is a morpheme that indicates a lexical meaning such as a specific object, an action, and a state. For example, in the user utterance sentence as shown in FIG. 5, "Seoul Station", "Departure", "COEX" , "Incheon Airport", "How", and so on. All the independent morphemes and dependence morphemes are the stem of vernacular. And the morpheme morpheme is a morpheme which is attached to the actual morpheme and is a formal morpheme for expressing the function between the horse and the horse. For example, in the user utterance sentence as shown in FIG. 5, These correspond to "to", "to", and "to go", and various investigations, endings, and affixes correspond to formal morphemes and are also called grammatical morphemes.

Accordingly, the morpheme analyzer 111-1 analyzes morphemes of the user utterance sentence by analyzing the user utterance sentence until it has no meaning.

Then, the individual utterance style profile generation module 111 may assign a morphing tag to each morpheme analyzed through the morpheme tagging in the morpheme analyzer 111-1 through the morpheme tag 111-2. In this context, a part-of-speech is a grouping of words with common characteristics, that is, a division of words according to their grammatical functions, forms, and meanings, and nouns, pronouns, investigations, verbs, adjectives, It can be classified as exclamation.

Thus, the morpheme tagger 111-2 attaches the tags of the morpheme parts of each morpheme to determine the correct part of speech of each morpheme analyzed so as to enable the semantics of the morpheme mechanically, You can have the words recalled.

Thereafter, the entity name and the semantic feature identifier 111-3 of the personalized utterance style profile generation module 111 correspond to each morpheme analyzed in the entity name dictionary or semantic feature dictionary stored in the entity name and semantic feature database 131 The object name and the semantic qualities of the user utterance sentence can be recognized by recognizing the object name and the semantic qualities of the user utterance sentence. Here, the object name recognition refers to automatically recognizing names of entities existing in the world such as a company name, a person name, a local name, a movie name, and the like, and the semantic qualification means the minimum component constituting the meaning of a word. For example, in a user utterance sentence as shown in the attached FIG. 5, a "Seoul Station" for a place + investigation through "Seoul + Station +" to "Seoul + Station + Recognizes the name of the object and recognizes the meaning qualities of "moving_root + mother" through "departure".

Accordingly, the entity name and the semantic feature recognizer 111-3 of the personalized utterance style profile generation module 111 recognize that the corresponding morpheme is a moveable word through a recognized semantic feature (" It can be analyzed as meaning. Here, the entity name and semantic feature recognizer 111-3 can analyze the meaning of the user utterance sentence by applying a LSP (Lexico Syntactic Pattern) representing sentence forms having the same meaning to each analyzed morpheme . Such a phrase pattern may be configured to include at least one or more of information on an object name, a semantic feature, a vocabulary, and a part of speech tag according to the concept of a user utterance sentence.

Then, the individual utterance style profile generator 111-4 of the utterance style profile generation module 111 grasps the utterance style of the user utterance sentence analyzed with meaning and accumulates and manages the uttered utterance style in the personal utterance style have. To this end, the personalized utterance style profile generator 111-4 obtains the recognition result of the object name and the semantic qualification, that is, the name of the object ("Seoul Station") for the place + + Fsd ") to determine the user utterance style. That is, the personalized utterance style profile generator 111-4 can grasp the meaning qualities of " get off the go "of the transliteration of the place into the user utterance style.

Then, the personalized utterance style profile generator 11-4 generates the personalized utterance style profile 11-4 based on the recognized entity name and the substantial morpheme and the type of the semantic feature according to the user utterance style in the form of the recognized entity name (place + survey) A personalized speech style profile of the user including the morpheme can be generated. In other words, it is possible to create and store a personalized speech style profile as an object name (place + inquiry: to Seoul Station +) and a meaning qualification (move_request + mother: departure). Here, the personalized utterance style profile may be mapped and stored in association with one or more semantic qualities (for example, a +, a +, a +, etc.) according to a user's various utterance styles .

3, the response sentence generation module 112 receives a response request signal from the personalized speech style profile generation unit 111. Then, the personalized speech style profile generation unit 111 generates a personalized speech style The corresponding sentence template can be read from the response sentence template DB 133 based on the morpheme of the sentence name and the sentence qualities. Then, the response sentence generation module 112 checks the meaning qualities (hereinafter referred to as response meaning qualities) used in the read response sentence templates, and then stores the actual morpheme and type morpheme corresponding to the confirmed meaning qualities in the personal speech style profile The response sentence can be generated by applying the selected morphemes and morphemes selected from the corresponding semantic qualities stored in the DB 132 to the response semantic qualities. For example, the response sentence generation module 112 confirms the recognized entity name (place + inquiry: to Seoul Station +) and the recognized meaning property (move_reason + ending: departure) according to the response request , The corresponding response sentence template (place + survey, move_directive + response_emory) is read and the recognized object name (Seoul station) + survey () is mapped to the object name (place + survey) of the response sentence template Quot; to " Go to ", and mapping the " ~ "for the translated term in the personalized utterance style profile database 132 to the translated word " Accordingly, the response sentence generation module 112 generates a response sentence of "Go to Seoul Station ", and additionally generates an additional response sentence (" The expected arrival time is 3 o'clock. " Can be provided. Here, the response sentence generation module 112 reads out the meaning qualities of the utterance style most used by the user when reading the substantial morpheme and formal morpheme about the semantic qualities to be applied to the response sentence in the personal utterance style profile DB 132, By applying it to a sentence, it is possible to generate a response sentence that is familiar and natural to the user.

In addition, the response sentence generation module 112 generates an additional response sentence according to a predetermined response pattern, reads the additional response sentence template mapped together with the response sentence template corresponding to the user uttered sentence, and applies it to the additional response sentence template If the object name or semantic qualification is required, it is possible to generate a response sentence to be presented to the end user by applying and applying the object name or the semantic qualification through DB or function that interlocks with the corresponding object name or semantic qualification.

The interface unit 120 is a means for providing an interface for generating and providing a response sentence according to a user utterance style. In particular, in the present invention, when the interface unit 120 receives an input signal for user's utterance from one or more other devices through a separate communication module (not shown), the interface unit 120 transmits the received input signal to the controller 110 , And input information about a user's utterance from a user through a separate input module (not shown) to generate an input signal. In addition, the interface unit 120 transmits a response sentence generated according to a user's utterance style to one or more other devices through a separate communication module (not shown) or outputs the response sentence to a user through a separate output module .

The storage unit 130 is a means for storing information necessary for analysis of a user utterance sentence. Specifically, the storage unit 130 may include an object name and semantic feature database DB 131, a personalized speech style profile database DB 132, and a response sentence template database DB 133.

Object name and meaning The attribute database (DB, 131) includes an object name dictionary and a vocabulary composed of a set of named entities having a unique meaning such as a name, a place name, an institution name, a date, a number, A semantic feature dictionary consisting of a set of semantic features, which is the minimum unit that constitutes meaning, can be stored.

The personalized speech style profile database (DB) 132 may analyze the user's utterance sentence in the personalized speech style profile generation module 111 and store information on the personalized speech style profile generated according to the recognized speech style.

The response sentence template database (DB) 133 may store information on the response sentence template necessary for generating a response sentence corresponding to the user utterance sentence.

Hereinafter, an interactive service method for generating a response sentence according to a user utterance style constructed as described above will be described in detail with reference to the accompanying drawings.

4 is a diagram illustrating an interactive service authentication method according to a user utterance style according to an embodiment of the present invention.

Referring to FIG. 4, in step 1101, the interactive service apparatus 100 determines whether an input signal for user utterance has been received through the interface unit 120. When an input signal for user utterance is received, The interactive service apparatus 100 confirms the sentence about the user utterance and analyzes the user utterance sentence. Here, the sentence verification for the user utterance can be performed by verifying the user utterance inputted by voice through the voice conversion module (not shown) or the like to confirm the user utterance sentence, and a detailed description thereof will be omitted.

To describe the user utterance sentence analysis in detail, the interactive service apparatus 100 analyzes the morpheme of the user utterance sentence, and assigns a part of speech tag to each analyzed morpheme. The interactive service device 100 then recognizes the entity name and one or more semantic qualities in each morpheme analyzed and applies a language pattern (LSP) preset to the recognized entity name and one or more recognized semantic qualities, Analyze the meaning of the sentence. At this time, the interactive service apparatus 100 grasps the user's utterance style according to one or more recognized qualities. Here, the method for analyzing the meaning of the user utterance sentence and for grasping the user uttered style has been described in detail in the operation description of the personal utterance style profile generation module 111 and the response sentence generation module 112 according to the attached FIG. 1 A detailed description thereof will be omitted.

Then, in step 1103, the interactive service apparatus 100 extracts the actual morpheme of the recognized entity name and the semantic feature according to the user utterance style in the form of the recognized entity name (place + survey) and the semantic qualification Create a user's personalized speech style profile, including format morphemes. For example, the interactive service apparatus 100 may include the name of the entity (place + inquiry: to Seoul Station +) and the meaning qualities (move_subscription + mother: start) And stores the generated personalized speech style profile in the personalized speech style profile DB 132. Here, the personalized utterance style profile may be mapped and stored in association with one or more semantic qualities (for example, a +, a +, a +, etc.) according to a user's various utterance styles .

Thereafter, in step 1104, the interactive service apparatus 100 searches the response sentence template DB 133 based on the recognized entity name and semantic qualities of the user utterance sentence (substantial morpheme and morpheme morpheme) .

Then, in step 1105, the interactive service apparatus 100 confirms the semantic qualities (hereinafter referred to as response semantic qualities) used in the read response sentence template, and then stores the actual morpheme and formal morpheme corresponding to the confirmed semantic qualification The main morpheme and morpheme morpheme for the most used semantic feature among the corresponding semantic qualities stored in the utterance style profile DB 132 is read and the response sentence is generated by applying the read actual morpheme and morpheme morpheme to the response semantic feature . For example, the interactive service apparatus 100 can recognize the recognized object name (place + inquiry: to Seoul Station +) and the recognized meaning property (move_subject + (Place + survey, move_directive + response_memory) corresponding to the corresponding response sentence template and reads the recognized object name (to Seoul Station) in the object name (place + survey) of the response sentence template And maps the " ~ "for the translation term read from the personalized speech style profile DB 132 to the translation term " response " Accordingly, the interactive service apparatus 100 generates a response sentence of "Go to Seoul Station ", and additionally generates an additional response sentence (" scheduled arrival time is 3:00 ").

Accordingly, in step 1106, the interactive service apparatus 100 transmits a generated response sentence, for example, "Go to Seoul station. (I.e., an output module (not shown)) to the user.

Embodiments in accordance with the present invention may be implemented by various means, for example, hardware, firmware, software, or a combination thereof. In the case of hardware implementation, an embodiment of the present invention may include one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs) field programmable gate arrays, processors, controllers, microcontrollers, microprocessors, and the like.

In addition, in the case of an implementation by firmware or software, an embodiment of the present invention may be embodied in the form of a module, a procedure, a function, and the like for performing the functions or operations described above, Lt; / RTI > Here, the recording medium may include program commands, data files, data structures, and the like, alone or in combination. Program instructions to be recorded on a recording medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. For example, the recording medium may be an optical recording medium such as a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, a compact disk read only memory (CD-ROM), a digital video disk (DVD) Optical media such as a floppy disk and a hardware device specifically configured to store and execute program instructions such as ROM, RAM, flash memory and the like. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like. Such hardware devices may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, It will be apparent to those skilled in the art. Furthermore, although specific terms are used in this specification and the drawings, they are used in a generic sense only to facilitate the description of the invention and to facilitate understanding of the invention, and are not intended to limit the scope of the invention. Accordingly, the foregoing detailed description is to be considered in all respects illustrative and not restrictive. The scope of the present invention should be determined by rational interpretation of the appended claims, and all changes within the scope of equivalents of the present invention are included in the scope of the present invention.

In addition, a device or terminal according to the present invention may be driven by instructions that cause one or more processors to perform the functions and processes described above. Such instructions may include, for example, interpreted instructions such as script commands, such as JavaScript or ECMAScript commands, or other instructions stored in executable code or computer readable media. Further, the apparatus according to the present invention may be implemented in a distributed manner across a network, such as a server farm, or may be implemented in a single computer device.

Further, a computer program (also known as a program, software, software application, script or code) that is embedded in the apparatus according to the present invention and which implements the method according to the present invention includes a compiled or interpreted language, a priori or procedural language , And may be deployed in any form including standalone programs or modules, components, subroutines, or other units suitable for use in a computer environment. A computer program does not necessarily correspond to a file in the file system. The program may be stored in a single file provided to the requested program, or in multiple interactive files (e.g., a file storing one or more modules, subprograms, or portions of code) (E.g., one or more scripts stored in a markup language document). A computer program may be deployed to run on multiple computers or on one computer, located on a single site or distributed across multiple sites and interconnected by a communications network.

Moreover, in describing the embodiments according to the present invention, operations are depicted in the drawings in a particular order, but it is to be understood that they should perform such operations in that particular order or sequential order shown in order to obtain the desired result, Should not be understood as being performed. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the described program components and systems will generally be integrated together into a single software product or packaged into multiple software products It should be understood.

The present invention relates to an interactive service apparatus and method according to a user utterance style, in which a meaning of a user utterance sentence is analyzed to grasp a user utterance intention, and a user having various semantic qualities for expressing a user utterance intention in a user utterance sentence By generating a personalized speech style profile by grasping the speech style, the user can generate a response sentence by applying the most frequently used speech style in generating a response sentence, so that the user can be more friendly It is possible to provide a natural response sentence.

In addition, the present invention has a possibility of commercial use or business, and is industrially applicable because it is practically possible to carry out clearly.

100: interactive service device 110:
111: Personal Talking Style Profile Creation Module
112: response sentence generation module 120:
130: Storage unit 131: Object name and meaning Qualitative DB
132: Personalized speech style profile DB 133: Response sentence template DB

Claims (13)

An interface unit for receiving a user utterance sentence according to user utterance; And
The user recognizes the user utterance sentence transmitted from the interface unit, analyzes the meaning of the user uttered sentence, grasps the user utterance style according to the meaning of the analyzed user utterance sentence, A control unit for generating and storing a style profile and generating a response sentence corresponding to the user utterance based on the stored personal utterance style profile;
And an interactive service device. The method according to claim 1,
A storage unit for storing the generated personalized speech style profile and storing a predetermined response sentence template used in the response sentence;
Further comprising: an interactive service device operatively coupled to the interactive service device. The apparatus of claim 1,
A personalized utterance style profile generation module for analyzing the meaning of the user utterance sentence, determining a user utterance style according to the meaning of the analyzed user utterance sentence, and generating a personal utterance style profile according to the grasped user utterance style; And
A response sentence generation module for generating a response sentence according to the user utterance based on the personalized utterance style profile generated by the user utterance style profile generation module;
And an interactive service device. 4. The method of claim 3, wherein the user utterance style profile generation module comprises:
Wherein the meaning of the user utterance sentence is analyzed by applying a LSP (Lexico Syntactic Pattern) expressing sentence forms having the same meaning to each analyzed morpheme. 5. The method according to claim 4,
Wherein the information includes at least one of an object name, a semantic feature, a vocabulary, and a part of speech tag according to a concept of the user utterance sentence. 4. The method of claim 3, wherein the user utterance style profile generation module comprises:
An analyzer for analyzing a morpheme of the user utterance sentence;
A morpheme tag that assigns part mark tags to each analyzed morpheme;
Recognizing the entity name and at least one semantic feature in each analyzed morpheme, analyzing the meaning of the user utterance sentence by applying the recognized entity name and a predefined phrase pattern to the recognized one or more semantic features, An entity name and a semantic qualifier for analyzing a user utterance style according to one or more semantic qualities; And
A personalized utterance style profile generator for generating and storing a personalized utterance style profile according to the analyzed user utterance style based on the recognized entity name and the actual morpheme and formal morpheme of the recognized meaning qualifier;
And an interactive service device. 4. The apparatus of claim 3, wherein the response sentence generation module comprises:
Reading out the pre-stored speech sentence template corresponding to the recognized entity name and the semantic feature, reading the actual morpheme and morpheme morpheme corresponding to the response semantic qualities used in the read speech sentence template from the stored personal speech style profile DB, And the response sentence is generated by applying the actual morpheme and the morpheme of the read out semantic feature to the response semantic feature. The method of claim 7, wherein the response sentence generation module comprises:
A response sentence is generated by combining the recognized entity name with the actual morpheme and the morpheme morpheme of the read out semantic feature, and an additional response sentence is added to the generated response sentence to generate a final response sentence to be presented to the user Interactive service device. Recognizing the inputted user utterance sentence;
Analyzing the meaning of the identified user utterance sentence;
Determining a user utterance style according to the meaning of the analyzed user utterance sentence;
Generating a personalized utterance style profile according to the identified user utterance style; And
Generating a response sentence corresponding to the user utterance based on the stored personal utterance style profile;
The interactive service method according to claim 1, 10. The method of claim 9, wherein analyzing the semantics of the user utterance sentence comprises:
Analyzing the morpheme of the user utterance sentence;
Assigning speech tags to each analyzed morpheme;
Recognizing an entity name and at least one semantic feature for each analyzed morpheme; And
Analyzing the meaning of the user utterance sentence by applying a recognized utterance pattern to the recognized entity name and the recognized one or more sense qualities;
The interactive service method according to claim 1, 10. The method of claim 9, wherein generating a response sentence corresponding to the user utterance based on the stored personalized utterance style profile comprises:
Reading a previously stored speech sentence template corresponding to the recognized entity name and semantic qualification;
Reading the actual morpheme and morpheme morpheme corresponding to the response semantic qualities used in the read speech sentence template from the stored personal speech style profile DB; And
Generating a response sentence by applying a substantial morpheme and a morpheme morpheme of the read semantic feature to the response semantic feature;
The interactive service method according to claim 1, 12. The method of claim 11, wherein generating a response sentence corresponding to the user utterance based on the stored personal utterance style profile comprises:
Reading a response sentence template for generating an additional response sentence; And
Generating an additional response sentence using a response sentence template for generating a readout additional response sentence;
Wherein the interactive service device is further configured to display the interactive style of service according to a style of user's utterance in the interactive service device. A computer-readable recording medium having recorded therein a program for executing an interactive service method according to at least one user utterance style according to any one of claims 9 to 12.

Images