KR20150054045A - Chain Dialog Pattern-based Dialog System - Google Patents

Abstract

The present invention relates to a chain dialog pattern-based dialog system and, more specifically to a technology enabling a dialog between a user and a system based on a dialog pattern. The chain dialog pattern-based dialog system according to an embodiment of the present invention comprises: a voice recognition unit recognizing spoken sentences from the user; and a dialog pattern-based dialog processing unit producing a dialog pattern of the spoken sentences recognized by the voice recognition unit, extracting a system speaking pattern according to the dialog pattern of the user, and providing the result to the user.

Description

{Chain Dialog Pattern-based Dialog System}

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a chained conversation pattern based dialogue system, and more particularly, to a technique for enabling conversation between a system and a user based on a conversation pattern.

As English is becoming an international language, we are trying to learn English more effectively in non - English speaking countries including Korea. However, existing English teaching methods did not help much to improve English conversation skills by using memorizing English education methods based on vocabulary and grammar.

In order to improve English conversational skills, multimedia teaching methods using audio and video have been developed. However, if learners follow simple words or sentences, they analyze and evaluate pronunciation of learners and feed them back to learners. It is not out of bounds.

An embodiment of the present invention provides a chained conversation pattern-based dialog system that automatically constructs a conversation pattern using basic noun phrase chunks and structure analysis, and facilitates conversation between the user and the system using the established conversation pattern.

According to an embodiment of the present invention, there is provided a chained conversation pattern based dialogue system comprising: a speech recognition unit for recognizing a speech sentence from a user; And a conversation pattern-based dialog processing unit for generating a conversation pattern of the user utterance sentence recognized through the voice recognition unit, extracting a system utterance pattern according to the conversation pattern of the user utterance, and providing the extracted utterance pattern to the user.

The conversation pattern-based dialog processing unit may include: a dialog scenario processing unit for extracting a system utterance sentence corresponding to the user utterance sentence; And a dialog pattern processing unit for generating a user utterance pattern from the user utterance sentence and extracting a system utterance pattern corresponding to the user utterance pattern when the system utterance sentence does not exist.

The dialog scenario processing unit may include a morpheme analyzing unit for analyzing the user utterance sentence by morpheme units; A dialog scenario storage unit for storing the system utterance sentence; A user utterance sentence matching unit for searching, in the conversation scenario storage unit, whether a system utterance sentence corresponding to the morpheme analyzed user utterance sentence exists; And a system utterance sentence extracting unit for extracting the system utterance sentence when the system utterance sentence exists.

The conversation pattern processing unit may further include: a conversation pattern generation unit that generates a user utterance pattern from the user utterance sentence; A conversation pattern storage unit for storing a system conversation pattern; A user utterance pattern matching unit for searching the conversation pattern storage unit for a system utterance pattern corresponding to the user utterance pattern; And the system utterance pattern extracting unit that extracts the system utterance pattern from the conversation pattern storage unit when the system utterance pattern corresponding to the user utterance pattern is retrieved.

Also, the dialog pattern generation unit may include: a basic noun phrase dialing unit for replacing the noun phrase of the user utterance sentence with a first symbol; A semantic code storage unit for storing a semantic code for each noun; A basic noun phrase meaning attaching unit for extracting a keyword of a noun phrase of the user utterance sentence and searching for a meaning of the keyword through the meaning code storage unit and attaching the keyword to a user utterance sentence in which the meaning code of the keyword is replaced with the first symbol; And a sentence structure analyzing unit for analyzing the sentence structure of the user uttered sentence to which the semantic code is attached.

Also, the sentence structure analyzing unit may replace the short sentence connected to the conjunction through the sentence structure analysis with the second symbol.

The apparatus may further include a basic noun phrase matching unit for performing numbering on the first symbol of the user utterance pattern and unifying the first noun phrase with the first symbol number.

Further, the morpheme analyzing unit may change the system utterance sentence to a circle.

The apparatus may further include a morpheme generator for generating a prototype system utterance sentence extracted from the dialog scenario processing unit by changing the system utterance sentence to the same tense as the user utterance sentence.

The apparatus may further include a basic noun phrase generating unit for generating a system utterance sentence by inverting the first symbol or the second symbol of the system utterance pattern received from the conversation pattern processing unit into a short phrase connected to a noun phrase or a conjunction.

This technology has a high effectiveness of the chain dialogue by automatically constructing the dialog pattern and managing the dialog between the system and the user by using the dialog pattern.

In addition, since the technology can construct a large-capacity chained conversation pattern only by knowledge of the basic noun phrase, the performance of the conversation system can be improved in a short period of time.

1 is a configuration diagram of a chained conversation pattern-based dialog system according to an embodiment of the present invention.
FIG. 2 is a detailed block diagram of the dialog pattern-based dialog processing unit of FIG. 1. FIG.
3 to 4 are flowcharts illustrating a chained conversation pattern-based conversation method according to an embodiment of the present invention.
5 is a flowchart illustrating a method of constructing a conversation pattern storage unit according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, in order to facilitate a person skilled in the art to easily carry out the technical idea of the present invention.

Field of the Invention [0001] The present invention relates to a cascaded dialog system based on a pair or a continuous pair of conversation patterns, and more particularly to a dialogue system in which a user constructs a conversation scenario and automatically constructs a conversation pattern using basic noun phrase chaining and structure analysis The present invention also relates to a chained conversation pattern-based dialog system in which conversation is managed by managing a chained conversation pattern with respect to the conversation. Here, the conversation pattern is a regular chain of user utterances corresponding to system utterances. By using the system utterance and the user utterance as a pair of input and output, it is transformed into a high-coverage dialogue pattern, thereby providing a highly interactive domain-based dialogue system can do.

Hereinafter, a chained conversation pattern based dialog system according to an exemplary embodiment of the present invention will be described with reference to FIGS. 1 to 5. FIG.

1 is a configuration diagram of a chained conversation pattern-based dialog system according to an embodiment of the present invention.

Referring to FIG. 1, a chained conversation pattern-based dialog system 10 according to an embodiment of the present invention includes an interactive speech recognition unit 100, a dialog pattern-based dialog processing unit 200, and a conversation voice generation unit 300 .

The conversation voice recognition unit 100 recognizes a voice as a character when a voice is input from the user 20, and transmits the voice to the conversation pattern-based conversation processing unit 200. [

When the user utterance is input, the conversation pattern-based dialog processing unit 200 analyzes the user utterance in morphological units, determines whether the system utterance sentence corresponding to the user utterance sentence in which each morpheme is changed into a circular form is stored, The stored system spoken sentence is extracted and the system spoken sentence is changed in accordance with the characteristics of the user utterance (for example, modification based on the tense or grammar).

If the system utterance sentence is not stored, the dialog pattern-based dialog processing unit 200 replaces the basic noun phrase with a specific symbol (NP) for the user utterance sentence, extracts the keyword from the NP, And a sentence associated with the conjunction is replaced with a specific symbol (S: sentence) through a syntax analysis to form a user utterance pattern. Determines whether the user utterance pattern thus formed is stored, and extracts the stored system utterance pattern when the system utterance pattern corresponding to the user utterance pattern is stored. Then, NP is again reduced to the basic noun phrase, and S is inverted to the sentence associated with the conjunction, and then the system utterance sentence is changed according to the characteristics of the user utterance (for example, the tense and the grammatical variation).

The conversation voice generation unit 300 generates a system utterance sentence generated on the basis of the conversation pattern by the conversation pattern based conversation processing unit 200 by voice.

The present invention does not separately disclose an input unit for receiving a user's voice and an output unit for outputting voice data of the system, but may include a microphone, a speaker, and the like, which corresponds to a typical configuration.

Hereinafter, the detailed structure of the dialog pattern-based dialog processing unit 200 of FIG. 1 will be described in detail with reference to FIG.

Referring to FIG. 2, the dialog pattern-based dialog processing unit 200 includes a dialog scenario processing unit 210, a dialog pattern processing unit 220, a basic noun phrase generating unit 230, and a morpheme generating unit 240.

The dialog scenario processing unit 210 analyzes the morpheme of the user utterance sentence input from the user 20 and judges whether or not the user uttered sentence is stored. If the user uttered sentence is stored, the system scenario utterance corresponding to the user uttered sentence is extracted And transmits it to the morpheme generator 240.

To this end, the dialog scenario processing unit 210 includes a morphological analysis unit 211, a user utterance sentence matching unit 212, a system utterance sentence extraction unit 213, and a dialogue scenario storage unit 214.

The morpheme analysis unit 211 analyzes the user utterance sentence in morpheme units. For example, we distinguish morphemes that form sentences such as nouns, verbs, adjectives, adverbs, and articles. In addition, the morpheme analysis unit 211 analyzes the verb tense, adjective, and adverbial deformation of the user utterance sentence, and converts it into a circular form. That is, the morpheme analysis unit 211 changes the verb tense, the adjective, and the adverbial transformation of the user utterance sentence into a verb form, an adjective form, and an adverbial form.

The user utterance sentence matching unit 212 searches whether or not the system utterance sentence corresponding to the circular user utterance sentence changed to the circle is stored in the dialogue scenario storage unit 214. [ At this time, the system utterance sentence is also stored in a circular state.

The system utterance sentence extracting unit 213 extracts a system utterance sentence corresponding to the user utterance sentence from the conversation scenario storage unit 214. [

The dialogue scenario storage unit 214 stores various dialogue scenarios in a circular form as shown in Table 1 below.

[KEY] dscenario @ favorite-season
[CONTENT]
{S: What's your favorite season?} -> {U: My favorite season be spring.}
{U: My favorite season be spring} -> {S: Why be it your favorite?
{UP: I like spring} -> {S: Why be it your favorite?}
{S: Why do you like it?} -> {U: Spring be my favorite season because it is not too cold or too hot}
{U: Spring be my favorite season because it's not too cold or too hot} -> {S: Which season do you like the least?
{S: Which season do you like the least?} -> {U: I do not like winter}

The conversation pattern processing unit 220 replaces the basic noun phrase with the specific symbol (NP) for the user utterance sentence, extracts the keyword from the NP, and attaches the meaning code of the keyword. Thereafter, the conversation pattern processing unit 220 forms a user utterance pattern by replacing the sentence associated with the conjunction with the specific symbol S through a syntax analysis. Then, the conversation pattern processing unit 220 determines whether the user utterance pattern formed as described above is stored, extracts the stored system utterance pattern when the system utterance pattern corresponding to the user utterance pattern is stored, To the generation unit (230).

The speech pattern processing unit 220 includes a dialog pattern generation unit 229, a user speech pattern matching unit 226, a system speech pattern extraction unit 227, and a dialog pattern storage unit 228.

The dialog pattern generating unit 229 generates a dialog pattern and includes a basic noun phrase chunking unit 221, a basic noun phrase sense attaching unit 222, a semantic code storage unit 223, a sentence structure analyzing unit 224, And may include a numbered portion 225.

The basic noun phrase syllable part 221 replaces the noun phrase with a specific symbol (NP) when there is a noun phrase in the result of morphological analysis of the user utterance sentence. For example, if "What is your favorite season?" Is a user utterance sentence, "NP is replaced by NP", and "What is NP1?"

The basic noun phrase sense attaching unit 222 extracts the keyword from the NP and extracts the meaning code of the keyword from the meaning code storage unit 223 and attaches it to the replaced user utterance sentence. At this time, the keyword is the rightmost word of the NP. For example, if NP is "your favorite season", the rightmost word "season" is the keyword. The semester code for "season" becomes "time" and is attached to NP1 = season @ time @ "your favorite season".

The semantic code storage unit 223 stores a semantic code for each word.

The sentence structure analysis unit 224 replaces all sentences (Simple sentences) connected with the conjunction through S by parsing the user utterance sentence. For example, if the user spoken sentence is "Spring is a favorite season because it is not too cold or too hot," substitute S for "it's not too cold or too hot" favorite season because S ", which can be" NP5 is NP6 because S "when NP substitution and semantic attachment are both performed.

The basic noun phrase unit number assigning unit 225 assigns NP0 to the NP for the subject that is currently uttering, and NP # having the same key word and meaning has the same number NP # to complete the user utterance pattern. That is, the same number is assigned to overlapping noun phrases in the dialog pattern.

The user utterance pattern matching unit 226 searches the conversation pattern storage unit 228 for a system utterance pattern corresponding to the user utterance pattern.

The system utterance pattern extraction unit 227 extracts a system utterance pattern corresponding to the user utterance pattern from the conversation pattern storage unit 228 and transmits the extracted system utterance pattern to the basic nominal phrase generation unit 232.

The conversation pattern storage unit 228 stores conversation patterns including system utterance patterns substituted with NP and S in advance and attached with meaning to key words as shown in Table 2 below. That is, the conversation pattern means a collection of speech patterns. A method of generating and constructing a dialog pattern in the dialog pattern storage unit 228 will be described in detail with reference to FIG.

{S: What is NP0? // my favorite season ", NP3 = spring @ time @" NP0 is NP3 // NP1 = NP0, NP0 = season @ "Spring"}

{U: NP0 is NP3 // NP2 = NP0, NP0 = season @ time @ "my favorite season", NP3 = spring @ time @ "spring"} -> {S: Why is it NP0? // NP4 = NP0, NP0 = season @ time @ "your favorite"}

{UP: I like NP3 // NP3 = spring @ time @ "spring"} -> {S: Why is it NP0? // NP4 = NP0, NP0 = season @ time @ "your favorite"}

{S: Why is it NP0? // NP3 = NP0 = NP0, // NP3 = spring @ time @ "spring", NP0 = NP0 = NP0, NP0 = season @ time @ "your favorite" = season @ time @ "my favorite season", S = "it's not too cold or too hot"}

{U: NP3 is NP0 because S // NP5 = NP3, NP6 = NP0, // NP3 = spring @ time "spring", NP0 = season @ time @ "my favorite season", S = or too hot "} -> {S: Which NP0 do you like the least? // NP7 = NP0, // NP0 = season @ time @ "season"}

{S: Which NP0 do you like the least? // NP8 = winter @ time @ "winter"} -> {U: I do not like NP8 // NP0 =

The basic noun phrase generation unit 230 inverses the specific symbols (NP, S) of the system utterance pattern output from the conversation pattern processing unit 220 to a short sentence connected to the basic noun phrase and the conjunction, and then transmits the short word to the morpheme generation unit 240.

The morpheme generation unit 240 generates a morpheme sentence sent from the dialog scenario processing unit 210 and the system utterance sentence and the basic noun phrase generation unit 230 to generate a system utterance sentence according to the characteristics of the user utterance sentence .

Hereinafter, a chained conversation pattern-based conversation method according to an embodiment of the present invention will be described in detail with reference to FIG. 3 to FIG.

Referring to FIG. 3, when a user inputs a speech (S101), the morpheme analysis unit 211 performs morpheme analysis on the user's speech (S102). That is, the user's utterance sentence is divided into morpheme units, and the modification of the word, such as the tempo modification, is changed into the circular state of the word.

Thereafter, it is determined whether a system utterance sentence corresponding to the user utterance sentence analyzed in the morpheme unit exists in the dialogue scenario storage unit 214 (S103).

If there is a system utterance sentence corresponding to the user utterance sentence in the conversation scenario storage unit 214, the system utterance sentence extraction unit 213 extracts a system utterance sentence corresponding to the user utterance sentence (S104).

At this time, since the extracted system utterance sentence is in a circular state, the morpheme generation unit 231 changes it according to the result of the morpheme analysis and morphing analysis of the user utterance sentence, which is input first, at step S105.

Meanwhile, a case (A) in which the system utterance sentence corresponding to the user utterance sentence is not present in the dialogue scenario storage unit 214 in the above-described step S103 will be described in detail with reference to FIG.

That is, when the system utterance sentence corresponding to the user utterance sentence does not exist in the dialogue scenario storage unit 214, the morpheme analyzed user utterance sentence is transmitted to the dialogue pattern processing unit 220.

The basic noun phrasing chunning unit 221 replaces the basic noun phrase of the morpheme analyzed user utterance sentence with NP (S106).

Then, the basic noun phrase sense attaching unit 222 extracts a keyword from the NP, fetches a meaning code for the keyword from the meaning code storage unit 223, and attaches the meaning code to the replaced user utterance sentence (S107).

Then, the sentence structure analyzer 224 performs a syntax analysis to generate a user utterance pattern by replacing the short sentence connected to the conjunction with S (S108).

The user utterance pattern matching unit 226 searches whether the system utterance pattern corresponding to the user utterance pattern thus generated exists in the conversation pattern storage unit 228 (S109).

When the system utterance pattern corresponding to the user utterance pattern exists in the conversation pattern storage 228, the system utterance pattern extractor 247 extracts the system utterance pattern corresponding to the user utterance pattern from the conversation pattern storage 228 And transmits it to the basic noun phrase generation unit 232 (S110).

Then, the basic noun phrase generation unit 232 generates a system utterance sentence by inverting NP and S of the system utterance pattern with the basic noun phrase, and transmits the generated system utterance sentence to the morpheme generation unit 231 (S111)

Then, the morpheme generator 231 changes the backward-replaced system utterance sentence according to the user utterance sentence characteristics (e.g., tense, deformation, etc.) (S112).

Hereinafter, a method for constructing a dialog pattern storage unit according to an embodiment of the present invention will be described with reference to FIG.

First, when a system and a user utterance scenario are input (S201), the morpheme analysis unit 211 performs morpheme unit analysis on the system and user utterance (S202). At this time, the analysis of the morpheme unit means to divide into morpheme units such as nouns, articles, adjectives, and verbs in user utterance sentences.

Subsequently, the basic noun phrase cheek unit 221 replaces the basic noun phrases with the NP as a result of the morphological analysis (S203).

Next, the basic noun phrase sense attaching unit 222 extracts the last word of the NP as a key word (S204), attaches the meaning code to the replaced user utterance sentence extracted from the semantic code dictionary for the extracted key word (S205).

Thereafter, the sentence structure analyzer 224 performs a structural analysis on the morpheme analysis result that is replaced with the NP (S206), and substitutes the simple sentence connected to the conjunction with S (S207). In other words, the structural analysis is to determine where the end of the sentence is connected to the conjunction.

Thereafter, the basic noun phrase number selector 228 completes the dialog pattern by matching the previous noun phrase of the topic tracking and the basic noun phrase numbers of the current utterance and the current utterance (S208), and stores the completed conversation pattern (S209) .

If the system utterance pattern corresponding to the user utterance pattern is not present in the conversation pattern storage unit 228 in step S109, the conversation system 10 may prompt the user to re- An utterance pattern for the utterance sentence may be generated and updated in the conversation pattern storage unit 228.

Hereinafter, a method of generating and storing a conversation pattern will be described in detail with reference to Tables 3 to 7.

In Table 3, S: refers to the dialog system, U: refers to users who are learners, and UP: refers to paradigm of U :. In the above dialogue scenario, the first column, " Speaking ", refers to the actual conversation between the teacher and the learner, which is actually collected for English conversation education.

Q: What is your favorite season?
U: My favorite season is spring.
UP: I like spring.
S: Why is it your favorite?
U: Spring is my favorite season because it's too cold or too hot.

In the dialogue scenario of Table 3 above, the second column, "Basic Noun phrase chunking", is the result of chunking and replacing the structures such as "noun", "article noun", and "article noun" with the basic noun phrase NP. "//" is followed by a speech expression for NP.

At this time, examples of the basic noun phrase for the dialog scenario are shown in Table 5 below.

Q: What is NP1? // NP1 = "your favorite season"
U: NP2 is NP3. // NP2 = "my favorite season", NP3 = "spring"
UP: I like NP3. // NP3 = "spring"
S: Why is it NP4? // NP4 = "your favorite"
U: NP5 is NP6 because S. // NP5 = "spring", NP6 = "my favorite season", S = "it's not too cold or too hot"

In the third column, "Keyword Extraction and Meaning Attachment" in the dialogue scenario above, the NP is serialized from the first utterance, and the original vocabularies chunked to NP after "//" are described.

Thereafter, the last word of the NP is extracted as a keyword in the basic noun phrase NP, and the meaning code is attached to the extracted keyword from the meaning code storage unit 223 as shown in Table 6 below.

Q: What is NP1? // NP1 = season @ time @ "your favorite season"
U: NP2 is NP3. // NP2 = season @ time @ "my favorite season", NP3 = spring @ time @ "spring"
UP: I like NP3. // NP3 = spring @ time @ "spring"
S: Why is it NP4? // NP4 = season @ time @ "your favorite"
U: NP5 is NP6 because S. // NP5 = spring @ time @ "spring", NP6 = season @ time @ "my favorite season", S = "it's not too cold or too hot"

NP1 = "your favorite season" of the first utterance of "Keyword Extraction and Meaning Attachment" in Table 6 above was that NP1's original utterance was "your favorite season" and its key word was season and meaning of season Means "@ time @".

In this way, the basic noun phrase chunking, key word extraction, and semantic-attached result for each sentence are compared with the basic noun phrase number matching process, which coherently links the NP numbers to the basic noun phrases of the previous utterance and the current utterance. Quot; conversation pattern " is made as shown in Table 7 below.

Q: What is NP0? // NP1 = NP0, NP0 = season @ time @ "your favorite season"
U: NP0 is NP3. // NP2 = NP0, NP0 = season @ time @ "my favorite season", NP3 = spring @ time @ "spring"
UP: I like NP3. // NP3 = spring @ time @ "spring"
S: Why is it NP0? // NP4 = NP0, NP0 = season @ time @ "your favorite"
U: NP3 is NP0 because S. // NP5 = NP3, NP6 = NP0, // NP3 = spring @ time "spring", NP0 = season @ time @ "my favorite season", S = or too hot "

In Table 7, the first speech S: What is NP0? // NP1 = NP0, NP0 = season @ Time In "your favorite season" NP1 = NP0 means that NP1 is the topic. Therefore, NPs with NP1 = season @ time @ "your favorite season" in subsequent utterances are all NP0. The last user call U: NP3 is NP0 because S. // NP5 = NP3, NP6 = NP0, // NP3 = spring @ time @ spring, NP0 = season @ NP5 is regarded as a topic because it has the same key word and meaning as NP3 of the previous utterance, so it is changed to NP3, and NP6 is the same key word and meaning as NP0.

<Examples>

Hereinafter, a process of actually talking with a conversation system and a user using each example of the conversation scenario storage unit 214 and the conversation pattern storage unit 228, which are assumed to be constructed above, will be described as an example.

First, let's assume that the conversation system asks the user the following questions.

[Interactive system question]

Q: What is your favorite season?

Suppose that the user replies as follows.

[Your answer]

U: I like summer.

The dialog system 10 sequentially searches for the user's answer "U: I like summer." In the dialogue scenario storage unit 214 and the dialog pattern storage unit 228. Since the &quot; U: I like summer. &Quot; is not present in the dialogue scenario storage unit 214 but has been searched in the dialogue pattern storage unit 228, the dialogue system 10 can generate a response thereto as follows.

[Search pattern DB]

{UP: I like NP3 // NP3 = spring @ time @ "spring"} -> {S: Why is it NP0? // NP4 = NP0, NP0 = season @ time @ "your favorite"}

[Conversation system answer]

S: Why is it your favorite?

Suppose that the user replies to the above dialog system's answer as follows.

[Your answer]

U: I like summer because I can get a tan in the hot sun.

The conversation system 10 sequentially searches the conversation pattern storage unit 228 for the user's answer &quot; U: I like summer because I can get a tan in the hot sun. &Quot; If the dialogue system 10 does not exist in the dialogue scenario storage unit 214 and the dialogue scenario storage unit 228 does not exist, Or may generate an utterance pattern for the corresponding user utterance sentence and update it in the conversation pattern storage unit 228. [

As described above, according to the configuration of the present invention, it is possible to improve the performance of the conversation system in a short period of time by providing a simple method of expressing a conversation pattern and facilitating automatic construction and flexibility of coping with an exception, It is possible to construct an interactive system that is highly useful in a real environment.

Accordingly, the present invention can be applied not only to the dialog system, but also to the dialogue automatic interpretation system, the chat translation system, and the interactive robot (Chat-Bot).

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, It should be regarded as belonging to the claims.

10: Conversation system 20: User
100: conversation voice recognition unit 200: conversation pattern-based conversation processing unit
300: Conversation speech generation unit 210: Conversation scenario processing unit
220: Conversation pattern processing unit 230: Conversation rule processing unit
211: morpheme analysis unit 212: user utterance sentence matching unit
213: system utterance sentence extracting unit 214: dialogue scenario storage unit
229: Dialogue pattern generation unit 221: Basic noun phrase area
222: basic noun phrase semantic attaching unit 223: semantic code storage unit
224: sentence structure analysis unit 225: basic noun phrase numeral unit
226: user utterance pattern matching unit 227: system utterance pattern extracting unit
228: Conversation pattern storage unit 230: Basic noun phrase generation unit
240: morpheme generator

Claims (1)

A speech recognition unit for recognizing an utterance sentence from a user; And
A dialog pattern-based dialog processing unit for generating a dialog pattern of the user spoken sentence recognized through the speech recognition unit, extracting a system spoken pattern according to the dialog pattern of the user spoken word,
Wherein the interactive dialog pattern-based dialog system comprises:

Images