KR20180116104A - Method and apparatus of dialog scenario database constructing for dialog system - Google Patents

Abstract

The present invention relates to a method for constructing a dialogue scenario database, and more specifically, to a method for constructing a dialogue scenario database for a dialogue system applied to an ontology dialogue network that automatically searches, collects, refines, and learns conversation scenarios from SNS, radio, and broadcasting to expand a conversation area automatically or improve conversation quality. To this end, the method for constructing a dialogue scenario database for a dialogue system applied to an ontology dialogue network comprises: a step (a) of extracting sentences by ID or name from a conversation-type voice file or a conversation-type article or comment; a step (b) of expressing a conversation sentence in tree form by ID or name according to conversation development of the article or a the comment from the sentence extracted in the step (a); a step (c) of extracting a dialog scenario from each tree of the step (b); a step (d) of expressing each sentence of the dialogue scenario generated in the step (c) as a semantic vector; a step (e) of expressing each sentence of the dialogue scenario generated in the step (d) by an intent pattern; a step (f) of constructing a database of the conversation scenario by the intent pattern and the semantic vector; and a step (g) of creating a new intention pattern with respect to an existing sentence having no intention pattern in the step (e).

Description

FIELD OF THE INVENTION [0001] The present invention relates to a method and apparatus for constructing a dialogue scenario database for a dialogue system,

The present invention relates to the construction of a dialogue scenario database, and more particularly, to an ontology dialogue service in which dialogue scenarios are automatically searched, collected, refined, and learned in SNS, radio, And a dialogue scenario database construction method for an interactive system applied to a network.

Humans have long dreamed to communicate naturally with people other than humans. Artificial Intelligence (AI) and Big Data are driving the fourth industrial revolution, and at the core of artificial intelligence is the natural dialog communication between humans and objects.

However, until now, the dialogue scenarios have been costly, time-consuming, and labor-intensive, since people manually build the scenarios by refining them. This allows people to collect and refine their own scenarios, which will require a relatively long time, which will allow them to engage in conversations in the past, allowing immediate conversations about current incidents or accidents, trends or issues. I did not.

That is, since only a limited dialogue is used in a limited area, there is a limitation in expanding the dialog area or improving the conversation quality.

KR 10-0444568 KR 0326931 KR 10-2012-0146174

It is an object of the present invention to provide an ontology dialogue network in which dialogue scenarios are automatically searched, collected, refined, and learned in SNS, radio, and broadcasting, The present invention provides a method for constructing a dialogue scenario database for an interactive system applied to a dialogue scenario.

According to another aspect of the present invention, there is provided a method for constructing a dialog scenario database for an interactive system applied to an ontology dialog network, the method comprising the steps of: (a) Extracting a sentence; (b) expressing a conversation sentence in tree form by ID or name according to conversation development of a comment or a comment from the sentence extracted in the step (a); (c) extracting a dialog scenario from each tree of step (b); (d) expressing each sentence of the dialog scenario generated in the step (c) as a semantic vector; (e) expressing each sentence of the dialogue scenario generated in the step (d) in an intent pattern; (f) databaseing the conversation scenario into an intent pattern and a semantic vector; And (g) creating a new intention pattern in the sentence without the existing intention pattern in the step (e).

Preferably, the step (e) further comprises the step of displaying the continuous semantic vector converted into the database on the ontology multidimensional space as one of a semantic word, a semantic node and a semantic cube.

Preferably, the interactive speech file of step (a) is extracted after being converted into text through speech recognition.

Preferably, the step (a) extracts a specific word (word) from a conversation-type article, and parses and extracts the posts and comments retrieved with the specified search term.

Preferably, the sentence extracted in step (a) is automatically converted into a semantic vector.

According to another aspect of the present invention, there is provided a communication system including a dialog scenario extracting unit for extracting a dialog scenario; A dialogue scenario learning unit for learning each sentence of the dialogue scenario generated by the dialogue scenario extracting unit; A dialogue scenario intention pattern classifying unit for classifying intention patterns of each sentence of the dialogue scenario by using the semantic vector generated by the dialogue scenario learning unit; An intention pattern generator for generating a new intention pattern for an intention pattern not classified by the intention pattern classifier of the dialog scenario; A dialog scenario database storing the dialog pattern intention patterns and the semantic vectors; And an ontology relationship mapping unit for displaying a continuous semantic vector and an intent pattern of the conversation scenario stored in the conversation scenario database on an ontology multidimensional space.

According to the present invention, it is possible to reduce the construction cost of the dialogue scenario by automating the dialogue scenario collection, refinement, and construction.

In addition, if a person directly collects scenarios, it takes a lot of time to refine and construct them, so that conversations are made in the past. However, since conversation scenarios are automatically collected and reflected in conversations, So that the conversation quality can be improved.

In addition, since conversation scenarios are constantly collected on various topics, it is possible to have conversations on topics reflecting various perspectives.

1 is a flowchart for explaining a method of constructing a dialogue scenario database for an interactive system according to the present invention;
Figure 2 schematically illustrates a database building apparatus for a dialog scenario for an interactive system according to the present invention;
3 is a detailed view of a database construction apparatus of a dialogue scenario for the dialog system according to FIG.
FIG. 4 to FIG. 5 are views illustrating an example of sentence extraction during the construction of a dialogue scenario database for the dialog system according to the present invention;
6 is a screen showing an example of sentence analysis during construction of a dialogue scenario database for the dialog system according to the present invention;
7 is a screen showing an example of conversation scenario learning during construction of a conversation scenario database for the conversation system according to the present invention;
8 illustrates an example of a dialog scenario database for an interactive system constructed in accordance with the present invention displayed on an ontology dialogue network;
9 is an example of a dialog scenario stored in a dialogue scenario database according to the present invention;
10 is a screen in which the dialog scenario stored in the dialog scenario data face according to the present invention is expressed by a three-dimensional authoring tool.
11 is an example of a scenario input screen in which a dialog scenario stored in the dialog scenario database according to the present invention is expressed by a three-dimensional authoring tool.
12 is an example of a scenario modification screen in which a dialog scenario stored in the dialog scenario database according to the present invention is expressed by a three-dimensional authoring tool.
13 is an example of a screen for deleting a scenario in which a dialog scenario stored in the dialog scenario database according to the present invention is represented by a 3D authoring tool.
FIG. 14 is a block diagram showing a sequence in which continuous conversation is performed using the conversation scenario automatic collection and ontology conversation network according to the present invention; FIG.
15 is a flowchart showing a sequence in which continuous conversation is performed using the conversation scenario automatic collection and the ontology conversation network according to the present invention.
FIG. 16 is a flow chart illustrating a method of mapping a new conversation sentence into an ontology conversation network when a new conversation sentence is input, in a continuous conversation using the ontology conversation network according to the present invention.
FIG. 17 is a block diagram illustrating a sequence for implementing conversation quality improvement using continuous conversation using an ontology conversation network according to the present invention; FIG.
18 is a diagram showing a configuration of a continuous conversation system using an ontology conversation network according to the present invention;
19 illustrates an embodiment of an ontology talk network structure according to the present invention.
20 illustrates an embodiment of a general conversation classification structure in an ontology conversation network according to the present invention;
FIG. 21 illustrates an embodiment of a professional conversation classification structure in an ontology conversation network according to the present invention; FIG.
22 is a diagram illustrating an example of a conversation classification structure to be exchanged with an agent in a hospital call center during a professional conversation in an ontology conversation network according to the present invention;
23 illustrates an example of a classification structure in which a daily conversation, an emotional conversation, and a professional conversation are connected in an ontology conversation network according to the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. Prior to this, terms and words used in the present specification and claims should not be construed as limited to ordinary or dictionary terms, and the inventor should appropriately interpret the concepts of the terms appropriately It should be interpreted in accordance with the meaning and concept consistent with the technical idea of the present invention based on the principle that it can be defined. Therefore, the embodiments described in this specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention and do not represent all the technical ideas of the present invention. Therefore, It is to be understood that equivalents and modifications are possible.

1 is a flowchart illustrating a method for constructing a dialogue scenario database for a dialog system according to the present invention.

In the dialogue scenario database building method for the dialog system according to FIG. 1, a sentence is extracted first (S110). Extraction of a sentence extracts a sentence by ID or name from conversation type voice file or conversation type comment, comment.

If a sentence is extracted in step S110, the dialogue sentence is expressed in tree form by ID or name according to the conversation development of the comment or comment from the extracted sentence (S120).

Then, a dialog scenario is extracted from each tree expressed in step S120 (S130), and each sentence in the generated dialog scenario is represented by a semantic vector (S140).

Subsequently, each sentence of the generated dialog scenario is expressed as an intention pattern (S150), and the dialog scenario is converted into a database by using the intention pattern and the semantic vector (S160).

Here, the sentence without the existing intention pattern creates a new intention pattern (S170)

Continuous semantic vectors and semantic vectors of the scenario thus database are continuously displayed on the ontology multidimensional space (S160).

The method for constructing a dialog scenario database for the dialog system of the present invention shown in FIG. 1 will be described with reference to a dialogue scenario database establishing apparatus for the dialog system of FIGS.

FIG. 2 is a view schematically showing an apparatus for constructing a dialogue scenario database for an interactive system according to the present invention, and FIG. 3 is a detailed view illustrating an apparatus for constructing a dialogue scenario database for the interactive system according to FIG.

2 to 3, an apparatus 100 for constructing a dialogue scenario database for an interactive system according to the present invention includes a sentence extraction unit 110 for extracting a sentence, a sentence extraction unit 110 for extracting a sentence extracted by the sentence extraction unit 110, A semantic vector extracting unit 130 for extracting a semantic vector from each sentence extracted by the scenario extracting unit 120, a semantic vector extracting unit 130 for extracting a semantic vector from the sentence extracted by the scenario extracting unit 120, An intention pattern generating unit 150 for generating an intention pattern that can not be classified by the intention pattern classifying unit 140, an intention pattern generating unit 150 for converting a conversation scenario into an intention pattern and a semantic vector, An ontology relationship mapping unit 17 for displaying successive intention patterns and semantic vectors of the dialog scenario stored in the dialog scenario database 160 on the ontology multidimensional space, 0).

A scenario extracting unit 120 for extracting a dialogue scenario from a sentence extracted by the sentence extracting unit 110, a sentence extracting unit 110 for extracting a semantic vector from each sentence extracted by the scenario extracting unit 120, An intention pattern classifying unit 140 for classifying the intent of each sentence by the semantic vector extracting unit 130 and an intention pattern generating unit 140 for generating an intention pattern that is not classified by the intention pattern classifying unit 140 A dialogue scenario database 160 for storing the dialogue scenario as an intention pattern and a semantic vector, a continuous intention pattern and a semantic vector of the dialogue scenario stored in the dialogue scenario database 160 as an ontology multidimensional space And an ontology relationship mapping unit 170 for displaying the ontology relationship mapping unit 170.

The sentence extracting unit 110 extracts a sentence by an ID or a name from a conversation type voice file, a conversation type post, and a comment. The sentence extracting unit 110 extracts a voice file, 3, a conversation format voice file, such as a call center, a radio, and a TV broadcast, is extracted from a voice file extraction A sentence is extracted through the module 111. When a search word is selected in the search word generator 113, the conversation type sentence posted on the SNS or the like is searched by the postexpression module 112 to search for posts or comments by ID or name, Parses comments to extract sentences. For example, it is possible to extract a sentence from a text after speech recognition of an existing voice recording file provided by a call center, or extract a sentence from text after speech recognition of a consultation content between a customer and an agent in a call center in real time. On the other hand, SNS extracts sentences from posts that talk about various subjects on Twitter or Facebook, searches for SNS with the prepared search words, extracts each of the searched search links (specific words) From the beginning of the first entry pointed to by the posting to the last posting (comment) of the discussion started from that posting as a single conversation topic, all the posts (comments) on the conversation topic are extracted.

The scenario extracting unit 120 extracts a dialogue sentence by a sentence extracting unit 110 by a dialogue type voice file, a conversation type post, a comment, or an ID or name.

For example, in the case of Twitter, a post may have one or more comments, and another comment about the comment runs continuously in descendents, like a tree trunk. In this way, conversation sentences are displayed consecutively by ID or name in the form of a tree based on the conversation of posts and comments. In one tree starting with one post, there are as many scenarios as the number of comments, .

In other words, if there are three first comments on a single post, and two comments on one comment, then there are four total conversation scenarios.

The semantic vector extracting unit 130 expresses each sentence constituting the dialog scenario as a semantic vector. Conventionally, a technique of expressing a word or a sentence as a semantic vector by a word2vec or sentence2vec algorithm is a known technique. Using this technique, each sentence constituting a dialogue scenario can be expressed as a semantic vector.

The intention pattern classifying unit 140 classifies intent patterns of each sentence constituting the dialogue scenario. The intention pattern classification method can classify the intention patterns into sentences that are newly input by the learning model by learning the intention patterns classified as correct by using algorithms such as DNN, CNN, SVM, etc. .

The intention pattern generator 150 newly generates an intention pattern that is not classified by the intention pattern classifier 140. In this case, when the intention pattern can not be classified, it also includes a case where a probability value (for example, 0.5 or less) classified as a specific intention pattern is too lower than an expectation value (for example, 0.8) when classified into a specific intention pattern. In this case, the predicted value is 10 ~ 20% lower than the probability value average (0.95) classified as the correct answer when the learning algorithm is tested with the test sentence.

The intention pattern generation unit 150 extracts an area candidate word and an action candidate word from one sentence and generates a combination of a domain word and an action word composed of a parent word using the parent word and the child word information by using WordNet And generates an intention pattern.

The conversation scenario database 160 is a database in which the conversation scenario is composed of an intention pattern and a semantic vector. At this time, the dialogue scenario stores consecutive intention patterns and semantic vectors composed of sentence unit questions and answers. The semantic vector of sentences and scenarios is also expressed as an intentional pattern in order to help human be intuitively grasped.

The ontology relationship mapping unit 170 maps the continuous scenarios of the intention pattern and semantic vector stored in the ontology dialog network to the dialog scenario database 160 in which the successive intention patterns and semantic vectors of the conversation scenario are stored, Display function. The ontology dialogue network is a multidimensional space composed of 300 to 600 vectors, but since the multidimensional vectors can not be represented physically, they are compressed in three dimensions and displayed. The ontology dialogue network expresses one point on the three-dimensional space as a node, and each node can be represented from an intention pattern and a semantic vector stored in the database 160.

The ontology dialogue network can upload a continuous intention pattern and a semantic vector of the dialogue scenario stored in the dialogue scenario database 160 via the ontology relationship mapping unit 170 and upload the scenario itself as a semantic vector, Similar sentences, and similar scenarios, the scenario closest to the input scenario can be mapped by distance calculation in the semantic vector space. At this time, sentences and scenarios can be expressed on the semantic vector space, but the sentences and scenarios each have a separate semantic space. Then, the semantic space of sentences and scenarios can be mapped to a single semantic space, and sentences and scenarios can be expressed in space. In the method of mapping, the sentence is expressed as the sum or product of word vectors, and the scenario is expressed as the sum or product of the sentence vectors. The semantic vector of the sentence scenario is used to help the intuitive understanding of the human being One or more intent patterns.

On the other hand, the conversation scenario stored in the conversation scenario database 160 can directly input the conversation scenario in the ontology conversation network through the ontology relationship mapping unit 170, and the relationship of the sentences constituting the scenario is described in the following [Embodiment 1] as a sequence of semantic patterns.

[Example 1]

Scenario 1 = (Question 1) - (Answer 1) - (Question 2) - (Answer 2) .... (Question N) - (Answer N)

Scenario 1 = (Where did you see?) - (Are you curious about my name?) - (Not where I saw you) - (Where did we last meet? I think we saw it last time in the last Yalujee seminar.)

Scenario 1 = (name + ambiguous) - (name + confirmation) - (place + ambiguous) - (place + confirmation) .... (alias + accept) - (alias + answer)

 Here, the intention pattern "name ambiguity" is a combination of the domain word "name" and the action word "ambiguous", and is an intention pattern representing a sentence such as "Where did you see?"

An intention pattern represents one or more sentences semantically, and can also be called a representative word representing many sentences with the same meaning.

The semantic patterns such as "semantic ambiguity" and "name resolution" also represent the continuity of each question and answer constituting one scenario, such as "(Question 1)" and "(Answer 1)".

4 to 5 are views showing examples of sentence extraction during database construction of a dialogue scenario for the dialog system according to the present invention.

As shown in FIG. 4, the sentence extraction extracts a word from a DBpedia or a WordNet, uses the word as a search word, searches the SNS post and the comment data Is parsed through the web. This is possible because when a post is posted on Twitter, the comment is similar to the format in which you are retweeting and exchanging conversations about a specific topic.

FIG. 5 retweets the article of the user who originally posted the article, and the other user continues to comment. At this time, the conversation development is similar to the tree form. Here, each tree is viewed as a dialog scenario, and a dialog scenario is expressed for each comment ID in order to facilitate understanding, as in the following [second embodiment].

[Example 2]

Scenario 1: ffebreze - hatter365 - fffebreze

Scenario 2: ffebreze - ffebreze - Teahya - ffebreze - Teahya

FIG. 6 is a screen showing an example of an intention pattern analysis during construction of a dialogue scenario database for an interactive system according to the present invention. As shown in FIG. 6, after parsing a post, Classify conversation intent patterns by learning.

7 is a screen showing an example of conversation scenario learning during construction of a dialogue scenario database for the dialog system according to the present invention. Question 1, Answer 1, Question 2, Question 2, Answer 2, Question 3, Answer 3, Answer 3, Question 3, Answer 3, etc. may occur because the question and answer do not appear alternately on one topic, Answer 3, etc.) Among these questions and answers, questions and answers suitable for the scenario are selected, and the selected dialogue scenario as shown in FIG. 7 shows one question and an iterative learning of one answer to the question.

FIG. 8 is a screen showing an example in which a dialogue scenario database for an interactive system constructed according to the present invention is mapped to an ontology dialogue network.

The scenario is represented by a sequence of semantic vectors consisting of sentence-level questions and answers. Each question and answer constituting a scenario has a multidimensional semantic vector, and each question and answer sentence is automatically mapped to a single intention pattern.

When a large number of scenarios are input as multidimensional semantic vector values, the vector distance between the input semantic vector value and the existing intention pattern is compared, and when the input value is within a certain value, an existing intention pattern may be assigned to the input semantic vector value have.

When a large number of scenarios input not only a multidimensional semantic vector value but also an intention pattern and a dialogue sentence, the dialogue scenario (each question sentence and answer sentence) is mapped to each intention pattern space. At this time, the intention pattern may automatically analyze the "conversation sentence" of the scenario to extract the intention pattern, or the person may directly attach the intention pattern matching the "conversation sentence".

[Example 3]

Scenario 1 = [Intent Pattern] [Conversation Sentence] [Meaning Vector], [Intent Pattern] [Conversation Sentence] [Meaning Vector] ....

Scenario 1 = [name ambiguity] [Where do you think] [2.382, 6.108, ...], [Name resolution] [Are you curious about Jay's name?] [8.730, 1,383, ....] ....

The method of automatically classifying [Intentional Patterns] can be analyzed based on natural language processing methods, rule based, statistical based, and machine learning based. In the case of machine learning based, Intent patterns are classified.

FIG. 9 shows an example of a dialog scenario stored in the dialogue scenario database according to the present invention. The dialogue scenario is usually displayed above 2turn (relation of question 1-answer 1-question 2-answer 2) The number of scenarios that can be displayed is also limited, and scenarios that are spatially close to the current scenario are also unknown. In addition, even if a scenario is input or modified, there is a problem that the correlation in the semantic space with other scenarios can not be known at all.

Dialogue scenarios with specific characters in order to avoid duplication as intended and displayed as a continuous sequence of pattern, illustration, like the first scenario, the top, "the name is ambiguous", "C Check Names", "C yes", "KE name of IU" It can also be combined and displayed.

FIG. 10 is a screen in which a dialog scenario stored in the dialog scenario database according to the present invention is expressed by a three-dimensional scenario authoring tool, and the scenario can be displayed in a three-dimensional space as shown in FIG. Each question and answer in the scenario is represented by a single intent pattern. It is much easier to grasp the semantic relationship between the intention patterns that make up the scenario because it is displayed in the near space and displayed in the far space depending on the semantic closeness between the intention patterns belonging to each scenario.

11 is an example of a scenario input screen in which a dialog scenario stored in the dialog scenario database according to the present invention is expressed by a three-dimensional scenario authoring tool. In the scenario, as shown in FIG. 11, the right intention pattern is dragged to the left margin space, A scenario is represented by a sequence of patterns (for example, a weekend schedule - a schedule answer - a hobby question - a hobby answer). When the scenario input is completed, the scenario is automatically mapped in the three-dimensional dialog network. The right intention patterns all have multidimensional semantic vector values. They can be made by extracting domain words and combining them (weekend + schedule), or by summing or multiplying semantic vectors of many sentences constituting the intention pattern.

The right intent pattern (eg, confirming the weekend schedule) represents various sentences and has various sentence structures such as [Table 1] below, which implies "Weekend schedule confirmation".

Intention pattern Sentence example Check your weekend schedule What is your weekend schedule? Please let me know your weekend schedule. I am curious about the weekend schedule. Tell me your weekend schedule. Do you have a weekend schedule?

FIG. 12 is an example of a scenario modification screen in which a dialog scenario stored in the dialog scenario database according to the present invention is expressed by a three-dimensional scenario authoring tool. The scenario modification screen can search a scenario by a search function and provides a function of modifying a searched scenario . When the scenario is modified, the modified scenario immediately reflects in the 3D space.

FIG. 13 is an example of a scenario deletion screen in which a dialog scenario stored in the dialog scenario database according to the present invention is represented by a three-dimensional scenario authoring tool. The scenario can be deleted. The deleted scenario is completely deleted in the three- Can not.

FIG. 14 is a block diagram showing a sequence in which continuous conversation is performed using the conversation scenario automatic collecting and ontology conversation network according to the present invention. FIG. 15 is a diagram illustrating a sequential conversation sequence using automatic conversation scenario collection and on- As a sequence diagram.

As described above, the ontology dialogue network is a multidimensional vector space composed of 300 to 600 vectors. However, since the multidimensional vector can not be represented physically, spatial compression (using a space compression algorithm such as PCA) is displayed in three dimensions. The ontology dialogue network expresses one point on the 3D space as nodes, and each node can represent a word semantic vector, a sentence semantic vector, and a scenario semantic vector. The term 'ontology dialogue network' expresses the entire structure of such a node and the configuration of a scenario by connection between nodes. When 'ontology dialogue network database' is used, the storage unit storing such data and structure relation is expressed, Hereinafter, they will be used in a mixed manner with no significant discrimination.

Also, as described above, the intention pattern is a phrase representing a plurality of sentences having a similar meaning, and may be a single word or a combination of several words. For example, the intent pattern "name ambiguity check" is a combination of the domain word "name" and the domain word "ambiguity" and the action word "affirmation", and the meaning vector of "name", "ambiguity" It is also a new semantic vector combined. The phrases such as "Where did I see you?" Are as described above. That is, the intention pattern can be represented by a semantic vector in the ontology dialog network space, and has one node.

The scenario can be displayed on the three-dimensional ontology dialogue network space, and each question and answer in the scenario can be displayed as a semantic vector. Since semantic closeness between semantic vectors belonging to each scenario may be displayed in the near space and displayed in a distant space, it is much easier to grasp the semantic relationship between the nodes constituting the scenario.

Hereinafter, a continuous conversation process using the ontology conversation network will be described with reference to the block diagram sequence of FIG. 14 and the flowchart of FIG.

First, when the user speaks, the user's voice is input to the continuous conversation system 200 (see FIG. 18) using the ontology conversation network of the present invention (S210). The continuous conversation system 200 using the ontology conversation network analyzes a sentence to understand a sentence of the input voice (S220). The continuous conversation system 200 using the ontology conversation network determines whether the intention pattern representing the conversation sentence matches the conversation sentence with respect to the analyzed conversation sentence from the ontology conversation relationship network database (S230).

If the intention pattern is not matched (S240), an intention pattern is determined for the conversation sentence, and the intention pattern is matched to the conversation sentence and stored in the ontology conversation network database (S250), which will be described later in detail with reference to FIG.

If the intention pattern is not matched to the conversation sentence and a new intention pattern is determined and matched to the conversation sentence or if the intention pattern is already matched to the conversation sentence, the intention pattern is matched to the corresponding sentence sentence (Hereinafter referred to as a 'second intention pattern') following an intention pattern (hereinafter referred to as 'first intention pattern') matched to the conversation sentence is stored in the ontology dialogue network database, (S260), selects one of the conversation sentences included in the corresponding second intention pattern (S270), and outputs the selected conversation sentence to the user (S280). For example, the first intention pattern may be an intention pattern representing a question conversation sentence that the current user has spoken, and the second intention pattern may be an intention pattern that the continuous conversation system 200 using the ontology conversation network decided to answer Answer It can be an intention pattern that represents a conversation sentence.

There may be a case where there are a plurality of intention patterns following the first intention pattern matched to the conversation sentence according to the dialog scenario in the ontology dialogue network database. In this case, it is possible to extract the intention pattern having the highest weight assigned to the scenarios of the plurality of intention patterns as the second intention pattern. For example, the scenario following the first intention pattern may include a first intention pattern -> 'A' (weight 0.7), a first intention pattern -> 'B' (weight 0.2) Weighting 0.1), the intention pattern A can be determined as the second intention pattern by determining the first intention pattern- > A ' (weight 0.7). Such a weight can be set in advance through conversation quality control for diagnosing and analyzing a conversation with a user, which will be described later with reference to FIG.

FIG. 16 is a flow chart illustrating a method for mapping a new conversation sentence into an ontology conversation network, when a new conversation sentence is input, in a continuous conversation using the ontology conversation network according to the present invention.

When a new scenario is input, the semantic vector values of the question and answer sentences of the scenario are extracted and classified into the input scenarios ("intention pattern (intention pattern), dialogue sentence, meaning Vector ") to the conversation network.

That is, when the intention pattern is not matched to the sentence sentence input by the user, that is, when a new scenario is input (S240), the semantic vector of the sentence sentence is derived (S251) (Step S252). The method of classifying the intent patterns can be one or more of rule based, statistical based, and machine learning based methods. Here, the machine learning corresponds to the 'conversation scenario learning' block in FIG.

If the intention pattern corresponding to the conversation sentence is classified (S252), the intention pattern is determined as the intention pattern of the conversation sentence, and is matched to the conversation sentence and stored in the ontology conversation network database (S253). At this time, a continuous list of the intention patterns classified as described above, a continuous list of conversation sentences, and a continuous list of the semantic vectors can be stored in the ontology conversation network database.

If the intention pattern corresponding to the conversation sentence is not classified (S252), the intention pattern mapped to the node closest to the node indicated by the semantic vector is grasped from the ontology dialogue network database, (S254). At this time, a continuous list of classified intention patterns, a continuous list of conversation sentences, and a continuous list of semantic vectors are also stored in the ontology dialogue network database It can be stored in the ontology dialogue network database.

At this time, the intention pattern mapped to the node closest to the node indicated by the semantic vector may be a single word, or may be a new word indicated by a semantic vector generated by a combination of words.

A scenario can be expressed as a series of pairs of question answers. Just as each question answer forms a single scenario, a scenario can contain specific dialogue information (education, literature, common sense, everyday conversation, sports, movies, etc.) And scenarios can be represented by a combination of intention patterns.

Scenario Classification Each scenario can be categorized using one or more of the following: rule-based, statistical-based, and machine-based. Therefore, the scenario classification may be firstly selected before classifying the conversation intention of each sentence, and the search intention (intention pattern) included in the scenario classification may be searched first to reduce the search time.

FIG. 17 is a block diagram illustrating a sequence for implementing conversation quality improvement using continuous conversation using an ontology conversation network according to the present invention. Referring to FIG.

As the user interacts with the system, the user can immediately know whether the user's response is positive or negative. The user's reaction such as positive reaction, negative reaction, neglect reaction, topic change reaction can be analyzed by analyzing the user's conversation sentence, and various analysis methods such as rule based, statistical based, and machine learning based can be used.

When the user response is positive, the current scenario can be recognized as the preferred dialog scenario, and the likelihood of adopting the current scenario through weight adjustment is increased, so that the preferred scenario continues to be selected, and the non-preferred scenario has priority , And managing the dialogue scenario continuously through the real-time user response and ultimately aiming at improving the conversation quality as the continuous conversation is performed.

This process will be described with reference to FIG. 17. The continuous conversation quality management is performed through the conversation scenario history between the normal user and the continuous conversation system 200 using the ontology conversation network of the present invention. In other words, the sentence inputted from the user is analyzed and the reaction of the user is analyzed from the analyzed conversation sentence. When the user reaction is analyzed as being positive, the likelihood that the dialogue scenario leading to the corresponding sentence sentence or the intention pattern of the corresponding sentence sentence is selected is set high, and when the user reaction is analyzed as negative, Is set to a low possibility.

Positive or negative here is a very generic term. As shown in the example of FIG. 17, it can be divided into details such as praise reaction, positive reaction, negative reaction, neglect reaction, topic change reaction, etc. However, it can be explained as a positive or negative reaction including all of them. This would be a more accurate expression of giving a degree or degree, rather than analyzing it with two kinds of reactions. In other words, the more responsive and favorable the user's response to the sentence analysis is, the more likely it is that the dialogue scenario with such response will be selected in the future through feedback, and the more the opposing dialogue scenario The possibility of being selected is lowered.

The setting of the likelihood that a future dialog scenario will be selected may be made by assigning a weight in relation to the preference / non-preference dialog scenario according to predetermined criteria in the dialog scenario in which the user response is made. This increases the probability that a conversation scenario with a higher weight will be selected in the future.

At this time, the analysis of the user reaction may be performed by analyzing the user's conversation sentence according to a rule (rule-based), performing based on the sentence statistics (statistical based), or machine learning Machine learning basis).

Alternatively, the analysis of the user response may be performed by a user preference that is analyzed and mapped on the corresponding intention pattern of the conversation sentence of the user in the ontology dialog network database. That is, the intention pattern space and the user preference space may be separately provided on the ontology dialog network database, and the user's preferences of the same node in the user's preference space and the specific intention pattern node of each intention pattern space may be mapped. That is, since the user preference analyzed by the user reaction is mapped to the user's intention pattern, the weight for the conversation can be set therefrom.

18 is a diagram illustrating a configuration of a continuous conversation system using an ontology conversation network according to the present invention.

The control unit 201 controls each of the components of the continuous dialog system using the ontology dialog network to perform a series of processes related to the continuous dialog using the ontology dialog network.

The voice input unit 202 receives the voice of the user.

The sentence analysis unit 203 analyzes sentences from the input speech.

The dialogue management unit 204 receives from the ontology dialogue network database an intentional pattern (hereinafter referred to as 'second intentional pattern') that follows an intentional pattern (hereinafter referred to as 'first intentional pattern' And selects one of the conversation sentences included in the second intention pattern as an output conversation sentence. Further, in the case where there are a plurality of intention patterns following the first intention pattern matched to the conversation sentence in accordance with the dialog scenario in the ontology dialogue network database, the dialogue management unit 204 assigns to the scenarios in the respective intention patterns And extract the intention pattern having the highest weight as the second intention pattern.

If the intention pattern is not matched with the analyzed conversation sentence, the new scenario processing unit 206 determines a new intention pattern for the sentence, stores the new intention pattern in the ontology dialog network database, matches the sentence with the sentence, And transmits it to the dialog management unit.

If the intention pattern is not matched with the input sentence sentence, the new scenario processing section can derive the semantic vector of the sentence sentence. And classifies the intention pattern corresponding to the conversation sentence from the derived semantic vector. If the intention pattern corresponding to the conversation sentence is classified, the intention pattern is determined as the intention pattern of the conversation sentence, and is matched to the conversation sentence, and is stored in the ontology conversation relationship network database. The intention pattern mapped to the node closest to the node indicated by the semantic vector is grasped from the ontology dialog network database, and the identified intention pattern is determined to be the intention pattern of the conversation sentence, and is matched to the sentence sentence Store it in the ontology dialog network database, and deliver the determined intention pattern to the conversation management unit.

As described above with reference to FIG. 16, an intention pattern mapped to a node closest to a node indicated by the semantic vector may be a single word or a new word indicated by a semantic vector generated by a combination of words.

The conversation quality management unit 205 analyzes the response of the user from the analyzed conversation sentence to determine the possibility that the conversation scenario leading to the intended conversation sentence or the intended pattern of the conversation sentence is selected if the user response is analyzed as being positive And when the user reaction is analyzed as negative, the conversation quality management is performed by setting the possibility of selecting the conversation scenario leading to the conversation sentence or the intention pattern of the conversation sentence to be low. At this time, as described above with reference to FIG. 17, the setting of the possibility that the conversation scenario is selected may be made by weighting according to a predetermined criterion. Also, analysis of the user response may be performed by analyzing the conversation sentence according to a rule (rule-based), based on statistics of a conversation sentence (statistical based), or by machine learning Based). The analysis of the user response may be performed by the user preference that is analyzed and mapped on the intention pattern of the conversation sentence of the user in the ontology dialog network database. This has been described in detail with reference to FIG. 17 .

The dialogue output unit 207 outputs the dialogue sentence selected by the dialogue management unit to the user through voice or the like.

FIG. 19 is a diagram showing an embodiment of the ontology talk network structure according to the present invention.

That is, referring to the embodiment of FIG. 19, the conversation of the ontology conversation network can be classified into a general conversation domain, a specialized conversation domain, or another such new domain by setting a new domain as necessary. That is, a large number of nodes such as an intention pattern mapped in the ontology talk network space may already be set in areas such as general conversation and professional conversation, respectively. That is, when a semantic vector for each sentence is obtained, the node indicated by each semantic vector according to the meaning of the sentence may be configured to point to an area of the classification determined on the ontology dialog network space. Of course, the same method can be used for detailed classification at the bottom of a general conversation or a professional conversation.

General conversations (daily conversations, common sense conversations, topic conversations, etc.) develop conversations based on conversation scenarios in a conversation network for various topics.

Specialized conversations (advance purchase, reservation, purchase, etc.) acquire specific information (Argument) according to a specific purpose of the strategy, and perform dialogue for the performance of the task. For example, in the case of KTX reservation, the user is asked about the information necessary for the reservation such as the reservation time, the number of the companion, the type of the seat, and the reservation is finished after the information is satisfied. Therefore, it is necessary to follow a dialogue procedure (Flow) for a specific purpose.

In this way, general conversation and professional conversation can be freely performed in the ontology conversation network.

20 to 23 show examples of conversations classified in the ontology conversation network.

20 is a diagram illustrating an embodiment of a general conversation classification structure in an ontology conversation network according to the present invention.

General conversations can include daily conversations, common conversations, topic conversations, emotional conversations, topic conversations, and conversations are possible by constantly moving conversation focus on various topics.

FIG. 21 is a diagram illustrating an example of a professional talk classification structure in an ontology talk network according to the present invention.

Professional conversation refers to conducting a specific purpose-based conversation, such as booking, reserving, or purchasing.

22 is a diagram illustrating an example of a conversation classification structure exchanged with an agent in a hospital call center during a professional conversation in an ontology conversation network according to the present invention.

23 is a diagram showing an example of a classification structure in which a daily conversation, an emotional conversation, and a professional conversation are connected in an ontology conversation network according to the present invention.

Continuous conversation can be done while freely coming in everyday conversation, emotional conversation, and professional conversation.

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 will be understood that various modifications and changes may be made without departing from the scope of the appended claims.

100: Dialogue scenario database building device
110: sentence extracting unit
111: voice file extraction module
112: Extraction module
113: Query Generator
120: sentence analysis unit
130: Conversation scenario generation unit
140: Dialogue scenario learning unit
150: Conversation scenario database
160: ontology relation mapping unit
200: Continuous conversation system using ontology dialogue network

Claims (6)

A method for constructing a dialog scenario database for an interactive system applied to an ontology dialog network,
(a) extracting a sentence by an id or name from a conversation type voice file or conversation type of a comment or a comment;
(b) expressing a conversation sentence in tree form by ID or name according to conversation development of a comment or a comment from the sentence extracted in the step (a);
(c) extracting a dialog scenario from each tree of step (b);
(d) expressing each sentence of the dialog scenario generated in the step (c) as a semantic vector;
(e) expressing each sentence of the dialogue scenario generated in the step (d) in an intent pattern;
(f) databaseing the conversation scenario into an intent pattern and a semantic vector; And
(g) creating a new intention pattern in a sentence without an existing intention pattern in the step (e)
The method comprising the steps of: The method according to claim 1,
In the step (f), the semantic vector obtained by the database is displayed as one of a semantic word, a semantic node and a semantic cube
Further comprising the steps of: creating a dialog scenario database for a dialog system for a dialog system. The method according to claim 1,
Wherein the conversation-type voice file in the step (a) is extracted after changing to text through speech recognition
The method comprising the steps of: The method according to claim 1,
The extraction from the interactive-type article of step (a)
A specific word (word) is specified as a search term, and the data and the posts and comments retrieved by the specified search term are parsed and extracted
The method comprising the steps of: The method according to claim 1,
The sentence extracted in the step (a) is automatically converted into a semantic vector
The method comprising the steps of: A dialog scenario extracting unit for extracting a dialog scenario;
A dialogue scenario learning unit for learning each sentence of the dialogue scenario generated by the dialogue scenario extracting unit;
A dialogue scenario intention pattern classifying unit for classifying an intention pattern of each sentence of the dialogue scenario using the semantic vector generated by the dialogue scenario learning unit,
An intention pattern generator for generating a new intention pattern for an intention pattern not classified by the intention pattern classifier of the dialog scenario;
A dialog scenario database storing the dialog pattern intention patterns and the semantic vectors; And
An ontology relationship mapping unit for displaying successive semantic vectors and intent patterns of the conversation scenario stored in the conversation scenario database on an ontology multidimensional space,
Wherein the dialog scenario database includes at least one of:

Images