JP2003316806A - Image processing system, image processing device, image processing method, program, and recording medium with program recorded thereon - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To retrieve, based on input information such as speech contents input from a user, pre-created answering contents correlated with contents understood from the input information, and refer to details of this retrieval, thereby, for example, the degree of a feeling with respect to the user is easily specified. <P>SOLUTION: The system according to the present invention comprises a topic retrieving portion 360 which compares first morpheme information constructing the speech contents of the user with each piece of pre-stored second morpheme information to retrieve a piece of the second morpheme information including a morpheme constructing the first morpheme information, and a ranking portion 380 which grades in rank, for example, the degree of a feeling with respect to the user based on the second morpheme information retrieved by the topic retrieving portion 360. <P>COPYRIGHT: (C)2004,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention records an information processing system, an information processing method, a program and a program for ranking the emotional level of the user based on the input information input by the user. Recording medium

[0002]

2. Description of the Related Art In recent years, the degree of emotion that a user has (hereinafter simply referred to as "emotion degree") can be specified (specified by ranking, etc.) using a personal computer. Specifically, this emotion level analyzes the utterance content from the user, compares the analyzed utterance content with a plurality of predetermined categories related to emotions, and determines which emotional category the utterance content belongs to. Can be specified by performing a process for determining.

[0003]

However, in the process of specifying the emotion level, in order to specify (rank) the emotion level based on the content of the utterance from the user, the emotion content of the user is It is necessary to build a complicated algorithm or a neural network to determine whether it belongs to the category related to, and it is difficult to create a system for easily specifying the emotional level of the user from the utterance content. there were.

Therefore, the present invention has been made in view of the above points, and is associated with the meaning content grasped from the input information in advance based on the input information such as the utterance content input by the user. To provide an information processing system, an information processing apparatus, an information processing method, a program, and a recording medium on which the program can be searched, by searching the created reply contents and the like and ranking according to the frequency of the search. Is an issue.

[0005]

According to the invention of the present application, one character or a plurality of character strings are used when ranking the emotional level or the like to the user based on the input information input by the user. Or a plurality of second morpheme information indicating a morpheme consisting of these combinations is stored in advance, based on the input information input by the user, a character string indicating the input information is specified, and based on the specified character string, At least one morpheme that constitutes the minimum unit of the character string is extracted as the first morpheme information, the extracted first morpheme information and each second morpheme information are collated, and from each of the second morpheme information, the first morpheme information is extracted. The second morpheme information including the morpheme information is searched, and the second morpheme information including the first morpheme information is ranked from the second morpheme information based on the search result according to the frequency of the search. Characterized by Than it is.

[0006] The conversation control device (information processing device) may output the ranked size as the emotional level of the user or the level of understanding of the input information. Also, the conversation control device, when the search frequency is low,
It is preferable to rank a low rank and rank a high rank when the search frequency is high.

According to the invention of the present application, the conversation control apparatus ranks according to the frequency with which the second morpheme information including the first morpheme information is searched from each second morpheme information. For example, if it is possible to output the ranked size as the degree of emotion that the user has (for example, screen, voice, etc.), the conversation control device can be simulated for the user. It can be used to specify the degree of emotions to be held.

A developer who develops a conversation control device is
Based on only the search history performed between the first morpheme information and each of the second morpheme information, for example, since the emotional level of the user can be specified, the emotional level of the user can be determined. It is not necessary to develop a complicated algorithm or neural network for the conversation controller to calculate, and as a result, the development time for developing this device can be shortened.

Further, according to the invention of the present application, a plurality of second morpheme information is associated with a discourse range indicating a morpheme that is relevant to the input information or the content of the reply to the user that is likely to be input by the user. Therefore, a plurality of discourse ranges are stored, the first morpheme information is compared with each discourse range, the discourse range including the first morpheme information is searched from each discourse range, and the first discourse range indicating the retrieved discourse range is displayed. The one discourse range is collated with the second discourse range indicating the discourse range retrieved by the discourse search means later to determine whether the second discourse range is related to the first discourse range, and based on this determination result. It is characterized by ranking.

When it is determined that the second discourse range is not related to the first discourse range, the conversation control device ranks a lower rank, and the second discourse range becomes the first discourse range. When it is determined that there is relevance, it is preferable to rank a higher rank.

According to the invention of the present application, the conversation control apparatus includes the first discourse range associated with the first morpheme information retrieved first and the second discourse range associated with the first morpheme information retrieved later. Depending on the relationship with the discourse range,
Since it is possible to rank, the conversation control device, based on the search result by collating the first morpheme information and each second morpheme information, rather than ranked, for example, as a more appropriate degree of emotion Can be attached.

For example, if the second discourse range is not related to the first discourse range, the current input information (input by the user) and the previously input information are Since it can be determined that the contents are completely different, the user can conclude that he / she is inputting inconsistency with respect to a certain topic, and the conversation control device displays the emotion level toward the user. Can be ranked low.

On the other hand, if the second discourse range is related to the first discourse range, the current input information (input by the user) and the previously input information are Since it can be judged that the user has input, it is possible to conclude that the user has input that the user is consistent with respect to a certain topic. The degree can be set high (good direction).

Further, according to the invention of the present application, the first morpheme information is composed of the respective morphemes associated with each attribute such as the subject case composed of the nominative case and the target case composed of the objective case. Based on, from each of the attributes that form the first morpheme information, to search for attributes that do not include morphemes, based on the searched attributes, add the morphemes that form the searched discourse range to the attributes, It is characterized in that the ranking is performed based on the result of adding the morphemes constituting the discourse range.

According to the invention of the present application, when the conversation control device adds the morphemes forming the discourse range to the first morpheme information, the emotional level of the user becomes high. Since the ranking is performed, the conversation control device may determine that the input information composed of the first morpheme information is an abbreviated sentence when the morpheme of the discourse range is added to each attribute forming the first morpheme information. it can.

Therefore, when the first morpheme information consisting of the input information is an abbreviation, it can be judged that the input information is being input on the premise of the discourse range retrieved previously. The person can determine that he / she is inputting consistency with respect to a certain topic, and the conversation control apparatus can set a high emotional level (good direction) to the user.

Further, according to the invention of the present application, a plurality of standard contents for replying the standard contents to the input information from the user are stored in advance, and the extracted first morpheme information and the respective standard contents are stored. Matching is performed, a standard content including the first morpheme information is searched from each standard content, and the frequency of searching for the standard content including the first morpheme information is determined from each standard content based on the search result. It is ranked according to the size.
If the conversation control device is searched frequently,
It is preferable to rank in a high rank and rank in a low rank when the search frequency is low.

According to the invention of the present application, the conversation control device collates the first morpheme information with each standard content,
From each standard content, the standard content including the first morpheme information is searched and ranked based on the size of the frequency of the search, so the conversation control device, for example, determines the standard content including the first morpheme information. If the standard content is searched and the answer sentence from the conversation control device is returned (parody),
Since the user can conclude that the input information for interrupting a certain topic has been input, it is possible to rank the emotion level of the user to a low rank, and as a result, it is appropriate. Can be ranked (such as the degree of emotion that the user has).

On the other hand, when the conversation control device cannot retrieve the fixed contents including the first morpheme information, the user has not input the input information for interrupting a certain topic, Since it is possible to artificially conclude that the topic is answered seriously, it is possible to rank it in a high rank.

Further, according to the invention of the present application, an input type indicating the type of input information is specified based on the specified character string, and when the specified input type is a repulsive element such as a repulsive sentence, It is characterized by being ranked in a low rank.

According to the invention of the present application, the conversation control device identifies the input type indicating the type of input information,
If the identified input type is a repulsive element such as a repulsive sentence, it is ranked in a lower rank, so that the conversation control device may, for example, repulsively respond to the response content output from the conversation control device by the user. If it is, for example, it is possible to rank the emotion level of the user to a low rank,
It is possible to more appropriately rank the emotional level of the user.

Further, according to the invention of the present application, if the second morpheme information including the first morpheme information is not retrieved, it is determined that the input information input by the user is difficult, and the degree of understanding of the input information is determined. Is characterized by being ranked at a low rank.

According to the invention of the present application, the second morpheme information related to the first morpheme information is stored in advance when the second morpheme information including the first morpheme information is not retrieved by the conversation control device. Because it means not been done
It can be determined that the input information including the first morpheme information is more difficult than the sentence including the second morpheme information.

For this reason, since the conversation control device cannot understand the input information consisting of the first morpheme information, it is pseudo-asserted that the user is inputting meaningless to a certain topic. Therefore, it is possible to rank the degree of comprehension of the input information in a low rank.

Further, in the invention according to the present application, when the second morpheme information including the first morpheme information is retrieved, it is determined that the input information input by the user is easy, and the degree of understanding of the input information is determined. Is characterized by being ranked in a high rank.

According to the invention of the present application, when the conversation control device can retrieve the second morpheme information related to the first morpheme information, the conversation control device determines the first morpheme information. Since the input information consisting of can be understood, the user can artificially conclude that he or she is inputting something that makes sense for a certain topic, and the degree of understanding of the input information is ranked high. can do.

Further, according to the invention of the present application, the topic desired by the user, the degree of emotion the user has for a certain matter, or the type of a statement, affirmative sentence, a question sentence, a repulsive sentence, etc., depending on the meaning of the content. It is characterized by being described in a language that is hierarchically stored in a database in association with morphemes. The language is DKML (Discourse Knowledge
Markup Language) is desirable. With this, the developer who develops the conversation control device can hierarchically construct the second morpheme information and the like for searching the answer content to the input information of the user in the database by using the language, The conversation control device can search the database for second morpheme information and the like related to the first morpheme information based on the first morpheme information corresponding to the input information of the user through a hierarchical procedure.

That is, the conversation control device has a hierarchy of the first morpheme information corresponding to the input information (for example, is it a superordinate concept or a subordinate concept with respect to the second morphological information accumulated in the database). It is possible to search for the appropriate second morpheme information from among the respective second morpheme information stored in advance based on the determined hierarchy.

Therefore, the conversation control device stores in advance the first morpheme information consisting of the input information of the user.
Since it is sufficient to compare each "specific" second morpheme information and the first morpheme information belonging to a certain hierarchy without collating all "second morpheme information", it is approximate to the first morpheme information. The second morpheme information can be searched for in a short time, and as a result, the emotional level of the user and the like can be ranked in a short time based on the search result.

In the invention according to the present application, a plurality of pieces of second morpheme information are stored, and each second morpheme information is associated with an answer content, and based on the retrieved second morpheme information, Acquires the reply content associated with the second morpheme information, stores the acquired past reply content, collates the acquired current first morpheme information with the past reply content, and determines the current first morpheme. It is characterized in that it is determined whether or not the information is included in the past reply contents, and ranking is performed based on the determination result.

According to the invention of this application, the conversation control device collates the present first morpheme information with the past answer contents, and the present first morpheme information is included in the past answer contents. In the above, the conversation control device can artificially determine that the user is humorous with respect to the past reply contents (that the user is listening again to the reply contents).

In this case, in the conversation control device, since the user makes a parody on the contents of the past answers, the user imitates that the user has input the input information for interrupting a certain topic. It can be determined, for example, that the emotional level of the user can be ranked in a low rank, and as a result, the emotional level of the user can be more appropriately ranked. .

Further, in the invention according to the present application, the acquired first morpheme information in the past is stored, the acquired first morpheme information in the past is collated with the past first morpheme information, and the current first morpheme information is compared. It is characterized in that it is determined whether or not the morpheme information is included in the past first morpheme information, and ranking is performed based on the determination result.

According to the invention of the present application, the conversation control device compares the present first morpheme information with the past first morpheme information, and the present first morpheme information is the past first morpheme information. , The user can simply determine that the input information input in the past is re-input regardless of the reply content from the conversation control device.

In this case, since the user simply repeatedly inputs the same input information as the previous input information regardless of the content of the reply from the conversation control device, the conversation control device For example, the emotional level of the user can be ranked lower, and as a result, the emotional level of the user can be more appropriately ranked.

It should be noted that the second morpheme information including the first morpheme information (including the discourse range, the fixed contents or the reply contents, etc.
“Abbreviated as“ second morpheme information etc. ”” does not only mean that the second morpheme information etc. includes the first morpheme information as it is, but the second morpheme information etc. includes at least one morpheme that constitutes the first morpheme information. We shall also mean the case.

[0037]

BEST MODE FOR CARRYING OUT THE INVENTION First Embodiment (Basic Configuration of Conversation Control System) A conversation control system according to the present invention will be described with reference to the drawings. Figure 1
Is a conversation control device 1 (ranked device) according to the present embodiment.
It is a schematic block diagram of a conversation control system having.

As shown in the figure, the conversation control device 1 includes an input unit 100, a voice recognition unit 200, and a conversation control unit 300.
A sentence analysis unit 400, a conversation database 500, an output unit 600, and a voice recognition dictionary storage unit 700.

In the present embodiment, for convenience of explanation, the description will be limited to the utterance content of the user (this utterance content is a kind of input information), but it is not limited to the utterance content of the user. Alternatively, the input information may be input from a keyboard or the like. Therefore, the following "utterance content" is
The "utterance content" can be replaced with the "input information" for explanation.

Similarly, in the following description, for convenience of explanation, the description will be limited to the "type of utterance sentence" (utterance type), but the keyboard type is not limited to this "type of utterance sentence". It may be an “input type” indicating the type of input information input from, for example. Therefore, the “utterance sentence type” (utterance type) shown below can be described by replacing the “utterance type” with the “input type”.

The input section 100 is an acquisition means for acquiring the input information from the user, and in the present embodiment, a microphone, a keyboard and the like can be mentioned. This input unit 100 is
It is also a character recognition means for specifying the character string indicating the input information based on the input information (other than voice) input by the user.

Here, the input information means a character, a symbol, a voice or the like input through a keyboard or the like. Specifically, the input unit 100 specifies a character string indicating the input information based on the input information (other than voice) that has been input, and the conversation control unit 30 uses the specified character string as a character string signal.
Output to 0. Further, the input unit 100, which has acquired the utterance content from the user (this utterance content is composed of voice and is a kind of input information) with a microphone or the like, outputs the voice that constitutes the acquired utterance content as a voice signal. To the voice recognition unit 200.

The voice recognition section 200 is a character recognition means for specifying a character string corresponding to the utterance content based on the utterance content acquired by the input section 100. Specifically, the input unit 10
The voice recognition unit 200, to which the voice signal is input from 0, analyzes the input voice signal and specifies the character string corresponding to the analyzed voice signal using the dictionary stored in the voice recognition dictionary storage unit 700. Then, the specified character string is output to the conversation control unit 300 as a character string signal. Voice recognition dictionary storage unit 7
00 stores a dictionary corresponding to a standard audio signal.

The sentence analysis unit 400 analyzes the character string specified by the input unit 100 or the voice recognition unit 200, and in the present embodiment, as shown in FIG. 2, the morpheme extraction unit 410 and the phrase. Analysis unit 420 and sentence structure analysis unit 430
, Utterance type determination unit 440, and morpheme database 45
0 and an utterance type database 460.

The morpheme extraction unit 410 is a morpheme extraction unit that extracts each morpheme that constitutes the minimum unit of the character string as the first morpheme information based on the character string specified by the input unit 100 or the voice recognition unit 200. .

Specifically, the morpheme extraction unit 410 to which the character string signal is input from the management unit 310 extracts each morpheme from the character string corresponding to the input character string signal. Here, in this embodiment, the morpheme means the minimum unit of the word structure represented in the character string. As the minimum unit of the word structure, as shown in FIG. 3, for example, a part of speech such as a noun, an adjective, or a verb can be cited. In the present embodiment, each morpheme is expressed as m1, m2, ..., Ml.

That is, the morpheme extraction unit 410 detects the character string corresponding to the input character string signal and the morpheme database 4
The morphemes (m1, m2, ...) Matching the morphemes in the character string are collated with the morphemes such as nouns, adjectives and verbs stored in advance in 50, and the extracted morphemes are extracted. Is output to the phrase analysis unit 420 as an extraction signal.

The phrase analysis unit 420 includes a morpheme extraction unit 410.
It is a conversion means for converting each morpheme into a bunsetsu format based on each morpheme extracted in. Specifically, the morpheme extraction unit 4
The bunsetsu analysis unit 420 to which the extracted signal is input from 10 uses the morphemes corresponding to the input extracted signal to assemble the bunsetsu form.

Here, the phrase format means, in the present embodiment,
In Japanese grammar, it means an independent word or a sentence in which one or more attached words are attached to an independent word, or a single-divided sentence in which a character string is divided as finely as possible without impairing the meaning of Japanese grammar. This clause is p1, p in this embodiment.
It is expressed as 2, ... pk.

That is, as shown in FIG. 4, the bunsetsu parsing unit 420, based on each morpheme corresponding to the input extracted signal, has a dependency element of each morpheme (eg, (m2). (M5) ...) is extracted, and each morpheme is collected into each clause based on the extracted dependency element. “T” shown in the figure means transposition.

A bunsetsu analysis unit 4 which collects each morpheme into each bunsetsu
The 20 outputs, as a sentence pattern signal, sentence pattern information including each phrase in which each morpheme is collected and each morpheme forming each phrase to the sentence structure analysis unit 430 and the utterance type determination unit 440.

The sentence structure analysis unit 430 includes a phrase analysis unit 420.
It is a classifying means for classifying each morpheme of the first morpheme information segmented into paragraphs into each attribute such as a subject case and a target case. Specifically,
The sentence structure analysis unit 430 to which the sentence pattern signal is input from the phrase analysis unit 420, based on each morpheme corresponding to the input sentence pattern signal and the phrase formed of each morpheme, is a “case configuration” of each morpheme included in the sentence. To decide.

Here, the "case composition" means a case (attribute) indicating a substantial concept in a bunsetsu, and in the present embodiment, for example, a subject (subject case) meaning a subject or a nominative case. , An object meaning a target (object case), an action meaning a motion, a time meaning a time (tens, aspect), a location meaning a place, and the like. In the present embodiment, each morpheme associated with a “case” (case composition) of three elements of a subject, an object, and an action is defined as first morpheme information.

That is, as shown in FIG. 5, when the dependency element of each morpheme is “” or “wa”, the sentence structure analysis unit 430 determines that the morpheme in front of the dependency element is Judge as a subject (subject or nominative case). In addition, for example, when the dependency element of each morpheme is “no” or “wa”, the sentence structure analysis unit 430 determines that the morpheme in front of the dependency element is an object (target).

Further, for example, when the dependency element of each morpheme is “do”, the sentence structure analysis unit 430 determines that the morpheme in front of the dependency element is an action (predicate; this predicate is a verb, an adjective, etc.). It consists of)).

The sentence structure analysis unit 430, which has determined the “case composition” of each morpheme constituting each phrase, will be described later on the basis of the first morpheme information associated with the determined “case composition”. The topic search command signal for specifying the range of is output to the reflexive determination unit 320.

The utterance type determination unit 440 is used by the phrase analysis unit 42.
Utterance content (input information) based on the clause specified by 0
It is a type specifying means for specifying the utterance type (input type) indicating the type. Specifically, the “utterance sentence type” (utterance type) is determined based on each morpheme corresponding to the sentence pattern signal input from the bunsetsu analysis unit 420 and the bunsetsu composed of each morpheme.

Here, in the present embodiment, the "type of utterance sentence" is the statement sentence (D; Declaratio) as shown in FIG.
n), impression sentence (I; Impression), conditional sentence (C; Conditi
on), a result sentence (E; Effect), a time sentence (T; Time), a place sentence (L; Location), a repulsive sentence (N; Negation), and the like.

The statement sentence means a sentence composed of a user's opinion or thought, and in the present embodiment, it is shown in FIG.
As shown in, for example, a sentence such as "I like Sato" can be cited. The impression sentence means a sentence composed of impressions held by the user. The place sentence means a sentence composed of place-like elements.

The result sentence means a sentence composed of a sentence including a result element for a topic. What is a time sentence?
It means a sentence composed of sentences including temporal elements related to the topic.

The conditional sentence means a sentence including elements such as a premise of a topic, a condition and a reason that the topic is established when one utterance is regarded as a topic. The repulsive sentence means a sentence composed of a sentence including an element that repels the utterance partner. An example sentence about each "utterance sentence type" is as shown in FIG.

That is, the utterance type determination unit 440 compares each bunsetsu with the dictionary stored in the utterance type database 460 based on each bunsetsu corresponding to the input sentence pattern signal, From, the sentence elements related to each dictionary are extracted. The utterance type determination unit 440 that has extracted the sentence element related to each dictionary from each bunsetsu determines the “utterance sentence type” based on the extracted sentence element. The sentence element means a type of a portion for specifying the type of character string, and in the present embodiment, the sentence element includes the definition phrase (which means to) described above and the like.

Here, the utterance type database 460 is used.
Is a definition phrase (for example, ~), as shown in Figure 7.
With definitional expression case dictionary with dictionaries related to, affirmative case dictionary with dictionary related to positive phrases (eg, yes, sympathy, ping pong), with dictionary related to result phrases (eg, so and so) result representation example dictionary, greeting clause (for example, Hello) greeting case dictionary with a dictionary related to, negative clause (for example, by not you say stupid, opposite) is composed of such negative cases dictionary with a dictionary related to the ,
Each dictionary is associated with a "sentence type".

As a result, the utterance type determination unit 440 collates the phrase with each dictionary stored in the utterance type database 460, extracts the sentence element related to each dictionary from the phrase, and extracts the extracted sentence element. By referring to the type of determination associated with, it is possible to determine the “type of utterance sentence”.

The utterance type determination unit 440 outputs an answer search command signal for causing the corresponding user to search for a specific answer sentence to the answer sentence retrieval unit 370 based on an instruction from the topic retrieval unit 360 described later. To do.

The conversation database 500 stores a plurality of second morpheme information indicating a morpheme consisting of one character, a plurality of character strings, or a combination thereof, and the contents of an answer to the user for the contents of utterance in association with each other in advance. Answer storage means (discourse storage means). The conversation database 500 is also an answer storage unit (discourse storage unit) that stores a plurality of answer types indicating the types of each answer content associated with the plurality of answer contents in advance in association with the second morpheme information.

Further, the conversation database 500 stores in advance a plurality of discourse ranges (keywords) indicating morphemes constituting a range relevant to the input contents or the reply contents to the user which are likely to be inputted by the user. It is also a means of storing discourse. This discourse range (keyword) is associated with a plurality of pieces of second morpheme information indicating a morpheme consisting of one character, a plurality of character strings, or a combination thereof, and each second morpheme information contains the content of the answer to the user. It is associated with each.

Furthermore, the conversation database 500 classifies and stores each element constituting the second morpheme information into attributes such as each subject consisting of the nominative case and the target case consisting of the objective case (discourse storage means). ) Is also.

As shown in FIG. 8, in the conversation database 500, according to the present embodiment, when broadly classified, the utterance content that is likely to be uttered by the user or the relevant range of the reply content to the user is shown. It is composed of a discourse range that means and a topic that means a range that is most closely related to the content spoken by the user. As shown in the figure, the "discourse range" is positioned as a superordinate concept of "topic" in the present embodiment.

Each discourse range can be configured to have a hierarchical structure as shown in FIG. As shown in the figure, for example, the discourse range (entertainment) of a higher concept for a certain discourse range (movie) is located in the upper hierarchical structure, and the discourse range of a lower concept (movie) for the discourse range (movie) is set. Attributes, movies to be shown) may be located in a lower hierarchical structure. That is, in the present embodiment, each discourse range can be arranged in a hierarchical position where the relationship of the superordinate concept, the subordinate concept, the synonym, and the antonym is clear with respect to the other discourse ranges.

As described above, the discourse range is made up of each topic. In the present embodiment, for example, if the discourse range is the A movie name, a plurality of topics related to "A movie name" will be displayed. Contains.

This topic means a morpheme consisting of one character, a plurality of character strings, or a combination thereof, that is, each morpheme that constitutes the utterance content that the user may utter. In form, subject (subject case), object (target case), action "case"
Each morpheme is associated with (attribute). In the present embodiment, each morpheme associated with these three elements will be expressed as a topic title (this topic title corresponds to a subordinate concept of "topic") (second morpheme information). .

The topic title is not limited to each morpheme associated with the above three elements, but means another "case", that is, a time (tense, aspect) meaning time and a place. Each morpheme may be associated with a location, a condition that means a condition, an impression that means an impression, an effect that means a result, and the like.

This topic title (second morpheme information) is
In the present embodiment, it is stored in advance in the conversation database 500 and is distinguished from the first morpheme information (derived from the utterance content uttered by the user).

For example, a topic title has a discourse range of "A".
In the case of "movie name", as shown in FIG. 10, from subject (A movie name), object (director), action (great) {this means "the director of A movie name is wonderful"} It is composed.

In the topic title, if there is no morpheme associated with “case composition” (subject, object, action, etc.), that part is indicated by “*” in this embodiment.

For example, {A movie name? } Is converted into a topic title (subject; object; action), {A movie name? }, "A movie name" can be specified as the subject, but other "objects" and "actions" are not elements of the sentence, so the topic title is "subject" (A
Movie name); “Object” is not provided (*); “Action” is not provided (*) (see FIG. 10).

The answer sentence means an answer sentence (responding content) to the user and is associated with each topic title (second morpheme information) in this embodiment (FIG. 8). reference). In this embodiment, the answer sentence is shown in FIG.
As shown in Fig. 1, in order to make an answer corresponding to the type of utterance sentence uttered by the user, a statement sentence (D; Declaratio
n), impression sentence (I; Impression), conditional sentence (C; Conditi
On), result sentence (E; Effect), time sentence (T; Time), place sentence (L; Location), negative sentence (N; Negation), etc.

That is, each answer sentence is, as shown in FIG.
For example, the discourse range (Sato) {subordinate concept: home run, superordinate concept; grass baseball, synonym: Panda Sato / Sato player / panda] and each topic title are associated.

As shown in the figure, for example, the topic title 1-1 is {(Sato; *; I like it): This is in the order of (subject; object; action) as described above. If the order is the same below}, the answer sentence 1 corresponding to the topic title 1-1
-1 is (DA; statement affirmative sentence "I like Sato"),
(IA; affirmative statement "I really like Sato"), (C
A: Conditional affirmative statement "Because Sato's home run is very impressive"), (EA; Result affirmative statement "I always watch Sato's games on TV"), (TA; Time affirmative statement "Actually, Koshien I've come to like it for five consecutive bats in "", (LA; place affirmative sentence "I like a serious face when standing at a blow"), (NA; repulsive affirmative sentence "people who dislike Sato. I don't want to talk to you, goodbye ”).

In the present embodiment, the conversation control unit 300, as shown in FIG. 2, has a management unit 310, a reflexive determination unit 320, a parrot judgment unit 330, and a conversation range determination unit 3.
40, an abbreviation completion unit 350, a topic search unit 360,
It has an answer sentence search unit 370.

The management section 310 controls the entire conversation control section 300. Specifically, the management unit 310, to which the character string signal is input from the input unit 100 or the voice recognition unit 200, extracts the input character string signal from the morpheme extraction unit 410.
Output to. In addition, the management unit 310, the answer sentence search unit 37
The answer sentence retrieved with 0 is output to the output unit 600.

The reflexive determination unit 320 includes a morpheme extraction unit 41.
The first morpheme information extracted with 0 is compared with each standard content,
It is a fixed form acquisition means for searching fixed form contents including the first morpheme information from the fixed form contents.

Here, the fixed contents mean the reflection element information for replying the fixed contents to the utterance contents from the user, and this reflection element information is the reflection element database 801 (fixed storage means). ) Are stored in advance.
As the reflective element information, in the present embodiment, as shown in FIG. 13, for example, "Good morning", "Hello", "Good evening", "greeting elements" such as "Hey", "I see", "Really?" Examples include "standard elements".

Specifically, the reflexive determination unit 320 to which the topic search command signal is input from the sentence structure analysis unit 430 is stored in the first morpheme information included in the input topic search command signal and the reflection element database 801. The reflective element information including the first morpheme information is searched from each reflective element information, and the searched reflective element information is output to the management unit 310.

That is, assuming that the reflection element information is D1 and the first morpheme information is W, the reflection determining unit 320 has W∩D1 ≠ φ.
When it is determined that the relationship of (φ: empty set) is established, the processing for making the above-mentioned reflexive reply is performed.

For example, when the user utters the utterance content "Good morning", the reflexive determination unit 320 collates the utterance content "Good morning" with each reflection element information, and selects from each reflection element information. , The reflection element information “good morning” including (matching with) the utterance content “good morning” is retrieved, and the retrieved reflection element information “good morning” is output to the management unit 310.

If the reflexive determination unit 320 cannot retrieve the reflexive element information including the utterance content from each reflexive element information, it returns the topic retrieval command signal input from the sentence structure analysis unit 430. It outputs to the determination unit 330.

The parrot judging section 330 includes a morpheme extracting section 4
The current first morpheme information extracted in step 20 is collated with the past answer contents stored in the parrot element database 802, and if the current first morpheme information is included in the past answer contents, an agreement is reached. It is a fixed form acquisition means for acquiring the contents.

Here, the term "back-and-back" is used in this embodiment.
User's utterance content as it is (or content close to it)
It means to say back. In the present embodiment, the parrot element is composed of the first morpheme information or the like that constitutes the content of the answer output immediately before from the conversation control device 1.
As shown in FIG. 4, for example, "horse is beautiful"(horse;*; beautiful), "I like Sato"(Sato;*; I like), etc.

In addition, a parrot element database 802
Is also an agreement storage unit that stores in advance the agreement content for agreeing to the input information input by the user. The contents of the agreement include, for example, the input information input by the user last time (the previous input information by the user is “A movie name is S
If it is "Mr.?", The content of the agreement includes "A is the director of the movie name is Mr. S"), "Yes, it is", "It is true", etc.

Specifically, the parody return judgment unit 330 to which the topic search command signal is input from the reflexive judgment unit 320, the first morpheme information and the parrot return element included in the input topic search command signal for each parallax return element. It is determined whether each morpheme constituting the above is compared with the morpheme element to include the first morpheme information (see FIG. 14).

When the parallax judging unit 330 judges that the first morpheme information is included in each parsing element, the agreement contents are acquired and the answer sentence including the acquired agreement contents is sent to the management unit 310. Output (parousel processing). That is,
Letting S be the parsing element (such as the previous answer sentence) and W be the first morpheme information, the parsing determination unit 330 determines that W⊂S, W
When the relationship of ≠ φ is established, the above-mentioned parrot feeding process is performed.

For example, the conversation control device 1 uses the answer sentence "
The director of the A movie name is Mr. S ”(Director of the A movie name; Mr. S;
*) (This order is subject; object; order of actions, the same shall apply hereinafter), and then the user answers "A is the director of the movie name Mr. S?" () When the utterance “Director of A movie name; Mr. S; *) is made, the parsing judgment unit 330 causes the first morpheme information of the user (Director of A movie name; Mr. S; *) and each morpheme of the answer sentence ( Since the director of A movie name; Mr. S; *) is the same, the user concludes that he is giving a reply to the answer contents, and acquires the memorized agreement contents "Yes" Then, the acquired agreement content is output.

Further, the parrot judging section 330 compares the present first morpheme information extracted by the morpheme extracting section 420 with the past first morpheme information stored in the parrot element database 802 to obtain the present first morpheme information. When one morpheme information is included in the first morpheme information in the past, it is also a fixed form acquisition means for acquiring the content of repulsion.

Specifically, when the user utters the utterance content that "horse is beautiful", and the conversation control device 1 outputs the content "it is good for a horse to be lively" as an answer content. Later, when the user repeats the utterance content that "horse is beautiful", the parrot judgment unit 330 causes the morphemes (first morpheme information) {horse; *; Beautiful} and the previous utterance "The horse is beautiful"
Since each morpheme (first morpheme information) {horse; *; beautiful} that composes the same matches the content of the response from the conversation control device 1 "the horse may have a sense of dynamism" Can be concluded to have not heard at all.

In this case, since the user has not heard the reply contents from the conversation control device 1, the parsing judgment unit 330 obtains the stored repulsion contents (for example, do not repeat the same contents), It is possible to output the acquired repulsion content.

On the other hand, when the parody judgment unit 330 judges that the first morpheme information is the same as the content of the previous answer sentence, or that the first morpheme information is not the same as the previous first morpheme information, the reflexive judgment is made. The topic search command signal input from the unit 320 is output to the discourse range determination unit 340.

Although the above-mentioned parsing judgment unit 330 has shown the processing when the user makes parsing for the "contents of reply of the conversation control device 1", the following processing can also be carried out. . For example, when the output unit 600 outputs an answer sentence "a horse is beautiful", the user asks "why a horse is beautiful?", "Why is it beautiful?", Or "why?" This is a process of the parody judgment unit 330 performed when a utterance is made.

In this case, the parrot judging section 330 outputs the response sentence S "horse is beautiful" and the utterance content W from the user.
If you match ("Why is the horse beautiful? (Question)" or "Why beautiful? (Question)"),
c) ⊂S (This c means the utterance type of W, and this utterance type is determined by the utterance type determination unit 440 described later. The utterance type is, for example, questioned as described later. Since a relation such as a sentence) is established, a “conditional” parsing process (a process when the user performs parsing with an interrogative sentence on the answer content) is performed.

As the "conditional" parsing process, for example, when the conversation control device 1 outputs an answer sentence "The horse is beautiful", the user asks "why is the horse beautiful?"
When the utterance content of “No.” is uttered, in order to solve the user's doubts, the parody judgment unit 330 gives a reply sentence such as “The horse is not beautiful” to the parody element database 802.
Processing for acquiring the obtained answer sentence from the management unit 310.

The discourse range determination unit 340 is used by the phrase analysis unit 42.
It is a discourse search means that collates the first morpheme extracted in 0 with each discourse range and retrieves the discourse range including the first morpheme information from each discourse range.

Specifically, the discourse range determination unit 340 to which the topic search command signal is input from the parody judgment unit 330 determines the discourse range of the user based on the input discourse search command signal. That is, the discourse range determination unit 340, based on the input search command signal, the conversation database 500.
From among the above, search for a range (discourse range) that is relevant to the content spoken by the user.

For example, the discourse range determination unit 340 includes the first morpheme information (interesting movie; *; is present) included in the input topic search command signal (is there an interesting movie? }, The first morpheme information is collated with the discourse range group, and the morpheme that constitutes the first morpheme information in the discourse range group (for example, "
When the movie “) is included, the“ movie ”included in the first morpheme information is determined as the discourse range. In this case, the discourse range determination unit 340 includes the discourse range“ movie ”in the first morpheme information. Therefore, the input first morpheme information is included in the topic search command signal and output to the topic search unit 360.

On the other hand, if the discourse range group is not included in the first morpheme information, the discourse range determination unit 340 includes the input first morpheme information in the topic search command signal and sends it to the abbreviated sentence complementation unit 350. Output.

As a result, the topic retrieval unit 360 described later will be described.
Can collate each “topic title” belonging to the “discourse range” determined by the discourse range determination unit 340 with the first morpheme information specified by the sentence structure analysis unit 430, so that “all” Since it is not necessary to collate the “topic title” (second morpheme information) with the first morpheme information, the answer sentence search unit 370, which will be described later, can shorten the time until the final answer sentence is searched.

As described above, the discourse range determining unit 340 collates the first morpheme information with the discourse range group, and if the discourse range group contains the morpheme of the first morpheme information, discourse the morpheme. Although it is determined as the range, it is not limited to this, and the morpheme of the parody returning element searched immediately before by the parody determining unit 330 or the morpheme constituting the utterance content uttered by the user is determined as the discourse range. May be. The abbreviated sentence complementing unit 350, which will be described later, can add the discourse range to the first morpheme information in which the morpheme is omitted, using the discourse range determined by the discourse range determining unit 340.

The abbreviated sentence complementing unit 350 includes a clause analyzing unit 420.
It is an attribute search means for searching an attribute that does not include a morpheme from among the attributes (subject, object, action, etc.) that form the first morpheme information based on the extracted first morpheme information. Also, the abbreviated sentence complementing unit 350
Based on the retrieved attribute, the discourse range determination unit 34 is set as the attribute.
It is also a morpheme addition means for adding the morphemes forming the discourse range searched for by 0.

Specifically, the abbreviated sentence complementation unit 350 to which the topic search command signal has been input from the discourse range determination unit 340, the first morpheme information based on the first morpheme information included in the input discourse search command signal. If the utterance content consisting of the first morpheme information is an abbreviation sentence, the morpheme of the discourse range to which the first morpheme information belongs is added to the first morpheme information. .

For example, in the abbreviated sentence complementing unit 350, the morphemes forming the first morpheme information included in the input topic search command signal are (director; *; *) (director?) In this case, the abbreviation is meant because it is unclear whether the director is the director.)
If the first morpheme information belongs to the discourse range determined by 0 (A movie name; this A movie name indicates the title of the movie), the determined discourse is the morpheme that constitutes the first morpheme information. A range (A movie name) is added to the first morpheme information (director of "A movie name";*; *).

That is, assuming that the first morpheme information is W and the determined discourse range is D, the abbreviated sentence complementing unit 350 adds the discourse range D to the first morpheme information W, and adds the first morpheme information after the addition. It is included in the topic search command signal and output to the topic search unit 360.

As a result, even when the first morpheme information is an abbreviated sentence and it is not clear in Japanese, the abbreviated sentence complementation unit 350 can: The discourse range D (A movie name) is added to the first morpheme information W (director; *; *), and the first morpheme information is W '(A movie name director; *; *) {A movie name director What? }
Even if the user's utterance content is an abbreviation, it can be supplemented based on the previously determined discourse range, and the abbreviation can be clarified. it can.

Therefore, the abbreviated sentence complementing unit 350 ensures that the utterance contents constituting the first morpheme information are in proper Japanese even if the utterance contents constituting the first morpheme information are abbreviated sentences. Since the specific morpheme can be complemented to the one morpheme information, the topic search unit 360, based on the first morpheme information after the complement, the optimum “topic title” (second morpheme information) related to the first morpheme information. ) Can be acquired, and the answer sentence search unit 370 can output the answer content more suitable for the utterance content of the user based on the “topic title” acquired by the topic search unit 360.

The topic search unit 360 collates the first morpheme information extracted by the phrase analysis unit 420 or the first morpheme information complemented by the abbreviated sentence complementation unit 350 with each second morpheme information, and each second morpheme information. It is a first searching means for searching the second morpheme information including the morphemes forming the first morpheme information from the morpheme information.

Specifically, the topic search unit 360 to which the topic search command signal is input from the discourse range determination unit 340 or the abbreviated sentence complementation unit 350 is based on the first morpheme information included in the input topic search command signal. The "topic title" including the morpheme of the first morpheme information is searched from each "topic title" (second morpheme information) belonging to the discourse range determined by the discourse range determination unit 340, and this search result is searched. As a result signal, the answer sentence search unit 370 and the utterance type determination unit 440
Output to.

For example, when the "case composition" that constitutes the first morpheme information is (Sato; *; I like) {I like Sato}, the topic retrieval unit 360, as shown in FIG. Each morpheme (Sato; *; I like) belonging to the above "case composition" and each topic title 1-1 to 1-4 belonging to the discourse range (Sato)
And a topic title 1-1 (Sato; *) that matches (or approximates) each morpheme (Sato; *; I like) that belongs to the "case composition" among the topic titles 1-1 to 1-4. ; I like), and outputs the search result as a search result signal to the answer sentence search unit 370 and the utterance type determination unit 440.

The utterance type determination unit 440, to which the search result signal is input from the topic search unit 360, searches for a specific answer sentence to be answered by the corresponding user based on the input search result signal. An answer search command signal (this answer search command signal also includes the determined “utterance sentence type”) is output to the answer sentence search unit 370.

The answer sentence search unit 370 is the topic search unit 360.
It is an answer acquisition unit that acquires the answer sentence associated with the second morpheme information, based on the second morpheme information (topic title) searched in. In addition, the response sentence search unit 370 collates the utterance type of the identified user with each answer type associated with the second morpheme information, based on the second morpheme information retrieved by the topic search unit 360, It is also a second search means for searching the answer type that matches the utterance type of the user from among the respective answer types.

Specifically, the answer sentence search unit 370, to which the search result signal from the topic search unit 360 and the answer search command signal from the utterance type determination unit 440 have been input, selects the topic title corresponding to the input search result signal. (Based on search results;
Based on the second morpheme information) and the "type of utterance sentence" (utterance type) corresponding to the answer search command signal, the answer sentence group (each answer content) associated with the "topic title"
From among the search results, search for an answer sentence consisting of an answer type that matches the “sentence type” (DA, IA, CA, etc.) (this answer type means the “answer sentence type” shown in FIG. 11). .

For example, the answer sentence search unit 370 determines that the topic title corresponding to the search result is the topic title 1 shown in FIG.
-1 (Sato; *; I like it), answer sentence 1-1 (DA, which is associated with the topic title 1-1)
IA, CA, etc.), the “utterance sentence type” (for example, DA; utterance type) determined by the utterance type determination unit 440.
Answer sentence 1-1 (D) consisting of the answer type (DA) that matches
A: (I also like Sato) is searched, and the searched reply sentence is output to the management unit 310 as a reply sentence signal.

The management unit 310 to which the answer sentence signal is input from the answer sentence search unit 370 outputs the input answer sentence signal to the output unit 600. In addition, the management unit 310 to which the reflection element information is input from the reflexive determination unit 320 or the content of the parallax return processing from the parallax determination unit 330 is input, the answer sentence corresponding to the input reflection element information, the content of the input parallax process. The answer sentence corresponding to is output to the output unit 600.

The output unit 600 is an output means for outputting the answer sentence acquired by the answer sentence search unit 370. In the present embodiment, for example, a speaker, a display, etc. can be mentioned. Specifically, the output unit 600 to which the answer sentence is input from the management unit 310 outputs the input answer sentence {for example, I also like Sato}.

(Conversation Control Method Using Conversation Control Device) A conversation control method by the conversation control device 1 having the above-mentioned configuration is as follows:
It can be carried out by the following procedure. FIG. 15 is a flowchart showing the procedure of the conversation control method according to this embodiment.

First, the input section 100 performs a step of acquiring the contents of the utterance from the user (S101). Specifically, the input unit 100 acquires a voice that constitutes the utterance content of the user, and uses the acquired voice as a voice signal, the voice recognition unit 200.
Output to. In addition, the input unit 100 specifies a character string corresponding to the input information (other than voice) based on the input information (other than voice) input by the user, and the conversation control unit uses the specified character string as a character string signal. Output to 300.

Next, the voice recognition unit 200 is changed to the input unit 10
Based on the utterance content acquired at 0, a step of identifying the character string corresponding to the utterance content is performed (S102). Specifically, the voice recognition unit 200 to which the voice signal is input from the input unit 100 analyzes the input voice signal, and outputs a character string corresponding to the analyzed voice signal to the voice recognition dictionary storage unit 700.
It is specified by using the dictionary stored in, and the specified character string is output to the conversation control unit 300 as a character string signal.

Then, the morpheme extraction unit 410 performs a step of extracting, as the first morpheme information, each morpheme constituting the minimum unit of the character string based on the character string specified by the voice recognition unit 200 (S103).

Specifically, the morpheme extraction unit 410 to which the character string signal is input from the management unit 310, the character string corresponding to the input character string signal, and the nouns and adjectives previously stored in the morpheme database 450. A morpheme group such as a verb is matched, each morpheme (m1, m2, ...) Matching the morpheme group is extracted from the character string, and each extracted morpheme is output to the clause analysis unit 420 as an extraction signal. .

Then, the phrase analysis unit 420 performs a step of collecting each morpheme in the phrase form based on each morpheme extracted by the morpheme extraction unit 410 (S104). Specifically, the bunsetsu analysis unit 420 to which the extraction signal is input from the morpheme extraction unit 410 uses the morphemes corresponding to the input extraction signal to group them in a bunsetsu form.

That is, as shown in FIG. 4, the bunsetsu analyzing section 420 determines the dependency element (eg, ga.ha ...) of each morpheme based on each morpheme corresponding to the input extracted signal.
Is extracted, and each morpheme is collected into each clause based on the extracted dependency element. The phrase analysis unit 420 that collects each morpheme into each phrase uses the sentence structure information that includes each phrase that collects each morpheme and each morpheme that forms each phrase as a sentence pattern signal, and the sentence structure analysis unit 430 and the utterance type determination unit 44.
Output to 0.

After that, the sentence structure analysis unit 430 performs a step of classifying each morpheme of the first morpheme information segmented by the phrase analysis unit 420 into each attribute such as a subject case and a target case (S).
105). Specifically, the sentence structure analysis unit 430, to which the sentence pattern signal is input from the phrase analysis unit 420, detects each morpheme included in the sentence based on each morpheme corresponding to the input sentence pattern signal and the phrase formed of each morpheme. Determine the case composition.

That is, as shown in FIG. 5, for example, when the dependency element of each morpheme is “” or “wa”, the sentence structure analysis unit 430 determines that the morpheme in front of the dependency element is Judge as a subject (subject or nominative case). In addition, for example, when the dependency element of each morpheme is “no” or “wa”, the sentence structure analysis unit 430 determines that the morpheme in front of the dependency element is an object (target).

Further, for example, when the dependency element of each morpheme is “do”, the sentence structure analysis unit 430 determines that the morpheme in front of the dependency element is an action (predicate; this predicate is a verb, an adjective, etc.). It consists of)).

The sentence structure analysis unit 430, which has determined the “case composition” of each morpheme that constitutes each phrase, will be described later based on the first morpheme information associated with the determined “case composition”. The topic search command signal for specifying the range of is output to the topic search unit 360.

Next, the utterance type determination unit 440 performs a step of identifying the utterance type indicating the type of utterance content based on the bunsetsu identified by the bunsetsu analysis unit 420 (S10).
6). Specifically, the “utterance sentence type” (utterance type) is determined based on each morpheme corresponding to the sentence pattern signal input from the bunsetsu analysis unit 420 and the bunsetsu composed of each morpheme.

That is, the utterance type determination unit 440 compares each bunsetsu with the dictionary stored in the utterance type database 460 based on each bunsetsu corresponding to the input sentence pattern signal, From, the sentence elements related to each dictionary are extracted. The utterance type determination unit 440 that has extracted the sentence element related to each dictionary from each bunsetsu determines the “utterance sentence type” based on the extracted sentence element.

The utterance type determination unit 440 outputs an answer search command signal for causing the corresponding user to search for a specific answer sentence to the answer sentence retrieval unit 370 based on an instruction from the topic retrieval unit 360 described later. To do.

Next, the reflexive determination unit 320 collates the first morpheme information extracted by the morpheme extraction unit 410 with each standard content, and retrieves the standard content including the first morpheme information from each standard content. Steps are performed (S107; reflective processing).

Specifically, the reflex determination unit 320 to which the topic search command signal is input from the sentence structure analysis unit 430 is stored in the first morpheme information included in the input topic search command signal and the reflection element database 801. It collates each reflection element information (standard content) that is present, and from each reflection element information,
The reflective element information including the first morpheme information is searched, and the searched reflective element information is output to the management unit 310.

When it is not possible to retrieve the reflection element information including the first morpheme information from each reflection element information, the reflexive determination section 320 receives the topic retrieval instruction signal input from the sentence structure analysis section 430. Is output to the parsing judgment unit 330.

Next, a step in which the parsley judging unit 330 collates the first morpheme information extracted by the morpheme extracting unit 410 with each parsing element and retrieves each parsing element containing the first morpheme information from each parsing element. (S1
08: parrying process).

When it is determined that the first morpheme information is contained in each of the parrot return elements, the parrot return element 330 acquires the parrot return element including the first morpheme information, and returns the response including the obtained parrot return element. The sentence is output to the management unit 310 (parsing process). That is, assuming that the parallax element (reply sentence output last time, utterance content uttered by the user last time, etc.) is S and the first morpheme information is W, the parody judgment unit 33
0 is W⊂S and W ≠ φ, if
Perform the parrying process shown above.

On the other hand, when the parallax judging section 330 judges that the first morpheme information is not included in each parsing element, the topic search command signal input from the reflexive judging section 320 is used to determine the discourse range. Output to the unit 340.

Then, the discourse range determination unit 340 collates the first morpheme extracted by the clause analysis unit 420 with each discourse range, and retrieves the discourse range including the first morpheme information from each discourse range. Steps are performed (S109).

Specifically, the discourse range determination unit 340 to which the topic search command signal is input from the parody judgment unit 330, the conversation database 5 based on the input search command signal.
From 00, a relevant range (discourse range) regarding the content spoken by the user is searched.

For example, the discourse range deciding unit 340 has the first morpheme information included in the input topic search command signal (interesting movie; *; there) {is there any interesting movie? }, The first morpheme information is collated with the discourse range group, and the morpheme that constitutes the first morpheme information in the discourse range group (for example, "
When the movie “) is included, the“ movie ”included in the first morpheme information is determined as the discourse range. In this case, the discourse range determination unit 340 includes the discourse range“ movie ”in the first morpheme information. Therefore, the input first morpheme information is included in the topic search command signal and output to the topic search unit 360.

On the other hand, if the discourse range group is not included in the first morpheme information, the discourse range determination section 340 includes the input first morpheme information in the topic search command signal and sends it to the abbreviated sentence complementing section 350. Output.

Next, the abbreviated sentence complementing unit 350 selects a morpheme from each attribute (subject, object, action, etc.) that constitutes the first morpheme information based on the first morpheme information extracted by the clause analysis unit 420. Perform the steps to search for attributes that are not included. After that, the abbreviated sentence complementing unit 35
0 performs a step of adding a morpheme that constitutes the discourse range previously searched by the discourse range determination unit 340 to the attribute based on the attribute that does not include the searched morpheme (S11).
0: Completion of abbreviations).

Specifically, the abbreviated sentence complementation unit 350 to which the topic search command signal is input from the discourse range determination unit 340, the first morpheme information is based on the first morpheme information included in the input discourse search command signal. If the utterance content consisting of the first morpheme information is an abbreviation sentence, the morpheme of the discourse range to which the first morpheme information belongs is added to the first morpheme information. .

For example, in the abbreviated sentence complementing unit 350, the morphemes forming the first morpheme information included in the input topic search command signal are (director; *; *) (director?) If it is “Director, it is unclear that it is an abbreviation.”), The discourse range determined by the discourse range determination unit 340 (A movie name; this A movie name is the movie title). If the first morpheme information belongs to the first morpheme information, the morpheme (A movie name) of the decided discourse range is added to the first morpheme information (“A movie name”) to the morpheme that constitutes the first morpheme information. Supervision; *; *).

That is, assuming that the first morpheme information is W and the determined discourse range is D, the abbreviated sentence complementing unit 350 adds the discourse range D to the first morpheme information W, and adds the first morpheme information after the addition. It is included in the topic search command signal and output to the topic search unit 360.

Next, the topic search unit 360 causes the phrase analysis unit 420 to extract the first morpheme information or the abbreviated sentence complementation unit 3.
The first morpheme information complemented by 50 is compared with each second morpheme information, and the step of searching the second morpheme information for the second morpheme information including the morpheme constituting the first morpheme information is performed. (S111).

Specifically, the topic search unit 360 to which the topic search command signal is input from the discourse range determination unit 340 or the abbreviated sentence complementation unit 350 is based on the first morpheme information included in the input topic search command signal. The "topic title" including the morpheme of the first morpheme information is searched from each "topic title" (second morpheme information) belonging to the discourse range determined by the discourse range determination unit 340, and this search result is searched. As a result signal, the answer sentence search unit 370 and the utterance type determination unit 440
Output to.

For example, when the “case composition” that constitutes the first morpheme information is (Sato; *; I like) {I like Sato}, the topic retrieval unit 360, as shown in FIG. Each morpheme (Sato; *; I like) belonging to the above "case composition" and each topic title 1-1 to 1-4 belonging to the discourse range (Sato)
And a topic title 1-1 (Sato; *) that matches (or approximates) each morpheme (Sato; *; I like) that belongs to the "case composition" among the topic titles 1-1 to 1-4. ; I like), and outputs the search result as a search result signal to the answer sentence search unit 370 and the utterance type determination unit 440.

The utterance type determination unit 440, to which the search result signal is input from the topic search unit 360, searches for a specific answer sentence for the corresponding user based on the input search result signal. An answer search command signal (this answer search command signal also includes the determined “utterance sentence type”) is output to the answer sentence search unit 370.

Then, the answer sentence search unit 370 determines the utterance type of the identified user and each answer type associated with the second morpheme information based on the second morpheme information retrieved by the topic retrieval unit 360. A step of collating and searching for an answer type that matches the user's utterance type from the respective answer types and acquiring an answer sentence associated with the searched answer type is performed (S112).

Specifically, the answer sentence search unit 370, to which the search result signal from the topic search unit 360 and the answer search command signal from the utterance type determination unit 440 have been input, returns to the topic title corresponding to the input search result signal. (Based on search results;
Based on the second morpheme information) and the "type of utterance sentence" (utterance type) corresponding to the answer search command signal, the answer sentence group (each answer content) associated with the "topic title"
From among the search results, search for an answer sentence consisting of an answer type that matches the “sentence type” (DA, IA, CA, etc.) (this answer type means the “answer sentence type” shown in FIG. 11). .

For example, in the answer sentence search unit 370, the topic title corresponding to the search result is the topic title 1 shown in FIG.
-1 (Sato; *; I like it), answer sentence 1-1 (DA, which is associated with the topic title 1-1)
IA, CA, etc.), the “utterance sentence type” (for example, DA; utterance type) determined by the utterance type determination unit 440.
Answer sentence 1-1 (D) consisting of the answer type (DA) that matches
A: (I also like Sato) is searched, and the searched reply sentence is output to the management unit 310 as a reply sentence signal.

Next, the management unit 310 to which the reply sentence signal is input from the reply sentence search unit 370 outputs the input reply sentence signal to the output unit 600. In addition, the reflective determination unit 320
The management unit 310 to which the reflection element information is input, or the content of the trick-and-repelling process is input from the trick-and-repelling determination unit 330, outputs the reply sentence corresponding to the input reflection-element information and the reply sentence corresponding to the input contents of the trick-and-repelling process. It is output to the unit 600. Output unit 600 to which the answer sentence is input from the management unit 310
Is the input answer {for example, I also like Sato}
Is output (S113).

(Operation and Effect of Conversation Control System and Conversation Control Method) According to the invention of the present application having the above-described configuration, the reflex determination unit 320 configures the first morpheme information that constitutes the utterance content uttered by the user. Since it is possible to search the standard contents including the first morpheme information from each standard content by collating each of the standard contents stored in advance with each of the pre-stored standard contents, the reflexive determination unit 320 determines, for example, that the first morpheme information is “ Hello "in the case of fixed content, such as, the standard contents same boilerplate content and" it is possible to say hello "or the like.

Further, when the utterance content of the user is the fixed content, the reflexive determination unit 320 replies the fixed content (greeting, etc.), so that the user first communicates with the conversation control device 1. You can feel as if you are communicating with each other.

Further, the parrot judging section 330 collates the present first morpheme information with the past answer contents, and if the present first morpheme information is not included in the past answer contents, it is stored in advance. Since it is possible to obtain the agreed content, the parsing and judgment unit 330 determines that the user can answer the past reply content if the input information currently input by the user and the past reply content match. It is possible to conclude that the input information for parsing (that the user is listening again to the answer contents) has been input.

[0162] In this case, the parsing judgment unit 330 acquires the consensus contents that have been stored because the user is parsing the past reply contents, and the acquired consensus contents (for example, "Yes." , Etc.) can be output. Thereby, if the user does not understand the meaning of the answer content output from the conversation control device 1, the user can listen again and listen again to the answer content.
I can also feel as if I was talking to another user.

Further, the parrot judging section 330 collates the present first morpheme information with the past first morpheme information, and when the present first morpheme information is included in the past first morpheme information, the repulsion is made. Since the contents can be acquired, the parody judgment unit 330 repeats the same contents as the previous input information when the previously input information is included in the previously input information. It is possible to judge that the user has input the information, and it can be concluded that the user has not properly answered the reply content from the conversation control device.

In this case, since the user has not properly responded to the previous reply content, the parsing judgment unit 330 acquires the stored repulsion content in order to repel the user, and acquires it. The content of the repulsion is output. As a result, if the user does not input the appropriate input information with respect to the reply content from the conversation control device 1, the repulsion content is output from the conversation control device 1, so that the user may have a conversation with another user. You can feel as if you are there.

Further, the topic retrieval unit 360 may collate each second morpheme information belonging to the "discourse range" with the first morpheme information in order to retrieve the second morpheme information which is similar to the first morpheme information. , It is not necessary to match the “all” second morpheme information with the first morpheme information, so that the time required to retrieve the second morpheme information that is similar to the first morpheme information can be shortened.

As a result, the topic search unit 360 can search (pinpoint search) the second morpheme information that is similar to the first morpheme information in a short time, so that the answer sentence search unit 370 can search the topic. The answer sentence associated with the second morpheme information can be acquired in a short time based on the second morpheme information retrieved by the unit 360, and the conversation control device 1
Can promptly reply to the utterance content from the user.

Further, the topic retrieval unit 360 retrieves, from each of the second morpheme information, the second morpheme information including the morpheme which constitutes the first morpheme information (elements which constitute the utterance content of the user), and returns the answer. Since the sentence search unit 370 can acquire the answer content associated with the second morpheme information based on the second morpheme information searched by the topic search unit 360,
The answer sentence search unit 370 considers a semantic space (subject, target, etc.) constructed by each morpheme, based on each morpheme (first morpheme information) that constitutes the utterance content of the user, and based on this semantic space Therefore, it is possible to acquire the answer content created in advance by using the entire utterance content as a keyword and acquire the answer content more suitable for the utterance content than simply acquiring the answer content associated with the keyword. You can

Further, since the topic retrieval unit 360 retrieves the second morpheme information including the first morpheme information, it is not necessary to retrieve the second morpheme information which completely matches the utterance content of the user, and the conversation control device The developer who develops No. 1 does not need to previously store a huge amount of reply content corresponding to the utterance content that will be uttered by the user, and can reduce the capacity of the storage unit.

Furthermore, the answer sentence search unit 370 matches the utterance type of the user from the answer types (statement, affirmation, place, repulsion, etc.) associated with each second morpheme information belonging to the “discourse range”. Since it is possible to retrieve the answer type to be obtained and obtain the answer content associated with the answer type based on the retrieved answer type, the conversation control device 1 makes the conversation control device 1 the utterance type that constitutes the conversation content of the user, for example, Matched to the type of utterance of the user from multiple answers based on what the user simply stated, what the user had impressions, what the user said about the spatial element, etc. Since the answer contents can be acquired, it is possible to give a more optimal answer to the corresponding user.

Furthermore, the answer sentence search unit 370 selects from the answer types associated with the respective second morpheme information belonging only to the “discourse range” searched by the discourse range determination unit 340,
Since it is only necessary to search for the answer type that matches the user's utterance type (pinpoint search is possible), the answer types associated with the "all" second morpheme information and the user's utterance type are searched point by point. It is not necessary and the optimum answer content corresponding to the type of utterance of the user can be acquired in a short time.

Finally, the abbreviated sentence complementing unit 350 uses the first morpheme information constituting the utterance content of the user as an abbreviated sentence, and even if the first morpheme information is not clear in Japanese, the discourse range including the first morpheme information , The discourse range can be added to the first morpheme information to complement the first morpheme information consisting of abbreviations.

Thus, the abbreviated sentence complementing unit 350 ensures that the utterance contents constituting the first morpheme information are in proper Japanese even if the utterance contents constituting the first morpheme information are abbreviated sentences. Since a specific morpheme (such as a morpheme forming a discourse range) can be complemented to the one morpheme information, the topic search unit 360, based on the complemented first morpheme information complemented by the abbreviated sentence complementation unit 350, The optimum second morpheme information related to the first morpheme information can be acquired, and the answer sentence search unit 370 is more suitable for the utterance content of the user based on the second morpheme information acquired by the topic search unit 360. Answer contents can be output.

As a result, even if the input information from the user is the abbreviated sentence, the conversation control device 1 can use the abbreviated sentence through the past search results without using the functions such as the neural network and the artificial intelligence. It is possible to infer what it means, and the developer of the conversation control device 1 does not need to install a neuro network or artificial intelligence.
The system of the conversation control device 1 can be constructed more easily.

[Modification] The present invention is not limited to the above embodiment, and the following modifications can be made.

(First Modification) In this modification, the conversation database 500 is an element storage means for storing a plurality of pieces of element information indicating the entire set group made up of a plurality of morphemes in association with the set group. May be. Further, the morpheme extraction unit 410 collates the morpheme extracted from the character string with each set group, selects a set group including the extracted morpheme from each set group, and selects an element associated with the selected set group. Information may be extracted as the first morpheme information.

As shown in FIG. 16, some morphemes included in the character string uttered by the user are similar. For example, as shown in FIG. 16, when the element information indicating the entire group is “gift”, the “gift” is similar to a present, a gift, a year-end gift, a mid-year gift, a celebration (a group). Therefore, when there is a morpheme similar to the “gift” (such as the above gift), the morpheme extraction unit 410 can handle the similar morpheme as the “gift”.

That is, for example, when the morpheme extracted from the character string is a "present", the morpheme extraction unit 410 indicates that the element information representing the "present" is a "gift", as shown in FIG. Therefore, the "present" can be replaced with the "gift".

As a result, the morpheme extraction unit 410 can sort out morphemes that are similar to each other, so that a developer who develops a conversation control device can create a semantic space that is understood from mutually similar first morpheme information. It is not necessary to create the corresponding second morpheme information and the response contents related to the second morpheme information one by one, and as a result, the amount of data stored in the storage unit can be reduced.

(Second Modification) As shown in FIG. 17, in this modification, the topic calculation unit 360 may include a ratio calculation unit 361 and a selection unit 362.

The ratio calculation unit 361 has a morpheme extraction unit 410.
Collate the first morpheme information and each second information extracted in,
It is a calculating means for calculating the ratio of the first morpheme information to the second morpheme information for each second morpheme information.

Specifically, as shown in FIG. 17, the ratio calculation unit 361 to which the topic search command signal is input from the sentence structure analysis unit 430 is based on the first morpheme information included in the input topic search command signal. Then, the first morpheme information is collated with each topic title (second morpheme information) stored in the conversation database 500, and the first morpheme is included in each topic title for each topic title. Calculate the percentage of information.

For example, as shown in FIG. 17, the first morpheme information constituting the utterance sentence uttered by the user is (Sato;
*; I like) {I like Sato}, the ratio calculation unit 361 determines that each morpheme (Sato; *; I like) belonging to the "case composition" and each morpheme (Sato; *) included in the topic title. ;
(I like it), and add "Case composition" to the topic title above.
The ratio of each morpheme belonging to (Sato; *; I like) is calculated to be 100%. The ratio calculation unit 361
These calculations are performed for each topic title, and each calculated ratio is output to the selection unit 362 as a ratio signal.

The selection unit 362 determines, according to the size of each ratio calculated for each second morpheme information by the ratio calculation unit 361.
It is a selection unit that selects one second morpheme information item from each second morpheme information item.

Specifically, the selection unit 362, to which the ratio signal is input from the ratio calculation unit 361, includes the respective ratios included in the input ratio signal (elements of “case composition” / elements of “topic title” × 100). From among the above, for example, a topic title with a high ratio is selected (see FIG. 18). The selecting unit 362 that selects a topic title with a high ratio outputs the selected topic title as a search result signal to the response sentence search unit 370 and the utterance type determination unit 440. The answer sentence search unit 370 is the selection unit 3
Based on the topic title selected in 62, the answer sentence associated with the topic title is acquired.

As a result, the selection unit 362 calculates the ratio of the first morpheme information to the second morpheme information for each second morpheme information, and the calculated ratio of each second morpheme information is calculated. Depending on the size, from each second morpheme information,
Since one second morpheme information can be selected, the selection unit 362, for example, the second morpheme information in which the first morpheme information (which constitutes the utterance content of the user) occupies a large proportion of the second morpheme information. , If it can be obtained from a plurality of second morpheme information group, it is possible to more accurately obtain the second morpheme information that follows the semantic space grasped from the first morpheme information, and as a result, Sentence search unit 370
Can give an optimal answer to the user's utterance content.

Further, since the selection unit 362 can select a topic title having a high ratio calculated by the ratio calculation unit 361 from a plurality of topic titles, the case composition included in the utterance sentence of the user is selected. Even if each morpheme belonging to "" does not completely match each topic title stored in the conversation database 500, a topic title closely related to each morpheme belonging to "case composition" can be acquired.

As a result, the selecting unit 362 can acquire the topic title closely related to the "case configuration" that constitutes the first morpheme information, so that the developer who develops the conversation control device 1 can obtain the first morpheme information. It is not necessary to store in the conversation database 500 the topic titles that completely match the constituent “case composition”, so that the capacity of the conversation database 500 can be reduced.

Further, the ratio calculation unit 361 determines the ratio of the first morpheme information to the second morpheme information for each second morpheme information belonging to only the "discourse range" retrieved by the discourse range determination unit 340. Since the calculation is performed, it is not necessary to calculate the ratio of the first morpheme information to the "all" second morpheme information, and the second morpheme information following the semantic space composed of the first morpheme information can be shortened. As a result, the optimum answer content for the utterance content from the user can be promptly output based on the acquired second morpheme information.

The ratio calculation unit 361 compares each morpheme of the first morpheme information belonging to each classified attribute with each morpheme of each second morpheme information stored in advance for each attribute for each attribute. However, it may be a first search unit that searches the second morpheme information in which at least one attribute includes each morpheme of the first morpheme information from each second morpheme information.

More specifically, the ratio calculation unit 361 to which the topic search command signal is input, for each “case” (subject; object; action) of the “case configuration” included in the input topic search command signal, Each morpheme belonging to the "case" is collated with each morpheme belonging to the "case" of the topic title consisting of the same "case", and it is determined whether or not the morphemes forming the "case" are the same.

For example, as shown in FIG. 19, if the morpheme of “case” of “case composition” is (dog; person; bite) {dog dog bite person} as shown in FIG. The morpheme "dog", "person", "bite" of the topic title consisting of those morpheme "dog", "person", "bite", and "case" which is the same as "case" that constitutes these morphemes The “morphology” morpheme consisting of the “case” that is the same as the “case” corresponding to each morpheme among the morphemes “dog”, “person”, and “bite” that form the topic title. The rate of matching with "dog", "person", and "bite" is calculated (100%).

If the element constituting the topic title is (person; dog; bite) {person bites dog},
Since the morphemes belonging to the two cases differ by the same procedure as described above, the ratio calculation unit 361 determines the degree of coincidence between the morphemes forming the “case composition” and the “topic title” by “case” to be 33.
% Is calculated (see FIG. 19).

The ratio calculation unit 361 that has calculated the ratio selects a topic title having a high ratio from each ratio, and the selected sentence title is used as a search result signal in the response sentence search unit 37.
0 and output to the utterance type determination unit 440.

As a result, the ratio calculation unit 361 sets each morpheme of the first morpheme information belonging to each classified “case composition” (subjective case, target case, etc.) and the topic title stored in advance in each “case case”. Since the second morpheme information that includes each morpheme of the first morpheme information in at least one “case” can be searched from each topic title, the ratio calculation unit 361 uses the normal word order. In the case of a utterance content composed of something different from, for example, "a person bites a dog", the morpheme of the subject case is "person" and the morpheme of the target case is "dog". You can search for the second morpheme information that matches the "case", and the answer content {"really?" Or "I don't know what you mean", etc. associated with that second morpheme information (person; dog; chew), etc. } Can be obtained.

That is, the ratio calculation unit 361 determines the utterance content that is difficult to identify, for example, “a person bites a dog” and “a dog bites a person”.
Since it is possible to identify the above, it is possible to give an optimum answer to the identified utterance content, for example, “really?” For the former and “okay?” For the latter.

Further, the ratio calculation unit 361 uses the "discourse range".
Since the second morpheme information including the morpheme of the first morpheme information in at least one attribute can be searched from each of the second morpheme information belonging to, the first of the "all" second morpheme information is searched. It is not necessary to acquire the two morpheme information, the second morpheme information following the semantic space composed of the first morpheme information can be acquired in a shorter time, and as a result, the conversation control device 1 acquires Based on the second morpheme information, it is possible to promptly output the optimum answer content for the utterance content from the user.

The selecting unit 362 may select one topic title from each topic title in accordance with a predetermined priority order. This priority order means the priority for being selected as a topic title.
This priority is predetermined by the developer at the development stage.

(Third Modification) As shown in FIG. 20, the present modification is not limited to the above-described embodiment and each modification, but includes the communication unit 800 in the conversation control devices 1a and 1b. , A communication unit 9 for transmitting and receiving data to and from the communication unit 800 via the communication network 1000.
00, each of the conversation databases 500b to 500d connected to the communication unit 900, and the servers 2a to 2c (conversation control system).

Here, the communication network 1000 is
It means a communication network for transmitting and receiving data, and in the present embodiment, for example, the Internet is mentioned.

In this modification, the conversation control devices 1a and 1b, the conversation databases 500b to 500d, and the servers 2a to 2c are limited for the sake of convenience. However, the present invention is not limited to this, and other conversation databases are also included. May be provided. A conversation database 50 is provided for the servers 2a to 2c.
The same contents as the contents stored in 0a to 500d are stored.

As a result, the conversation control unit 300 causes the conversation database 50 arranged inside the conversation control device 1a.
0a as well as via the communication network 1000,
Other conversation control device 1b, conversation database 500b-5
00d and the servers 2a to 2c can also be referred to, and therefore, for example, from the conversation database 500a, a discourse range associated with each morpheme (first morpheme information) belonging to the “case configuration” included in the topic search command signal. Even if it is not possible to search for the other conversation control device 1b, conversation databases 500b to 500d, and servers 2a to 2c.
By referring to, it is possible to search the discourse range related to the first morpheme information, and it is possible to search the answer sentence more suitable for the utterance sentence of the user.

(Fourth Modification) The sentence structure analysis unit 430 stores, in the conversation database 500, each “case composition” that constitutes the specified first morpheme information and each morpheme associated with each “case composition”. It may be one. The answer sentence search unit 370 may be configured to store, in the conversation database 500, each “case composition” and each morpheme associated with each “case composition” that make up the retrieved answer sentence.

The discourse range determination unit 340 may store the retrieved discourse range in the conversation database 500. The topic search unit 360 may store the searched second morpheme information in the conversation database 500.

The above-mentioned first morpheme information, second morpheme information, each "case configuration" constituting the first morpheme information or the second morpheme information, and each morpheme associated with each "case configuration" are searched. Each “case composition” forming each answer sentence, each morpheme associated with each “case composition”, and the searched discourse range may be stored in the conversation database 500 as history morpheme information in association with each other. it can.

The abbreviated sentence complementing unit 350 includes a clause analyzing unit 420.
From the attributes (subject, object, action, etc .; case configuration) that compose the first morpheme information based on the extracted first morpheme information, an attribute that does not include a morpheme is searched, and based on the searched attribute The history morpheme information stored in the conversation database 500 may be added to the attribute.

Specifically, the abbreviated sentence complementation unit 350 to which the topic search command signal has been input from the discourse range determination unit 340, the first morpheme information based on the first morpheme information included in the input discourse search command signal. If the utterance content consisting of is an abbreviation, and the utterance content consisting of the first morpheme information is an abbreviation (for example, the subject, object, or action does not have a predetermined morpheme),
The history morphological information stored in the conversation database 500 is added to the first morpheme information.

That is, if the subject included in the history morphological information is S1, the object is O1, the action A1, the discourse range is D1, and the omitted first morpheme information is W, the first morpheme information W1 after the complement is: S1∪W, O1∪
It can be expressed as W, A1∪W, or D1∪W.

The topic retrieval unit 360 includes the abbreviated sentence complementing unit 350.
By collating the first morpheme information W1 complemented with each second morpheme information and searching the second morpheme information including the first morpheme information W1 from each “topic title” (second morpheme information), The retrieved topic title is output to the response sentence search unit 370 and the utterance type determination unit 440 as a search result signal.

As a result, even if the utterance content consisting of the first morpheme information is an abbreviated sentence and it is not clear as Japanese, the abbreviated sentence complementing unit 350 causes the conversation database 50
Since the morpheme of the omitted first morpheme information can be complemented by using the history morphology information stored in 0,
It is possible to clarify the utterance content including the omitted first morpheme information.

Therefore, when the utterance content forming the first morpheme information is an abbreviated sentence, the abbreviated sentence complementing unit 350:
Since the omitted morphemes can be complemented in the first morpheme information so that the utterance content composed of the first morpheme information becomes appropriate Japanese, the topic retrieval unit 360 causes the topic search unit 360 to perform the morpheme complemented first morpheme information. Based on, the optimal "topic title" related to the first morpheme information (second morpheme information)
Based on the optimum “topic title” acquired by the topic search section 360, the response sentence search section 370 can output the reply content more suitable for the utterance content of the user.

(Fifth Modification) The topic retrieval unit 360 is shown in FIG.
As shown in FIG. 1, a deletion unit 361 and a discourse addition unit 362 may be provided. The deleting unit 361 determines the second morpheme information and the discourse range determining unit 34 based on the searched second morpheme information.
It is a deleting unit that collates the discourse range searched for 0 and deletes the morpheme that matches the discourse range from among the morphemes forming the second morpheme information.

Specifically, the topic search unit 360 to which the topic search command signal is input from the abbreviated sentence complementation unit 350 determines the first morpheme information included in the input topic search command signal and the discourse range determination unit 340. The second morpheme information that belongs to the discourse range is collated, and the second morpheme information that matches the first morpheme information is searched from the respective second morpheme information.

Then, the deleting unit 361 collates the second morpheme information with the morphemes constituting the discourse range determined by the discourse range determining unit 340 based on the retrieved second morpheme information, and determines the second morpheme. The morphemes that match the morphemes that make up the discourse range are deleted from the information, and the second morpheme information from which the morphemes have been deleted is output to the discourse addition unit 362 as a deletion signal.

That is, the deleting unit 361 removes the current discourse range D2 (this D2 is composed of morphemes) determined by the discourse range determining unit 340 from each morpheme t1 constituting the second morpheme information. (T2 = t1-D2, where t2 is the removed result).

The discourse adding unit 362 acquires and obtains another discourse range associated with the discourse range searched by the discourse range determining unit 340 based on the second morpheme information from which the morpheme was deleted by the deleting unit 361. It is a discourse adding unit that adds the morphemes forming the other discourse range to the second morpheme information.

Specifically, if the current discourse range D2 is a discourse range that is related to the answer sentence K1, then DK is the answer sentence K.
1 or another discourse range D3 that is related (in a sibling relationship) to the current discourse range D2 can be expressed as D3 = D2∪DK, so a morpheme that constitutes another discourse range D3 is added. The second morpheme information W2 after
= T2∪D3.

For example, each morpheme t1 constituting the second morpheme information is (A movie name; *; interesting) {A movie name is interesting? }, And when the current discourse range D2 determined by the discourse range determination unit 340 is (A movie name), the deletion unit 3
61 is, first, each morpheme t1 (A movie name; *; interesting)
The discourse range D2 (A movie name) is deleted from, and the deleted result is set to t2 (*; *; funny) (t2 = t1-D).
2).

If another discourse range D3 related to the current discourse range D2 (A movie name) is "B movie name", it is the first after adding the morphemes constituting the other discourse range D3. Since the dimorpheme information W2 is t2∪D3, (B movie name; *; interesting) {B movie name is interesting? } Can be used.

As a result, when the utterance content of the user is "A is the movie name interesting?"
Each morpheme (A movie name; *;
The second morpheme information (A movie name; *; funny) that matches with (interesting), the other second morpheme information (B movie name; *; funny) {B movie name is interesting? }, The answer sentence search unit 370 acquires the answer sentence associated with the second morpheme information changed by the discourse addition unit 362 (for example, “B movie name is funny”), It is possible to output the acquired answer sentence.

As a result, the answer sentence search unit 370 does not output the answer sentence for the utterance content of the user,
Since the answer sentence related to the utterance content can be output based on the second morpheme information including the morpheme added by the discourse adding unit 362, the output unit 600 causes the answer sentence searching unit 37 to output.
It is possible to output a more human-like answer sentence based on the answer sentence retrieved with 0.

Note that the discourse addition unit 362 is not limited to the one that adds another discourse range to the second morpheme information in which the morpheme has been deleted, and the history morpheme in the second morpheme information in which the morpheme has been deleted. Information (stored in the conversation database 500) may be added.

(Sixth Modification) When the second topic morpheme information cannot retrieve the second morpheme information including the first morpheme information from the second morpheme information, the topic retrieval unit 360 returns the first morpheme information and each answer. When the answer contents including the first morpheme information can be searched from the respective answer contents by collating the contents, the second search that acquires the second morpheme information associated with the searched answer contents It may be a means.

Specifically, the topic search unit 360 to which the topic search command signal is input from the abbreviated sentence complementation unit 350 determines the first morpheme information based on the first morpheme information included in the input topic search command signal. If the second morpheme information that matches the first morpheme information cannot be acquired from each of the second morpheme information by collating with each second morpheme information,
As shown in 2, the first morpheme information is collated with the answer sentence associated with the second morpheme information.

When the topic search unit 360 determines that the answer sentence includes a morpheme (action or a morpheme associated with the action) that constitutes the first morpheme information by this collation, The second morpheme information associated with the answer sentence is searched.

As a result, even if the topic retrieval unit 360 cannot retrieve the second morpheme information that matches the first morpheme information from the respective second morpheme information, the topic retrieval unit 360 retrieves the first morpheme information from the respective answer sentences. Since it is possible to specify the answer sentence including the morpheme (the action or the morpheme associated with the action) that constitutes one morpheme information, and search the second morpheme information associated with the specified answer sentence, the user The second morpheme information corresponding to the first morpheme information constituting the utterance content of can be appropriately searched.

As a result, the topic retrieval unit 360 can retrieve the optimum second morpheme information corresponding to the first morpheme information. Therefore, the answer sentence retrieval unit 370 causes the topic retrieval unit 360 to operate.
Based on the optimum second morpheme information searched in, it is possible to acquire appropriate answer contents for the user's utterance contents.

[Program] The contents described in the conversation control system and the conversation control method can be realized by executing a dedicated program for utilizing a predetermined programming language in a general-purpose computer such as a personal computer.

Here, as the programming language, in the present embodiment, the topic desired by the user, the emotional level of the user with respect to a certain matter, or a statement, an affirmative sentence, a question sentence,
A language for hierarchically accumulating types of repulsive sentences and the like in a database by associating them with morphemes according to their semantic content, for example, DKML (Discourse Knowle) developed by the inventors.
dge Markup Language), XML (eXtensible Markup L)
anguage), C language, etc.

That is, the conversation control device 1 stores the data stored in each of the conversation databases 500a to 500d (the second morpheme information, the fixed contents, the answer sentence, the answer type, the set group, the discourse range, the element information, and the like). ), Other parts,
It can be realized by constructing in DKML (Discourse Knowledge Markup Language) or the like and executing a program for utilizing the constructed memory information and the like.

According to the program according to the present embodiment as described above, each morpheme constituting the utterance content of the user is specified, the semantic content grasped from each specified morpheme is analyzed, and the analyzed semantic content is obtained. A conversation control device, a conversation control system, and a conversation control method, which have an effect that the optimum response content corresponding to the utterance content of the user can be output by outputting the associated pre-created response content. Can be easily realized by a general purpose computer.

Further, the developer who develops the conversation control device 1 can hierarchically construct the second morpheme information and the like for retrieving the answer contents to the utterance contents of the user in the database using the language. Therefore, the conversation control device 1 can acquire the answer content for the utterance content from the database through a hierarchical procedure based on the utterance content of the user.

That is, the conversation control device 1 determines the hierarchy of the utterance content of the user (for example, whether it is in the superordinate concept or the subordinate concept with respect to the second morpheme information accumulated in the database). It is possible to acquire appropriate answer contents from the answer contents accumulated in advance based on the determined hierarchy.

For this reason, the conversation control device 1 does not collate the first morpheme information consisting of the utterance content of the user with the "all" second morpheme information stored in advance, without any specific collation. Since the second morpheme information belonging to the first morpheme information and the first morpheme information may be collated, the second morpheme information that is similar to the first morpheme information can be acquired in a short time.

Further, the communication between the communication section 800 and the communication section 900 is performed through the communication network 1000 through the D network.
Data may be transmitted and received by a protocol such as KML. As a result, the conversation control device 1 sends the DK through the communication network 1000 when the conversation control device 1 does not have an answer content suitable for the utterance content of the user.
According to a convention such as ML, it is possible to search the answer content (the one described in DKML or the like) suitable for the utterance content of the user, and obtain the searched answer content (see FIG. 20).

The program can be recorded in a recording medium. As shown in FIG. 23, this recording medium is, for example, a hard disk 1100, a floppy (registered trademark) disk 1200, a compact disk 1300,
An IC chip 1400, a cassette tape 1500 and the like can be mentioned. According to the recording medium recording such a program, it is possible to easily store, transport, sell, etc. the program.

Second Embodiment (Basic Configuration of Information Processing System) A second embodiment of the present invention will be described with reference to the drawings. FIG. 24 shows the internal structure of the information processing system (conversation control system) according to this embodiment. As shown in the figure, the information processing system includes a conversation control device 1 according to the first embodiment.
The internal structure is almost the same as that of the (information processing device), except that the conversation control unit 300 has a ranking unit 380 (ranking unit). Except for this difference, the structure is the same as the structure of the first embodiment and the modification, and therefore the description of the structure other than the difference is omitted.

In the first embodiment, the conversation control device 1 has described the processing for acquiring the optimum answer sentence corresponding to the input information based on the input information from the user, but in the present embodiment, the conversation control unit is described. The ranked section 380 in 300
A process of ranking the emotional level of the user and the like based on the input information from the user will be described. The specific description is as follows.

The ranking unit 380 ranks the emotional level of the user based on the input information input by the user. In the present embodiment, FIG.
As shown in FIG. 3, the emotional state determination unit 381, the understanding state determination unit 382, and the conflict state determination unit 383 are included. Here, the degree of emotion means the degree of emotion that the conversation control device 1 has for the input information. This emotion level is
In this embodiment, the emotional state determination unit 381, which will be described later, makes a unique determination based on the input information.

The ranking unit 380 determines the emotional level of the user and the like based on the "discourse event" table stored in the discourse database. here,
As shown in FIG. 25, the "discourse event" table is a coherence factor (coher) indicating that the first morpheme information is a factor having relevance (cohesion) with the discourse range in the present embodiment.
e), which includes a topic change (shift) indicating that the first morpheme information is a factor that is not related to the current discourse range.

Specifically, as shown in FIG. 26, the binding factors are the binding factor (-) and the binding factor (+) in this embodiment.
Consists of. As for the cohesion factor (-), as shown in the figure, the topic search unit 360 searches for a topic title whose first morpheme information belongs to the previous discourse range and which is associated with "low emotion" belonging to the topic title. Means that Here, "low emotional level" means that the conversation control apparatus 1 has a low emotional level with respect to the topic title (for example, when the conversation control apparatus 1 has little interest in the topic title). Means that

As for the cohesion factor (+), as shown in the figure, the topic morpheme information belongs to the previous discourse range, and the topic title associated with “high emotion” belonging to the discourse range is the topic search unit 360. It means that it was searched by. here,
“High emotion level” means that the conversation control device 1 sets a high emotion level for the topic title (for example, when the conversation control device 1 is interested in the topic title). To do.

As shown in FIG. 26, these binding factors (-) and (+) are determined based on the result of the "conditional" parsing process by the paring judgment unit 330 and the result of the abbreviated sentence complementing process by the abbreviated sentence complementing unit 350. , The ranking section 380 determines.

Further, the topic change is as shown in FIG.
It consists of topic change (-) and topic change (+). The topic change (-) means that the current topic title retrieved by the topic retrieval unit 360 is later changed to another topic title associated with "low emotional level", as shown in FIG. .

The topic change (+) means that the current topic title retrieved by the topic retrieval unit 360 is later changed to another topic title associated with "high emotion level", as shown in FIG. Means Change these topics (-)
As shown in FIG. 26, (+) indicates the discourse range determination unit 340.
Ranking unit 380 based on the search result of the discourse range by
It is decided by.

[0245] The "discourse range event" table is
In addition to the above, an interruption factor indicating that the first morpheme information is a factor that interrupts the current topic (interruput), an esoteric factor indicating that the first morpheme information is more esoteric information than the second morpheme information ( harass), an opposition factor (oppos) indicating that the first morpheme information causes a conflict with the second morpheme information.
e) etc.

As shown in FIG. 24, the interruption factors are the bird-peel process by the bird-peel determination unit 330 and the reflex determination unit 32.
It is determined by the ranking unit 380 based on the reflective processing by 0. The difficulty factor is based on the search result of the topic title (second morpheme information) by the topic search unit 360.
It is determined by the ranking unit 380. The confrontation factor is determined by the ranking unit 380 based on the determination of the utterance type by the utterance type determination unit 440.

The emotional state determination unit 381 is the topic search unit 36.
It is a ranking unit that ranks the second morpheme information including the first morpheme information based on the search result of 0 according to the frequency of search.

The emotional state determination unit 381 is also a ranking means for ranking a low rank when the frequency of the search is low and a high rank when the frequency of the search is high. The size of this rank can be expressed as the degree of emotions the user has, the degree of understanding of the input information, and the degree of conflict felt with the user.

In the present embodiment, the emotional level determined by the emotional state determination section 381 can be ranked into, for example, six levels as shown in FIG. As for this emotion level, the degree of emotion that the user has is high (direction to improve).
The higher the value, the more the numerical value shown in FIG.

Therefore, it means that the transition of the emotion level from e (0) to e (3) increases the emotion level of the user. On the other hand, the transition of the emotion level from e (0) to e (-2) means that the emotion level held by the user decreases. Out of 6
In this embodiment, the reference emotion level is e (0).

In the present embodiment, the ranking of the emotion level is performed by using the negative emotion factor, the positive emotion factor, and the topic change (+) (-). In the present embodiment, this negative emotion factor is assumed to be the interruption factor, the difficult factor, the conflict factor, the cohesion factor (-), and the topic change (-) described above. Positive emotion factors consist of cohesion factors (+) and topic changes (+).

[0252] In the figure, the degree of emotion changes by two or more stages due to topic change (-) (+). This means that the emotion level is "very low" or "emotional" from the current topic title. When the topic title associated with the degree of "very high" is selected, the emotion level is changed in two or more stages.

Specifically, when the topic search unit 360 does not search for the second morpheme information including the first morpheme information, the emotional state determination unit 381 ranks the emotional level of the user low. To do.

That is, the fact that the topic search unit 360 does not search the second morpheme information including the first morpheme information means that the first morpheme information constituting the input information input by the user is stored in advance. More difficult than dimorphic information (ha
Since it can be pseudo-asserted that it is rass), the emotional state determination unit 381 determines that the input information (first morpheme information) input by the user is an emotional negative factor (difficulty factor), Set the emotional level of the user to be lower.

On the other hand, when the topic search unit 360 searches for the second morpheme information including the first morpheme information, the emotional state determination unit 381 ranks the emotional level of the user in a high rank. .

That is, the fact that the topic search unit 360 has searched for the second morpheme information including the first morpheme information means that the first morpheme information constituting the input information input by the user is stored in advance. Since it can be pseudo-asserted that it is easier than the second morpheme information, the emotional state determination unit 381 determines that the user can understand the input information input by the user, and Set the emotional level to be high.

The emotional state determination unit 381 is also a ranking unit for ranking based on the determination result by the discourse range determination unit 340 (relevance determination unit). In the present embodiment, the discourse range determination unit 340 matches the first discourse range indicating the retrieved discourse range with the second discourse range indicating the retrieved discourse range, and the second discourse range is the first discourse. It is a relevance determination means for determining whether or not the range has relevance.

Specifically, when the discourse range determination unit 340 determines that the second discourse range is not related to the first discourse range, the emotional state determination unit 381 embraces the user, for example. Rank the emotional level low.

That is, the fact that the second topic range is not related to the first topic range by the discourse range determination unit 340 means that the current discourse range including the first morpheme information (second discourse range). Is different from the previous discourse range (the first discourse range) (the context related topics have no cohesiveness; this is also called "topic change"), so it can be pseudo-asserted. When the state determination unit 381 includes the first morpheme information belonging to the second discourse range in the topic title (second morpheme information) associated with “low emotional level”,
The first morpheme information is a negative factor for emotions (topic change (-))
Then, the emotional level of the user is set to be lower (see FIGS. 26 and 27).

As a result, the topic change (-) is such that the current discourse range is changed to another discourse range, and the first morpheme information belonging to the changed discourse range is not interesting to the conversation control device 1. Means there is.

In this case, if the emotional state determining unit 381 includes the first morpheme information belonging to the second discourse range in the topic title (second morpheme information) associated with “high emotion level”, It is also possible to determine that the morpheme information is an emotional plus factor (topic change (+)) and set the emotional level to the user to be higher.

As a result, the topic change (+) is an interesting content for the conversation control device 1 because the current discourse range is changed to another discourse range and the first morpheme information belonging to the changed discourse range is interesting. Means that.

On the other hand, when the discourse range determination section 340 determines that the second discourse range is related to the first discourse range, the emotional state determination section 381 determines, for example, the emotional level of the user. Rank high.

That is, the discourse range determination unit 340 determines that the second topic range is related to the first topic range, which means that the current discourse range including the first morpheme information (second discourse range) is Since it can be pseudo-asserted that it is substantially the same as the previous discourse range (first discourse range) (the related topics have cohesiveness), the emotional state determination unit 381 determines that When the first morpheme information belonging to the two discourse ranges is included in the topic title (second morpheme information) associated with “high emotion level”, the first morpheme information is an emotional plus factor (cohesion factor (+)). It is determined that there is, and the emotional level that the user has is set to be higher (see FIGS. 26 and 27).

As a result, the cohesion factor (+) is such that the current discourse range is substantially the same as the previous discourse range, and the first morpheme information belonging to the current discourse range is interesting to the conversation control device 1. Means that.

In this case, if the emotional state determination section 381 includes the first morpheme information belonging to the second discourse range in the topic title (second morpheme information) associated with "low emotional level", It is also possible to determine that the morpheme information is a negative factor for emotion (cohesion factor (-)) and set the emotional level to the user to be lower.

As a result, the cohesion factor (-) is such that the current discourse range is substantially the same as the previous discourse range, but the first morpheme information belonging to the current discourse range is the conversation control device 1.
It means that the content is not interesting to me.

The emotional state determination section 381 is also a ranking means for ranking the morphemes forming the discourse range in the abbreviated sentence complementing section 350 on the basis of the result added to the first morpheme information.

More specifically, the abbreviated sentence complementing unit 350 selects from among the attributes (the subject case consisting of the nominative case, the target case consisting of the objective case, etc.) constituting the first morpheme information extracted by the sentence structure analyzing section 430. , Search for attributes that do not include morphemes. The abbreviated sentence complementing unit 350 adds the morphemes forming the discourse range searched by the discourse range determining unit 340 to the attribute based on the searched attribute.

The emotional state determining unit 381 is the abbreviated sentence complementing unit 3
When the morphemes composing the discourse range at 50 are added to the first morpheme information, the emotional level of the user is ranked high.

That is, in the abbreviated sentence complementing unit 350, the input information consisting of the first morpheme information is the abbreviated sentence (when the discourse range is added to the first morpheme information, the first morpheme information before this morpheme is added It means that the input information consisting of is abbreviations) means that the user can input the input information that belongs to the current discourse range on the assumption that the user belongs to the current discourse range. Since it is considered that the input information is input at this stage, it is highly likely that the input information input at this stage is an abbreviated sentence in which the morpheme consisting of the current discourse range is omitted (for details, refer to the first embodiment. (See the section "Abbreviated sentence complementing section 350").

Therefore, when the abbreviated sentence complementing unit 350 determines that the first morpheme information is an abbreviated sentence, the emotional state determination unit 381 has the current discourse range substantially the same as the previous discourse range. And the first morpheme information is determined to be a cohesive factor that is related to the previous discourse range. In this case, the emotional state determination unit 381 sets the emotional level of the user to be higher if the binding factor is the binding factor (+), and sets the binding factor to be the binding factor (-), It is possible to set the emotional level of the user to be low.

Further, the emotional state determination unit 381 determines, based on the search result by the reflexive determination unit 320 or the parody return determination unit 330, the standard content including the first morpheme information or the frequency of retrieval of the parody return element. It is also a means of ranking. The reflexive determination unit 320 is a fixed-form acquisition unit that collates the extracted first morpheme information with each standard content and retrieves reflexive element information including the first morpheme information from each standard content. Specifically, when the reflexive determination unit 320 retrieves a standard content that matches the first morpheme information from each standard content, the emotional state determination unit 381.
Ranks a user's emotional level to a low rank.

That is, the fact that the reflexive determination unit 320 has searched for the fixed contents that match the first morpheme information is an element (interruption factor; interrupt) for the first morpheme information to interrupt the current topic. Therefore, the emotional state determination unit 381 determines that the first morpheme information is an emotional negative factor (interruption factor), and sets the emotional level held by the user to a lower emotional level. (Fig. 26,
See FIG. 27). For example, if the user inputs "Good morning" (standard content) that has nothing to do with the topic during the conversation, "Good morning" becomes the interruption factor.

[0275] Further, the parrot judgment unit 330 determines that the present first morpheme information extracted by the morpheme extraction unit 410 is the past answer content extracted by the morpheme extraction unit 410 (this past first morpheme information (parousel element ) Is stored in the parrot element database 802).

When the parody judgment unit 330 judges that the current first morpheme information is included in the past reply contents, the emotional state judging unit 381 determines that the user has returned the parody to the past reply contents (use The person is listening again to the answer contents), and it is possible to artificially conclude that the first morpheme information is an interruption factor for interrupting the current topic.

In this case, since the current first morpheme information is an emotional negative factor (interruption factor), the emotional state determining unit 381 sets the emotional level to the user to be lower. (See FIGS. 26 and 27).

Furthermore, the parrot judging section 330 determines that the present morpheme information extracted by the morpheme extracting section 410 is the past first morpheme information (the past first morpheme information is stored in the parrot element database 802). When it is determined that the first first morpheme information is included in the past first morpheme information,
It can be determined that the user repeatedly inputs the same input information as the past input information regardless of the current topic.

In this case, the emotional state determination unit 381 determines that the input information repeatedly input is the interruption factor and sets the emotional level to the user to be lower (details will be described below).
(Refer to the "parsing process" in the first embodiment).

If the parody judgment unit 330 or the reflexive judgment unit 320 cannot retrieve the fixed contents matching the first morpheme information from the fixed contents, the emotional state judging unit 3
81 may rank the emotional level that the user has in a low rank.

Furthermore, when the input information specified by the utterance type determination unit 440 is a repulsive element such as a repulsive sentence, the emotional state determination unit 381 ranks the emotional level of the user to be low. It is also something to do.

Here, the repulsion element means an element for the user to repel the reply content output from the conversation control device 1. In the present embodiment, for example,
It consists of a repulsive sentence indicating that the input information of the user is a sentence that is repulsive to the response content, and a negative sentence that indicates that the input information of the user is a negative sentence to the response content. is there.

That is, the fact that the input type of the input information input by the user by the utterance type determination unit 440 is specified to consist of repulsive elements means that the user and the conversation control device 1 are in opposition. ), The emotional state determination unit 381 determines that the first morpheme information is an emotional negative factor (opposite factor), and determines the emotional level to the user. The lower one is set (see FIGS. 26 and 27).

The understanding state determination unit 382 is the topic search unit 36.
When the second morpheme information including the first morpheme information is not retrieved from each second morpheme information with 0, it is determined that the input information input by the user is harass (difficulty factor), It is a ranking means that ranks the degree of comprehension of input information to a low rank.

That is, the fact that the second morpheme information including the first morpheme information is not retrieved from the respective second morpheme information by the topic retrieval unit 360 means that the first morpheme information is more difficult than the second morpheme information. Since it is possible to make a pseudo-assertion, the understanding state determination unit 382 determines that the first morpheme information is a difficult factor and sets the degree of comprehension of the input information to the lower one.

When the topic retrieval unit 360 retrieves the second morpheme information including the first morpheme information from the second morpheme information, the understanding state determination unit 382 inputs the input from the user. It may be determined that the information is easy, and the degree of understanding of the input information may be ranked high. Further, when the first morpheme information is a factor that changes the topic to a cohesion factor, the understanding state determination unit 382 may rank the degree of comprehension of the input information to a high rank.

Here, the degree of comprehension means the degree of comprehension of the input information inputted by the user. As shown in FIG. 28, the degree of understanding can be ranked in four levels in this embodiment, for example.

The larger the numerical value (direction from r (-2) to r (1)), the more the understanding of the input information is deepened (the direction in which the understanding is clearly extended). . On the other hand, the smaller the numerical value (from r (1) to r
(-2) means that the input information tends to be less understood (direction in which the understanding is unclear).

Specifically, as shown in the same figure, when the understanding state judging unit 382 judges that the first morpheme information is a difficult factor with r (0) as a reference, the understanding level is lowered. When it is determined that the first morpheme information is a factor that changes the topic to a cohesion factor, the understanding level is transitioned to a higher degree.

If the understanding state determination unit 382 determines that the first morpheme information is the interruption factor or the conflicting factor, the first morpheme information does not contribute to the understanding of the input information. The rank of is maintained as it is (see the figure). Further, the understanding state determination unit 382 transitions the understanding level to a higher rank when the emotion level shifts in the positive direction.

Since the difficult factor, the cohesive factor, the topic change, the interruption factor, and the conflicting factor are the same as the contents described in the section of the emotional state determining section 381, the description thereof will be omitted.

If the input information specified by the utterance type determination unit 440 is a repulsive element (oppose; also referred to as an opposition factor) such as a repulsive sentence, the conflict state determination unit 383 determines the degree of conflict with the user. Is to be ranked high. In addition, the conflict state determination unit 383 is the utterance type determination unit 4
When the input information specified by 40 is not a repulsive element such as a repulsive sentence, the degree of confrontation with the user is also ranked low.

Here, the degree of conflict means the degree of conflict the conversation control device 1 has with the user.
As shown in FIG. 29, this degree of conflict is
For example, it can be ranked in five stages. The higher the value, the lower (weaker) the degree of conflict with the user is. On the other hand, the smaller the numerical value, the higher (stronger) the degree of conflict with the user is.

Specifically, as shown in the same figure, the confrontation state determination unit 383 determines that the degree of confrontation is lower when the first morpheme information is the confrontation factor based on O (0). And make a transition (with rank). In addition, the conflict state determination unit 383
If it is determined that the first morpheme information is not a confrontation factor but a discourse change factor (not a repulsion factor) to a cohesion factor, the first morpheme information transitions to a higher confrontation degree.

Further, when the emotional degree with respect to the first morpheme information is set to a higher direction by the emotional state determining section 381, the conflicting state determining section 383 sets the conflicting degree to a lower one (weaker the degree of conflicting). can do. In addition, when the emotional degree with respect to the first morpheme information is set to a lower direction by the emotional state determination unit 381, the conflict state determination unit 383,
It is also possible to set the degree of conflict to be higher (stronger degree of conflict).

If the first morpheme information is an interruption factor or an esoteric factor, the conflict state determination unit 383 determines that the first morpheme information is not repulsive to the content of the answer, and therefore the degree of conflict is determined. Keep it as it is (see figure).

The emotional state determination unit 381, the understanding state determination unit 382, or the conflict state determination unit 383 outputs the determined emotion level, understanding level, and conflict level to the output unit 600, and the output unit receives the input emotion. Display the degree, comprehension, and conflict.

(Information Processing Method Using Information Processing System) The information processing method by the information processing system having the above configuration can be implemented by the following procedure. Figure 3
0 is a flow chart showing the procedure of the ranking method according to the present embodiment.

As shown in the figure, first, the input unit 100
Performs a step of acquiring the input information input by the user (S201). Then, the morpheme extraction unit 410
Based on the input information acquired by the input unit 100, a step of extracting each morpheme forming the input information is performed (S2).
02).

After that, the sentence structure analysis unit 430 performs a step of collecting each morpheme into a phrase form based on each morpheme extracted by the morpheme extraction unit 410 (S203). In the present embodiment, each morpheme belonging to one bunsetsu format is the first morpheme information.

Next, the reflexive determination unit 320 performs a reflexive processing step based on the first morpheme information specified by the sentence structure analysis unit 430 (S204, S20).
5). Then, the parrot determining process 330 performs a parcel returning process or a conditional paring returning process based on the first morpheme information identified by the sentence structure analyzing unit 430 (S206).

After that, the discourse range determination unit 340 performs a step of collating the first morpheme information with each discourse range and searching the discourse range for the discourse range including the first morpheme information (S207). Further, when the input information including the first morpheme information is an abbreviation, the abbreviated sentence complementing unit 350 performs a step of adding a morpheme including a discourse range to the first morpheme information (S208).

Then, the topic retrieval unit 360 compares the first morpheme information and the respective second morpheme information with each other based on the identified first morpheme information or the first morpheme information to which the morpheme is added. A step of searching the morpheme information for the second morpheme information including the first morpheme information is performed (S20).
9). Since the specific processing of S201 to S208 is the same as the content of the "conversation control method" described in the first embodiment, the details of these processings will be omitted.

Next, the emotional state determination unit 381 determines whether to use the emotional state determination unit 320 based on the search results by the reflexive determination unit 320, the parody judgment unit 330, the discourse range determination unit 340, the abbreviated sentence completion unit 350, or the topic search unit 360. A step of ranking the emotional level to be held is performed (S210). Specifically, when the topic search unit 360 does not search for the second morpheme information including the first morpheme information, the emotional state determination unit 381 ranks the emotional level of the user to be low.

That is, the fact that the topic search unit 360 does not search the second morpheme information including the first morpheme information means that the first morpheme information constituting the input information input by the user is stored in advance. More difficult than dimorphic information (ha
Since it can be pseudo-asserted that it is rass), the emotional state determination unit 381 determines that the input information (first morpheme information) input by the user is an emotional negative factor (difficulty factor), Set the emotional level of the user to be lower.

On the other hand, when the topic search unit 360 searches for the second morpheme information including the first morpheme information, the emotional state determination unit 381 ranks the emotional level of the user in a high rank. .

That is, the fact that the topic search unit 360 has searched for the second morpheme information including the first morpheme information means that the first morpheme information constituting the input information input by the user is stored in advance. Since it can be pseudo-asserted that it is easier than the second morpheme information, the emotional state determination unit 381 determines that the user can understand the input information input by the user, and Set the emotional level to be high.

The emotional state determination unit 381 can also perform a step of ranking the emotional level of the user based on the determination result by the discourse range determination unit 340. In the present embodiment, the discourse range determination unit 340 matches the first discourse range indicating the retrieved discourse range with the second discourse range indicating the retrieved discourse range, and the second discourse range is the first discourse. It is determined whether or not there is a relationship with the range.

Specifically, when the discourse range determination unit 340 determines that the second discourse range is not related to the first discourse range, the emotional state determination unit 381 has emotions to the user. Rank the degree low.

That is, the fact that the second topic range is not related to the first topic range by the discourse range determination unit 340 means that the current discourse range including the first morpheme information (second discourse range). Is different from the previous discourse range (the first discourse range) (the context related topics have no cohesiveness; this is also called "topic change"), so it can be pseudo-asserted. When the state determination unit 381 includes the first morpheme information belonging to the second discourse range in the topic title (second morpheme information) associated with “low emotional level”,
The first morpheme information is a negative factor for emotions (topic change (-))
Then, the emotional level of the user is set to be lower (see FIGS. 26 and 27).

As a result, the topic change (-) is such that the current discourse range is changed to another discourse range, and the first morpheme information belonging to the changed discourse range is not interesting to the conversation control device 1. Means there is.

In this case, if the emotional state determining unit 381 includes the first morpheme information belonging to the second discourse range in the topic title (second morpheme information) associated with “high emotion level”, It is also possible to determine that the morpheme information is an emotional plus factor (topic change (+)) and set the emotional level to the user to be higher.

As a result, the topic change (+) changes the current discourse range to another discourse range, and the first morpheme information belonging to the changed discourse range is interesting to the conversation control device 1. Means that.

On the other hand, when the discourse range determination unit 340 determines that the second discourse range is related to the first discourse range, the emotional state determination unit 381 has a high emotional level to the user. Rank to rank.

That is, the fact that the second topic range is related to the first topic range by the discourse range determination unit 340 means that the current discourse range (second discourse range) including the first morpheme information is Since it can be pseudo-asserted that it is substantially the same as the previous discourse range (first discourse range) (the related topics have cohesiveness), the emotional state determination unit 381 determines that When the first morpheme information belonging to the two discourse ranges is included in the topic title (second morpheme information) associated with “high emotion level”, the first morpheme information is an emotional plus factor (cohesion factor (+)). It is determined that there is, and the emotional level that the user has is set to be higher (see FIGS. 26 and 27).

Accordingly, the cohesion factor (+) is such that the current discourse range is substantially the same as the previous discourse range, and the first morpheme information belonging to the current discourse range is an interesting content for the conversation control device 1. Means that.

In this case, if the emotional state determining unit 381 includes the first morpheme information belonging to the second discourse range in the topic title (second morpheme information) associated with "low emotional level", It is also possible to determine that the morpheme information is a negative factor for emotion (cohesion factor (-)) and set the emotional level to the user to be lower.

As a result, the cohesion factor (-) is such that the current discourse range is substantially the same as the previous discourse range, but the first morpheme information belonging to the current discourse range is the conversation control device 1.
It means that the content is not interesting to me.

When the abbreviated sentence complementing unit 350 adds the morphemes forming the discourse range to the first morpheme information, the emotional state determining unit 381 ranks the emotional level of the user high. The steps of attaching can also be performed.

Specifically, the abbreviated sentence complementing unit 350 selects from among the attributes (the subject case consisting of the nominative case, the target case consisting of the objective case, etc.) that constitute the first morpheme information extracted by the sentence structure analyzing section 430. , Search for attributes that do not include morphemes. The abbreviated sentence complementing unit 350 adds the morphemes forming the discourse range searched by the discourse range determining unit 340 to the attribute based on the searched attribute. When the morphemes forming the discourse range are added to the first morpheme information by the abbreviated sentence complementing unit 350, the emotional state determining unit 381 ranks the emotional level of the user in a high rank.

That is, the input information consisting of the first morpheme information in the abbreviated sentence complementing unit 350 is the abbreviated sentence (when the discourse range is added to the first morpheme information, the first morpheme information before this morpheme is added It means that the input information consisting of is abbreviations) means that the user can input the input information that belongs to the current discourse range on the assumption that the user belongs to the current discourse range. Since it is considered that the input information is input at this stage, it is highly likely that the input information input at this stage is an abbreviated sentence in which the morpheme consisting of the current discourse range is omitted (for details, refer to the first embodiment. (See the section "Abbreviated sentence complementing section 350").

Therefore, when the abbreviated sentence complementation unit 350 determines that the first morpheme information is an abbreviated sentence, the emotional state determination unit 381 makes the current discourse range substantially the same as the previous discourse range. And the first morpheme information is determined to be a cohesive factor that is related to the previous discourse range. In this case, the emotional state determination unit 381 sets the emotional level of the user to be higher if the binding factor is the binding factor (+), and sets the binding factor to be the binding factor (-), It is possible to set the emotional level of the user to be low.

Furthermore, the emotional state determination unit 381 can also perform the step of ranking the emotional level of the user, based on the search result by the reflexive determination unit 320 or the trick-back determination unit 330. This reflective determination unit 320
Is a fixed-form acquisition unit that collates the extracted first morpheme information with each standard content and retrieves the reflective element information including the first morpheme information from each standard content. Specifically, when the reflexive determination unit 320 retrieves a standard content that matches the first morpheme information from each standard content, the emotional state determination unit 381 ranks the emotional level of the user low. Rank.

That is, the fact that the reflexive determination unit 320 has searched for the fixed contents that match the first morpheme information is an element (interruption factor; interrupt) for the first morpheme information to interrupt the current topic. Therefore, the emotional state determination unit 381 determines that the first morpheme information is an emotional negative factor (interruption factor), and sets the emotional level held by the user to a lower emotional level. (Fig. 26,
See FIG. 27). For example, if the user inputs "Good morning" (standard content) that has nothing to do with the topic during the conversation, "Good morning" becomes the interruption factor.

Further, the parody judgment unit 330 determines that the current first morpheme information extracted by the morpheme extraction unit 410 is the past answer content extracted by the morpheme extraction unit 410 (this past first morpheme information is parody Element database 802
(Stored in) is included.

When the parrot judging section 330 determines that the current first morpheme information is included in the past answer content, the emotional state determining section 381 determines that the current first morpheme information is included in the past answer content. Therefore, the user is arguing back to the past reply contents (that the user is listening again to the reply contents), and the first morpheme information is the interruption factor for interrupting the current topic. Can be artificially determined.

In this case, since the current first morpheme information is an emotional negative factor (interruption factor), the emotional state determination unit 381 sets the emotional level held by the user to the lower emotional level. (See FIGS. 26 and 27).

Further, the parrot judging section 330 collates the present morpheme information extracted by the morpheme extraction section 410 with the past first morpheme information, and the present first morpheme information is included in the past first morpheme information. If it is determined that the current first morpheme information is included in the past first morpheme information, the emotional state determination unit 381 has no relation to the current topic.
It can be determined that the user simply repeatedly inputs the same input information as the past input information. In this case, since the input information repeatedly input is the interruption factor, the emotional state determination unit 381 sets the emotional level to the user to be lower.

If the reflexive determination unit 320 cannot retrieve a fixed form content that matches the first morpheme information from the fixed form contents, the emotional state determination unit 381 has a high emotional level to the user. You may rank in a rank. When the parody judgment unit 330 cannot retrieve past first morpheme information or past answer contents that match the current first morpheme information, the emotional state determination unit 381 ranks the emotion level of the user to be high. May be ranked.

Furthermore, when the input information specified by the utterance type determination unit 440 is a repulsive element such as a repulsive sentence, the emotional state determination unit 381 ranks the emotional level of the user low. The steps of attaching can also be performed.

That is, the fact that the input type of the input information input by the user by the utterance type determination unit 440 is specified to consist of the repulsive element means that the user and the conversation control device 1 are in opposition. ), The emotional state determination unit 381 determines that the first morpheme information is an emotional negative factor (opposite factor), and determines the emotional level to the user. The lower one is set (see FIGS. 26 and 27).

Next, when the understanding state determination unit 382 does not retrieve the second morpheme information including the first morpheme information from the respective second morpheme information by the topic retrieval unit 360, the input information input by the user Is difficult (harass) (difficult factor)
Then, a step of ranking the degree of understanding of the input information to a low rank is performed (S211).

More specifically, the fact that the topic search unit 360 does not search the second morpheme information including the first morpheme information from the respective second morpheme information means that the first morpheme information is more difficult than the second morpheme information. Therefore, the understanding state determination unit 382 determines that the first morpheme information is a difficult factor and sets the degree of comprehension to the input information to be lower.

When the topic retrieval unit 360 retrieves the second morpheme information including the first morpheme information from the second morpheme information, the understanding state determination unit 382 inputs the input from the user. It may be determined that the information is easy, and the degree of understanding of the input information may be ranked high. Further, when the first morpheme information is a factor that changes the topic to a cohesion factor, the understanding state determination unit 382 may rank the degree of comprehension of the input information to a high rank.

Then, if the input information specified by the utterance type determination unit 440 is a repulsive element (oppose; also referred to as an opposition factor) such as a repulsive sentence,
A step of ranking the degree of confrontation with the user into a high rank is performed (S212). In addition, the conflict state determination unit 383
When the input information specified by the utterance type determination unit 440 is not a repulsive element such as a repulsive sentence, the step of ranking the degree of confrontation with the user to a low rank is performed.

After that, the emotional state determination unit 381, the understanding state determination unit 382, or the conflict state determination unit 383 outputs the determined emotion level, understanding level, and conflict level to the output unit 600, and the output unit receives the input. A step of displaying the emotional level, understanding level, and conflict level is performed (S213).

(Operations and Effects of Information Processing System and Information Processing Method) According to the invention of the present embodiment, the reflexive determination unit 320, the parody return determination unit 330, or the topic search unit 360 is the first morpheme information. And each second morpheme information are collated, and the second morpheme information including the first morpheme information is searched from each second morpheme information, and the emotional state determination unit 3
81 can be ranked as the degree of emotion to the user according to the frequency with which the second morpheme information including the first morpheme information is searched from each second morpheme information. Therefore, if the emotional state determination unit 381 can output (for example, a screen, a voice, etc.) the ranked size as the degree of emotion held by the user, the conversation control device 1 uses the simulated state. It can be used to specify the emotional level of a person.

Further, the developer who develops the information processing system can easily rank the emotion level based on the search history performed between the first morpheme information and each second morpheme information. Therefore, it is not necessary to develop a complicated algorithm or a neural network for causing the information processing system to calculate the degree of emotion held by the user, and as a result, the development time for developing this system can be shortened. be able to.

Further, the discourse range determination unit 340 relates the first discourse range associated with the first morpheme information searched first and the second discourse range related with the first morpheme information retrieved later. The emotional state determining unit 38
Since 1 ranks the emotional level of the user based on the result determined by the discourse range determination unit 340, the emotional state determination unit 381 compares the first morpheme information with each second morpheme information. It is possible to rank the emotional level of the user more appropriately than to rank the emotional level of the user based on the search result.

For example, if the second discourse range has no relevance to the first discourse range, the emotional state determination unit 381 determines that the current input information (the one input by the user) is displayed before the second discourse range. Since it can be judged that the input information is completely different from the input information entered, the user can artificially conclude that the input is inconsistent for a certain topic, and It is possible to set a low emotional level for a person (in a bad direction).

On the other hand, if the second discourse range is related to the first discourse range, the emotional state determination unit 381 determines that the current input information (those input by the user) is displayed before. Since it can be judged that the input information is related to the input information, the user can artificially conclude that the input information is consistent with respect to a certain topic. It is possible to set a high emotional level for (good direction).

Furthermore, when the abbreviated sentence complementing unit 350 adds morphemes in the discourse range to each attribute forming the first morpheme information, the emotional state determining unit 381 omits the input information consisting of the first morpheme information. It can be determined that the sentence is a sentence, and the user can determine that the input information is input on the premise of the discourse range previously searched.

Therefore, if the first morpheme information consisting of the input information is an abbreviation,
Since it can be judged that the input information is entered based on the discourse range searched previously, the user can artificially conclude that the input is consistent for a certain topic. Therefore, it is possible to set a high emotion level for the user (a good direction).

Furthermore, the reflexive determination unit 320 collates the first morpheme information with each standard content, retrieves the standard content including the first morpheme information from each standard content, and the emotional state determination unit 381. However, since the emotional level of the user is ranked based on the search result, the emotional state determination unit 38
1 is, for example, when the standard content including the first morpheme information is searched, the user can artificially determine that the input information for interrupting a certain topic is input, The emotional level of the user can be ranked lower, and as a result, the emotional level of the user can be more appropriately ranked.

On the other hand, when the reflexive determination unit 320 cannot retrieve the fixed contents including the first morpheme information, the emotional state determination unit 381 inputs the input for the user to interrupt a certain topic. Since it is possible to artificially conclude that the user has answered the current topic seriously without inputting information, it is possible to rank the emotion level of the user in a high rank. .

Further, the utterance type determination unit 440 identifies the input type indicating the type of input information, and when the identified input type is a repulsive element such as a repulsive sentence, the emotional state determination unit 381 uses It is possible to rank the emotional level that the user has in a lower rank, and to more appropriately rank the emotional level that the user has.

Furthermore, if the topic search unit 360 does not search the second morpheme information including the first morpheme information, the understanding state determination unit 382 stores the second morpheme information related to the first morpheme information in advance. Since it means that the input information composed of the first morpheme information is more difficult to understand than the sentence composed of the second morpheme information, it can be pseudo-asserted.

For this reason, since the understanding state determination unit 382 cannot understand the input information composed of the first morpheme information, it is pseudo that the user inputs that the meaning is unknown to a certain topic. Therefore, it is possible to rank the degree of comprehension with respect to input information to a low rank.

When the understanding state determination unit 382 can retrieve the second morpheme information related to the first morpheme information by the topic retrieval unit 360, the understanding state determination unit 382.
Can pseudo-assert that the user is inputting something that makes sense for a certain topic, and can rank the degree of comprehension of the input information to a high rank.

Further, the developer who develops the conversation control device 1 can hierarchically construct the second morpheme information and the like for searching the answer contents to the input information of the user using a language such as DKML. Therefore, the conversation control device 1 can search the database for the second morpheme information and the like related to the first morpheme information based on the first morpheme information corresponding to the input information of the user through a hierarchical procedure. it can.

That is, the reflex determination unit 320, the parody judgment unit 330, the discourse range determination unit 340, or the topic search unit 360.
Identifies the hierarchy of the first morpheme information corresponding to the input information (for example, whether it is in a superordinate concept or a subordinate concept with respect to the second morpheme information stored in the database), Based on each of the second morpheme information stored in advance, it is possible to search for appropriate second morpheme information.

Therefore, the reflex determination unit 320, the parody judgment unit 330, the discourse range determination unit 340, or the topic search unit 3
60 is the first morpheme information consisting of the input information of the user,
Since it is sufficient to collate each "specific" second morpheme information and the first morpheme information belonging to a certain specific hierarchy without collating each "all" second morpheme information stored in advance, The second morpheme information that is similar to the one morpheme information can be searched for in a short time, and the result can be ranked in a short time, for example, the emotional level that the user has based on the search result.

Further, when the parody judging section 330 collates the present first morpheme information with the past answer contents and decides that the current first morpheme information is included in the past answer contents, the emotional state is judged. The determination unit 381 can artificially determine that the user is pardoning the previous reply content (that the user is listening again to the reply content).

In this case, the emotional state determination section 381 simulates that the user has input the input information for interrupting a certain topic, because the user is performing a trick reply to the past reply contents. The emotional level of the user can be ranked lower, and as a result, the emotional level of the user can be more appropriately ranked.

Finally, the parrot judging section 330 collates the present first morpheme information with the past first morpheme information, and when the present first morpheme information is included in the past first morpheme information, The emotional state determination unit 381 can artificially determine that the input information input by the user in the past is re-input regardless of the reply content from the conversation control device 1.

In this case, the emotional state determination section 381 has nothing to do with the content of the reply from the conversation control device 1, and the user simply repeatedly inputs the same input information as the previous input information. Therefore, the emotional level of the user can be ranked lower, and as a result, the emotional level of the user can be more appropriately ranked.

[0357]

As described above, according to the present invention,
The conversation control device (information processing device) searches for pre-created answer contents and the like associated with the meaning contents grasped from the input information, based on the input information such as the utterance contents inputted by the user, Ranking can be performed according to the frequency of this search.

[Brief description of drawings]

FIG. 1 is a block diagram showing a schematic configuration of a conversation control device according to a first embodiment.

FIG. 2 is a block diagram showing an internal structure of a conversation control unit and a sentence analysis unit in the first embodiment.

FIG. 3 is a diagram showing the contents of each morpheme extracted by a morpheme extraction unit in the first embodiment.

FIG. 4 is a diagram showing the content of each phrase extracted by a phrase analysis unit in the first embodiment.

FIG. 5 is a diagram showing the content of “case” specified by the sentence structure analysis unit in the first embodiment.

FIG. 6 is a diagram showing “type of utterance sentence” specified by the utterance type determination unit in the first embodiment.

FIG. 7 is a diagram showing the contents of each dictionary stored in the utterance type database in the first embodiment.

FIG. 8 is a diagram showing contents of a hierarchical structure constructed inside a conversation database in the first embodiment.

FIG. 9 is a diagram showing a detailed relationship of a hierarchical structure constructed inside the conversation database in the first embodiment.

FIG. 10 is a diagram showing the contents of a “topic title” constructed inside the conversation database in the first embodiment.

FIG. 11 is a diagram showing the content of “response sentence type” associated with “topic title” constructed inside the conversation database in the first embodiment.

FIG. 12 is a “topic title” belonging to a “discourse range” constructed inside the conversation database according to the first embodiment.
It is a figure which shows the content of and "answer sentence."

FIG. 13 is a diagram showing the content of reflective element information stored in a reflective element database in the first embodiment.

FIG. 14 is a diagram showing the contents of a hawk and a turtle's morpheme stored in the bird and turtle element database in the first embodiment.

FIG. 15 is a flowchart showing a procedure of a conversation control method according to the first embodiment.

FIG. 16 is a diagram showing utterance contents organized by a morpheme extraction unit in the first modification.

FIG. 17 is a diagram showing an internal configuration of a topic search unit in a second modification.

FIG. 18 is a case configuration in which the ratio calculation unit in the second modification example
It is a figure which shows a mode that each morpheme which belongs to and each "topic title" are collated for every "topic title."

FIG. 19 is a diagram showing that the ratio calculation unit in the second modified example is “each component”.
It is a figure which shows a mode that each morpheme which belongs to "topic title" is collated for every "case".

FIG. 20 is a diagram showing a schematic configuration of a conversation control system in a third modification.

FIG. 21 is a diagram showing an internal configuration of a topic search unit in a sixth modification.

FIG. 22 is a diagram showing how the topic search unit in the sixth modified example matches the first morpheme information with the second morpheme information or the answer sentence.

FIG. 23 is a diagram showing a recording medium that stores a program according to the present embodiment.

FIG. 24 is a block diagram showing internal structures of a conversation control unit and a sentence analysis unit in the second embodiment.

FIG. 25 is a diagram showing the content of a “discourse event table” stored in a discourse event database in the second embodiment.

FIG. 26 is a diagram showing a relationship between “topic change” and “cohesion factor” in the second embodiment.

FIG. 27 is a diagram showing ranks of emotion levels determined by an emotional state determination unit according to the second embodiment.

FIG. 28 is a diagram showing ranks of understanding levels determined by an understanding state determination unit according to the second embodiment.

FIG. 29 is a diagram showing ranks of the degree of conflict determined by a conflict state determination unit in the second embodiment.

FIG. 30 is a flowchart showing a procedure of a ranking method in the second embodiment.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Conversation control device, 100 ... Input part, 200 ... Voice recognition part, 300 ... Conversation control part, 310 ... Management part, 320 ... Reflexive determination part, 321 ... Ratio calculation part, 322 ... Selection part, 3
30 ... Parlor judgment unit, 340 ... Discourse range determination unit, 35
0 ... Abbreviated sentence complementing unit, 360 ... Topic search unit, 361 ... Delete unit, 362 ... Discourse addition unit, 370 ... Answer sentence search unit, 38
0 ... Ranking unit, 381 ... Emotional state determination unit, 382 ... Understanding state determination unit, 383 ... Conflict state determination unit, 400 ... Sentence analysis unit, 410 ... Morpheme extraction unit, 420 ... Phrase analysis unit, 4
30 ... Sentence structure analysis unit, 440 ... Utterance type determination unit, 450
... Morphological database, 460 ... Utterance type database, 500 ... Conversation database, 600 ... Output unit, 70
0 ... Voice recognition dictionary storage unit, 800 ... Communication unit, 801 ... Reflective element database, 802 ... Pardal element database, 900 ... Communication unit, 1000 ... Communication network, 1
100 ... Hard disk, 1200 ... Floppy disk, 1300 ... Compact disk, 1400 ... IC chip, 1500 ... Cassette tape

   ─────────────────────────────────────────────────── ─── Continued front page    (72) Inventor Wu             3-22-9 Takanawa, Minato-ku, Tokyo Aruze Takanawa Bi             Le (72) Inventor Lee Dong             3-22-9 Takanawa, Minato-ku, Tokyo Aruze Takanawa Bi             Le F term (reference) 5B075 ND03 PP07 PP24 PQ72

Claims (75)

[Claims] 1. A character recognizing unit that specifies a character string indicating the input information based on input information input by a user, and based on the character string specified by the character recognizing unit,
A morpheme extraction unit that extracts at least one morpheme that constitutes the minimum unit of the character string as the first morpheme information, and a plurality of second morpheme information that indicates a morpheme consisting of one character, a plurality of character strings, or a combination thereof in advance. A morpheme storage unit to store, collates the first morpheme information and each of the second morpheme information extracted by the morpheme extraction unit, and from the second morpheme information, including the first morpheme information, First search means for searching the second morpheme information, based on the search result searched by the first search means, from among each of the second morpheme information, the second morpheme information including the first morpheme information An information processing system comprising: ranking means for ranking according to the size of the search frequency. 2. The information processing system according to claim 1, wherein the ranking means outputs the ranked size as an emotional level that the user has. . 3. The information processing system according to claim 1, wherein the ranking means ranks a lower rank when the frequency of searching is low. A characteristic information processing system. 4. The information processing system according to claim 1 or 2, wherein the ranking means ranks a higher rank when the frequency of searching is high. A characteristic information processing system. 5. The information processing system according to claim 1, wherein the information related to the input information or the reply content to the user that is likely to be input from the user is provided. A discourse storage unit that stores a plurality of discourse ranges indicating the morphemes, the first morpheme information extracted by the morpheme extraction unit and the discourse ranges are collated, and the first discourse range is selected from the discourse ranges. A discourse search means for searching the discourse range including morpheme information, a first discourse range showing the discourse range before and a second discourse range showing the discourse range after being searched by the discourse search means. , And a relevance determination unit that determines whether the second discourse range is related to the first discourse range, and the ranking unit ranks based on the determination result by the relevance determination unit. Information that is characterized by Processing system. 6. The information processing system according to claim 5, wherein in the ranking unit, the relevance determination unit determines that the second discourse range is not related to the first discourse range. In the case of the above, an information processing system characterized by ranking in a low rank. 7. The information processing system according to claim 5, wherein the ranking unit determines that the second discourse range has relevance to the first discourse range by the relevance determination unit. In some cases, an information processing system that ranks high. 8. The information processing system according to claim 5, wherein the first morpheme information includes morphemes associated with each attribute such as a subject case composed of a nominative case and a target case composed of an objective case. An attribute search unit that searches the attribute that does not include the morpheme from the attributes that form the first morpheme information based on the first morpheme information extracted by the morpheme extraction unit; A morpheme adding means for adding the morpheme constituting the discourse range searched by the discourse search means to the attribute based on the attribute searched by the search means, and the ranking means, An information processing system, wherein the morpheme adding means ranks based on a result of adding the morphemes forming the discourse range. 9. The information processing system according to claim 1, wherein a plurality of standard contents for replying standard contents to the input information from the user are provided in advance. A fixed-form storage unit for storing, collates the first morpheme information extracted by the morpheme extraction unit with each of the fixed-form contents, and searches the fixed-form contents including the first morpheme information from the fixed-form contents. The fixed form acquisition unit, and the ranking unit, based on the search result searched by the fixed form acquisition unit, from among the fixed form contents, the frequency of the fixed form contents including the first morpheme information is searched. An information processing system characterized by ranking according to size. 10. The information processing system according to claim 1 or 2, wherein based on the character string specified by the character recognition means,
It has a type identifying means for identifying an input type indicating the type of the input information, and the ranking means is low when the input type identified by the type identifying means is a repulsive element such as repulsive sentence. An information processing system characterized by ranking in ranks. 11. The information processing system according to claim 9.
A plurality of the second morpheme information is stored in the morpheme storage means.
The answer contents are stored in each of the second morpheme information.
The second morpheme information, which is associated with each of them, is searched based on the second morpheme information searched by the first search means.
Then, in the answer associated with the second morpheme information
And an answer acquisition unit for acquiring the content, and the past contents of the answer acquired by the answer acquisition unit.
And a history storage unit that stores the history, and the fixed form obtaining unit obtains the morpheme extracting unit.
Compare the current first morpheme information and past answer contents.
And the current first morpheme information is included in the past answer contents.
The ranking means determines the determination result by the routine acquisition means.
Information processing system characterized by ranking based on
Tem. 12. The information processing system according to claim 9, wherein the history storage unit stores the past first morpheme information acquired by the fixed form acquisition unit, and the fixed form acquisition unit includes: The present first morpheme information and the past first morpheme information acquired by the morpheme extraction means are collated to determine whether the present first morpheme information is included in the past first morpheme information. The information processing system, wherein the ranking means ranks based on the determination result by the fixed form obtaining means. 13. The information processing system according to claim 1, wherein the ranking means outputs a ranked size as an understanding level for the input information. 14. The information processing system according to claim 1, wherein the ranking means is a topic requested by the user, an emotional level of the user with respect to a certain matter, or a statement or an affirmative sentence. An information processing system characterized by being described in a language for hierarchically accumulating types such as question sentences and repulsive sentences in the database in association with the morphemes according to their meaning contents. 15. The information processing system according to claim 1, wherein the language is DKML. 16. A character recognizing unit that specifies a character string indicating the input information based on input information input by a user; and a character string specified by the character recognizing unit,
A morpheme extraction unit that extracts each morpheme that constitutes the minimum unit of the character string as the first morpheme information, and a plurality of second morpheme information indicating a morpheme consisting of one character, a plurality of character strings, or a combination thereof is stored in advance. A morpheme storage means, collates the first morpheme information extracted by the morpheme extraction means with each of the second morpheme information, and from the second morpheme information, the second morpheme information including the first morpheme information First search means for searching morpheme information, based on the search results searched by the first search means, from the second each morpheme information, the second morpheme information including the first morpheme information is searched An information processing apparatus, comprising: a ranking unit that ranks according to the magnitude of the frequency. 17. The information processing apparatus according to claim 16, wherein the ranking means outputs the ranked size as an emotional level to hold for the user. . 18. The information processing apparatus according to claim 16, wherein the ranking means ranks a lower rank when the frequency of searches is low. A characteristic information processing device. 19. The information processing apparatus according to claim 16 or 17, wherein the ranking unit ranks a high rank when the frequency of the search is high. A characteristic information processing device. 20. The information processing apparatus according to claim 16 or 17, wherein the information related to the input information or the reply content to the user that is likely to be input from the user. A discourse storage unit that stores a plurality of discourse ranges indicating the morphemes, the first morpheme information extracted by the morpheme extraction unit and the discourse ranges are collated, and the first discourse range is selected from the discourse ranges. A discourse search means for searching the discourse range including morpheme information, a first discourse range showing the discourse range before and a second discourse range showing the discourse range after being searched by the discourse search means. , And a relevance determination unit that determines whether the second discourse range is related to the first discourse range, and the ranking unit ranks based on the determination result by the relevance determination unit. Characterized by Broadcast processing apparatus. 21. The information processing apparatus according to claim 20, wherein the ranking unit determines that the second discourse range has no relevance to the first discourse range by the relevance determination unit. In the case of the above, the information processing apparatus is characterized in that it is ranked low. 22. The information processing apparatus according to claim 20, wherein the ranking unit determines that the second discourse range has relevance to the first discourse range by the relevance determination unit. In some cases, the information processing device is characterized by being ranked high. 23. The information processing apparatus according to claim 20, wherein the first morpheme information includes morphemes associated with each attribute such as a subject case composed of a nominative case and a target case composed of an objective case. An attribute search unit that searches the attribute that does not include the morpheme from the attributes that form the first morpheme information based on the first morpheme information extracted by the morpheme extraction unit; A morpheme adding means for adding the morpheme constituting the discourse range searched by the discourse search means to the attribute based on the attribute searched by the search means, and the ranking means, An information processing apparatus, wherein the morpheme adding means ranks based on a result of adding the morphemes forming the discourse range. 24. The information processing apparatus according to claim 16, wherein a plurality of standard contents for replying standard contents to the input information from the user are provided in advance. A fixed-form storage unit for storing, collates the first morpheme information extracted by the morpheme extraction unit with each of the fixed-form contents, and searches the fixed-form contents including the first morpheme information from the fixed-form contents. The fixed form acquisition unit, and the ranking unit, based on the search result searched by the fixed form acquisition unit, from among the fixed form contents, the frequency of the fixed form contents including the first morpheme information is searched. An information processing device characterized by being ranked according to size. 25. The information processing apparatus according to claim 16 or 17, wherein the character string is identified by the character recognition means,
It has a type identifying means for identifying an input type indicating the type of the input information, and the ranking means is low when the input type identified by the type identifying means is a repulsive element such as repulsive sentence. An information processing device characterized by being ranked according to rank. 26. The information processing apparatus according to claim 24, wherein the morpheme storage unit stores a plurality of the second morpheme information, and each of the second morpheme information includes the answer content. Corresponding, based on the second morpheme information searched by the first search unit, an answer acquisition unit that acquires the answer content associated with the second morpheme information, and the answer acquisition unit And a history storage unit that stores the acquired response contents in the past, the fixed form acquisition unit collates the current first morpheme information acquired by the morpheme extraction unit with the past response contents. An information processing apparatus, wherein it is determined whether or not the present first morpheme information is included in the past answer contents, and the ranking unit ranks based on the determination result by the fixed form obtaining unit. 27. The information processing apparatus according to claim 24, wherein the history storage unit stores the past first morpheme information acquired by the fixed form acquisition unit, and the fixed form acquisition unit includes: The present first morpheme information and the past first morpheme information acquired by the morpheme extraction means are collated to determine whether the present first morpheme information is included in the past first morpheme information. The information processing apparatus, wherein the ranking means ranks based on the determination result by the fixed form obtaining means. 28. The information processing apparatus according to claim 16, wherein the ranking means outputs a ranked size as an understanding level for the input information. 29. The information processing apparatus according to claim 16, wherein the ranking means is a topic desired by the user, a degree of emotion the user has for a certain matter, or a statement statement, an affirmative statement, An information processing apparatus, characterized in that it is described in a language for hierarchically accumulating types such as interrogative sentences and repulsive sentences in the database in association with the morphemes according to their meaning contents. 30. The information processing apparatus according to claim 16, wherein the language is DKML. 31. A step of specifying a character string indicating the input information based on input information input by a user, and each of the minimum units of the character string based on the specified character string. A step of extracting a morpheme as the first morpheme information; a step of pre-storing a plurality of second morpheme information consisting of one character, a plurality of character strings or a combination thereof, the extracted first morpheme information and each of the first morpheme information Collating the two morpheme information and searching the second morpheme information including the first morpheme information from the respective second morpheme information; and the second morpheme based on the searched search result. And a step of ranking the second morpheme information including the first morpheme information in accordance with the frequency of retrieval from the information. 32. The information processing method according to claim 31, wherein the ranked size is output as an emotion level to the user. 33. The information processing method according to claim 31 or 32, wherein when the frequency of retrieval is low, a low rank is applied. . 34. The information processing method according to claim 31 or 32, wherein when the frequency of retrieval is high, a high rank is assigned. . 35. The information processing method according to claim 31 or 32, wherein the input information or the reply content to the user, which is likely to be input from the user, is relevant. Storing a plurality of discourse ranges indicating a certain morpheme, collating the extracted first morpheme information with each discourse range, and selecting the discourse range including the first morpheme information from each discourse range And a second discourse range indicating the previous discourse range and a second discourse range indicating the subsequent discourse range, and the second discourse range is related to the first discourse range. An information processing method comprising: a step of determining whether or not there is property, and a step of ranking based on a result of the determination. 36. The information processing method according to claim 35, wherein when it is determined that the second discourse range is not related to the first discourse range, the second discourse range is ranked low. An information processing method characterized by: 37. The information processing method according to claim 35, wherein when it is determined that the second discourse range is related to the first discourse range, the second discourse range is ranked high. A characteristic information processing method. 38. The information processing method according to claim 35, wherein the first morpheme information includes morphemes associated with each attribute such as a subject case composed of a nominative case and a target case composed of an objective case. , Based on the extracted first morpheme information, from among the attributes constituting the first morpheme information, searching for the attribute that does not include the morpheme, based on the searched attribute, Information including the step of adding the morphemes forming the searched discourse range to the attribute, and ranking based on the result of adding the morphemes forming the discourse range Processing method. 39. The information processing method according to claim 31 or 32, wherein a plurality of standard contents for replying standard contents to the input information from the user are prepared in advance. A step of storing, a step of collating the extracted first morpheme information with each of the standard content, and a step of searching the standard content including the first morpheme information from the respective standard content; Based on the search results, from each standard content,
And a step of ranking the standard contents including the first morpheme information according to the frequency of the search. 40. The information processing method according to claim 31 or 32, wherein, based on the character string specified by the character recognition means,
Information having a step of specifying an input type indicating the type of the input information, and a step of ranking a low rank when the specified input type is a repulsive element such as a repulsive sentence Processing method. 41. The information processing method according to claim 39, wherein a plurality of the second morpheme information items are stored, and each of the second morpheme information items is associated with the answer content. Acquiring the answer content associated with the second morpheme information based on the acquired second morpheme information; storing the acquired answer content in the past; Collating the first morpheme information with the past answer content, determining whether the current first morpheme information is included in the past answer content, and a step of ranking based on the result of the determination. An information processing method comprising: 42. The information processing method according to claim 39, wherein the step of storing the acquired past first morpheme information, the acquired current first morpheme information and the past first It is characterized by comprising a step of comparing with the morpheme information and determining whether the current first morpheme information is included in the past first morpheme information, and a step of ranking based on the result of the determination. Information processing method. 43. The information processing method according to claim 31, wherein the ranked size is output as an understanding level for the input information. 44. The information processing method according to claim 31, wherein a topic desired by the user, an emotional level of the user having a certain thing, a statement, an affirmative sentence, a question sentence, a repulsive sentence, and the like. The information processing method is characterized by being described in a language for hierarchically accumulating in the database the types of the items in association with the morphemes according to their meaning contents. 45. The information processing method according to claim 31, wherein the language is DKML. 46. A step of specifying, on the computer, a character string indicating the input information based on the input information input by the user; and a minimum unit of the character string based on the specified character string. A step of extracting each morpheme constituting the first morpheme information; a step of pre-storing a plurality of second morpheme information indicating each of the morphemes of the input information that will be input from the user; Collating one morpheme information with each of the second morpheme information, and searching the second morpheme information including the first morpheme information from each of the second morpheme information, and based on the searched result A step of ranking the second morpheme information among the respective second morpheme information in accordance with the frequency with which the second morpheme information including the first morpheme information is searched. Program. 47. The program according to claim 46, which carries out a process including a step of outputting the ranked size as an emotional level to the user. 48. The program according to claim 46 or 47, wherein the program has a step of ranking a low rank when the frequency of searches is low. 49. The program according to claim 46 or 47, wherein the program has a step of ranking a high rank when the frequency of searching is high. 50. The program according to claim 46 or 47, wherein the program is related to the input information that may be input from the user or the reply content to the user. Storing a plurality of discourse ranges indicating morphemes, collating the extracted first morpheme information with each discourse range, and searching the discourse range including the first morpheme information from each discourse range And a second discourse range indicating the retrieved discourse range and a second discourse range indicating the retrieved discourse range, and the second discourse range is related to the first discourse range. A program for performing processing including a step of determining whether or not to have and a step of ranking based on the result of the determination. 51. The program according to claim 50, further comprising the step of ranking a lower rank when it is determined that the second discourse range is not related to the first discourse range. A program for processing. 52. The program according to claim 50, wherein when the second discourse range is determined to be related to the first discourse range, a process of ranking a higher rank Program to let you do. 53. The program according to claim 50, wherein the first morpheme information is composed of morphemes associated with each attribute such as a subject case made up of a nominative case and a target case made up of an objective case. A step of searching the attribute that does not include the morpheme from the respective attributes that constitute the first morpheme information based on the searched first morpheme information; and the attribute based on the searched attribute. And a step of adding the morphemes forming the searched discourse range, and ranking based on a result of the addition of the morphemes forming the discourse range. 54. The program according to claim 46 or 47, wherein a plurality of standard contents for replying standard contents to the input information from the user are stored in advance. A step of collating the extracted first morpheme information with each of the standard contents and searching the standard contents including the first morpheme information from the standard contents; Based on each of the standard contents,
And a step of ranking the standard content including the first morpheme information according to the frequency of the search. 55. The program according to claim 46 or 47, wherein the program is based on the character string specified by the character recognition means,
A program for performing a process including a step of specifying an input type indicating the type of the input information, and a step of ranking a lower rank when the specified input type is a repulsive element such as a repulsive sentence. . 56. The program according to claim 54, wherein a plurality of the second morpheme information items are stored, and each of the second morpheme information items is associated with the answer content and retrieved. Acquiring the answer content associated with the second morpheme information based on the second morpheme information; storing the acquired answer content in the past; A process including a step of comparing the morpheme information with the past answer content, determining whether the current first morpheme information is included in the past answer content, and a step of ranking based on a result of the determination. Program to let you do. 57. The program according to claim 54, wherein the step of storing the acquired first morpheme information of the past, the acquired first morpheme information of the present and the first morpheme information of the past And a step of determining whether the current first morpheme information is included in the past first morpheme information, and a step of ranking based on the result of the determination. 58. The program according to claim 46, wherein the program has a step of outputting a ranked size as an understanding level for the input information. 59. The program according to claim 46, wherein the topic desired by the user, the degree of emotion the user has for a certain matter, or the type of statement, affirmative sentence, question sentence, repulsive sentence, etc. Is described in a language for hierarchically accumulating in a database in association with the morpheme according to its meaning content. 60. The program according to claim 46, wherein the language is DKML. 61. A step of specifying, in a computer, a character string indicating the input information based on input information input by a user; and a minimum unit of the character string based on the specified character string. A step of extracting each morpheme constituting the first morpheme information, a step of pre-storing a plurality of second morpheme information indicating a morpheme consisting of one character, a plurality of character strings or a combination thereof, the extracted first morpheme information Matching the morpheme information with each of the second morpheme information, and searching the second morpheme information including the first morpheme information from each of the second morpheme information, and based on the searched result Of the second morpheme information, the second morpheme information including the first morpheme information is ranked according to the frequency of retrieval, A computer-readable recording medium storing a program fit. 62. The recording medium according to claim 61, wherein the computer-readable recording medium stores a program for causing a process to output a ranked size as an emotional level to the user. Recording medium. 63. The recording medium according to claim 61 or 62, wherein a program having a step of ranking a lower rank when the frequency of the search is low is provided. A computer-readable recording medium in which is recorded. 64. The recording medium according to claim 61 or 62, wherein a program having a step of ranking a high rank when the frequency of searching is high A computer-readable recording medium in which is recorded. 65. The recording medium according to claim 61 or 62, wherein the recording medium is relevant to the input information that may be input from the user or the reply content to the user. Storing a plurality of discourse ranges indicating the morphemes, collating the extracted first morpheme information with each discourse range, and selecting the discourse range including the first morpheme information from each discourse range. The step of searching and the searched first discourse range indicating the discourse range and the retrieved second discourse range indicating the discourse range are collated, and the second discourse range is related to the first discourse range. A computer-readable recording medium having a program for performing a process including a step of determining whether or not the item has a value and a step of ranking based on a result of the determination. 66. The recording medium according to claim 65, wherein when it is determined that the second discourse range is not related to the first discourse range, a step of ranking a lower rank is performed. A computer-readable recording medium in which a program for causing the processing to be recorded is recorded. 67. The recording medium according to claim 65, further comprising a step of ranking a higher rank when it is determined that the second discourse range is related to the first discourse range. A computer-readable recording medium in which a program for processing is recorded. 68. The recording medium according to claim 65, wherein the first morpheme information includes morphemes associated with each attribute such as a subject case composed of a nominative case and a target case composed of an objective case, Based on the extracted first morpheme information, a step of searching for the attribute that does not include the morpheme from among the attributes that form the first morpheme information; and, based on the searched attribute, A program for performing a process that includes a step of adding the morphemes forming the searched discourse range to an attribute, and a step of ranking based on a result of adding the morphemes forming the discourse range The recorded computer-readable recording medium. 69. The recording medium according to claim 61 or 62, wherein a plurality of standard contents for replying standard contents to the input information from the user are stored in advance. And a step of collating the extracted first morpheme information with each of the standard contents and searching the standard contents including the first morpheme information from the standard contents, and the searched search Based on the results, from each standard content,
A computer-readable recording medium having a program for performing a process including a step of ranking the standard contents including the first morpheme information according to the frequency of the frequency of retrieval. 70. The recording medium according to claim 61 or 62, wherein, based on the character string specified by the character recognition means,
A program for performing a process including a step of specifying an input type indicating the type of the input information, and a step of ranking a lower rank when the specified input type is a repulsive element such as a repulsive sentence. A computer-readable recording medium in which is recorded. 71. The recording medium according to claim 69, wherein a plurality of the second morpheme information items are stored, and each of the second morpheme information items is associated with the answer content and is searched. The step of acquiring the answer content associated with the second morpheme information based on the second morpheme information, the step of storing the acquired past answer content, and the acquired current first The method includes a step of comparing one morpheme information with the past answer content, determining whether the current first morpheme information is included in the past answer content, and a step of ranking based on the result of the determination. A computer-readable recording medium in which a program for processing is recorded. 72. The recording medium according to claim 69, wherein the step of storing the acquired past first morpheme information, the acquired current first morpheme information and the past first morpheme information A program for performing a process including a step of determining whether the current first morpheme information is included in the past first morpheme information by collating information, and a step of ranking based on the result of the determination A computer-readable recording medium in which is recorded. 73. The recording medium according to claim 61, wherein a computer-readable recording medium having recorded therein a program for causing a process to have a step of outputting a ranked size as an understanding level with respect to the input information. . 74. The recording medium according to claim 61, wherein a topic desired by the user, an emotional level that the user has for a certain matter, or a statement, an affirmative sentence, a question sentence, a repulsive sentence, or the like. A computer-readable recording medium storing a program, characterized in that a type is described in a language for hierarchically accumulating in a database in association with the morpheme according to its meaning content. 75. The recording medium according to claim 61, wherein the language is DKML and a computer-readable recording medium recording a program.