JP6598227B1 - Cat-type conversation robot - Google Patents

Abstract

The present invention provides a cat-type conversation robot that has a pseudo-ego and a cat that changes a dialogue attitude each time an utterance is received, and that changes facial expressions according to the contents of the dialogue. A cat-type conversation robot 10 includes a voice input unit 11 that receives an uttered voice and outputs a received signal, and a display unit 12 that displays a face image of a character set as a robot-side dialoguer. A voice output means 13 for generating a dialog voice for the speaker, and voice data forming a dialog voice based on a dialogue attitude set in response to the received signal and inputting the voice data to the voice output means 13, The facial image composition data for forming the facial image of the character and the facial expression data for changing the facial expression during the dialogue of the character are respectively created, and the combined facial image data and facial expression data are input to the display means 12 as image display data. And a control device 14 for controlling. [Selection] Figure 1

Description

The present invention relates to a cat-type conversation robot, and in particular, a speaker who performs a conversation (conversation) with a cat-type conversation robot by having the cat-type conversation robot respond like a pet with a pseudo ego. An environment in which a user (a user of a cat-type conversation robot, hereinafter also simply referred to as a user) enjoys a conversation with a cat-type conversation robot is constructed.
In other words, with an about life schedule (for example, sleep until 9 o'clock, enjoy music until 14 o'clock, run hobbies until around 18 o'clock, and sleep etc.) Establish a situation where a cat-type conversation robot lives, and let the user talk about the life of the cat-type conversation robot, or make the user troublesome, for example, pseudo food requests and excrement processing The aim is to enhance the conversation by having the user interact with each other according to the user's interests, including changing the content of the conversation in response to the requested action.
In addition, it has the character of a cat that changes the dialogue attitude every time it receives the speech from the user, and when the cat-type conversation robot responds to the user's speech, the cat-type conversation robot side (hereinafter simply referred to as the robot side) It is also related to a cat-type conversation robot that changes the facial expression of a character in accordance with the content of the conversation while displaying a facial image of the character set as a conversation person.

Here, “having the character of a cat” means, for example, 1) a dialogue pattern in which the user speaks spontaneously or makes an utterance requesting something so that the cat can slip and pamper, and 2) the cat is independent. 3) Dialogue patterns that are ignored even if the user speaks so that the owner does not always show obedience, 3) Dialogue on a topic that is different from the topic spoken by the user so that the cat exhibits unexpected behavior 4) Having a dialogue attitude such as a dialogue pattern that rejects dialogue to the user so that the cat sometimes shows a threatening attitude towards the owner.

In conversations (conversations) with conventional conversational robots, it is easy to perform repetitive and uniform conversations (so-called unnatural conversations) as typified by customer-based customer service, and conversations are not interesting. It has been pointed out that there is a problem that it is difficult to continue and conversation like chat is not possible. For this reason, the conversational robot identifies the user and creates a response sentence based on the user's profile acquired in advance, or obtains the user's new information while interacting, and obtains the obtained information Proposals have been made to avoid unnatural dialogue by appropriately reflecting it in the creation of a response sentence (see, for example, Patent Document 1).

Further, since the conventional conversational robot cannot perform a conversation while changing its facial expression, there is a problem that it is difficult for the user to communicate with the conversational robot. Therefore, the emotion of the user is quantified from the voice of the user, and the emotion parameters are calculated for each item such as joy, stress, etc., and based on the utterance scenario, facial expression scenario, and operation scenario that are created in advance for each emotion parameter Thus, there has been proposed a conversation robot system that outputs a predetermined voice (utterance content), creates a predetermined facial expression, and realizes a predetermined action (see, for example, Patent Document 2).

JP-T-2006-536630 JP 2008-125815 A

In the invention of Patent Document 1, since a response sentence is created based on user information, there is a problem that it is difficult for a conversation topic to change, and it is difficult to continue a conversation with a conversational robot. In addition, when the user starts a conversation for the purpose of chatting, it is almost impossible for the conversational robot to obtain the user's information on the topic of chatting if the topic of chatting has arisen from the idea. If the conversation is continued forcibly, the conversation tends to be unnatural and it becomes difficult to continue the conversation with the conversational robot.
Further, the conversational robot disclosed in Patent Document 2 determines the utterance content, facial expression, and action based on the user's emotion estimated by the conversational robot and the utterance scenario, expression scenario, and action scenario created in advance. However, it is not possible to appropriately change the expression of the conversational robot based on the response contents while the conversational robot has a conversation. For this reason, the problem that it is difficult for the user to communicate with the conversational robot cannot be solved.

In addition, a “watching function” is added to a conversational robot by attaching a monitoring camera such as a monitoring camera or a human sensor to detect an abnormal state of the user to a conventional conversational robot. . However, in monitoring the abnormal state of the user using the monitoring sensor, it is monitored that no obvious abnormality occurs (for example, “the user cannot fall and move”, “the user is fainted and falls”). Abnormality cannot be recognized unless it can be obtained as a camera image. For this reason, there is a problem that even if a monitoring sensor is provided, there is a high risk that the user will be left unattended until a serious condition occurs.

The present invention has been made in view of such circumstances, and the cats who are involved in the life of a cat-type conversation robot naturally promote mutual conversation, and in addition, the cats that change the conversational attitude each time they receive uttered speech. It is possible to change the dialogue by having the personality of the character, and change the facial expression according to the content of the dialogue while displaying the facial image of the character set as the robot dialogue person A cat-type conversation robot that makes it easier to communicate, and that can quickly detect abnormalities in the speaker and notify relevant parties from changes in the conversation state during the conversation of the speaker and changes in the content of answers to questions. The purpose is to provide.

Cat type conversation robot according to the present invention along the object has a ego like artificially pets, cats type conversation robot with the characteristics of cat to change the conversation attitude each time it receives the speech of a speaker There,
Voice input means for receiving the uttered voice and outputting a received signal;
A display means for displaying a face image at the time of dialogue of the character set as a dialogue person on the robot side;
Voice output means for generating dialogue voice for the speaker;
Image display data for changing the facial expression of the character's facial image during dialogue while creating voice data forming the dialogue voice based on the dialogue attitude set in response to the received signal and inputting the voice data into the voice output means create and have a control device to be input to the display means,
The control device
(1) a voice input processing unit that converts the received signal output from the voice input means into an utterance voice file, creates an utterance character file from the utterance voice file, and outputs the utterance character file;
(2) a dialogue management unit that receives the input of the spoken character file and creates and outputs a dialogue character file that is a basis of the dialogue voice;
(3) a voice output processing unit that receives input of the dialogue character file, forms the voice data from the dialogue character file, converts the voice data into a voice signal, and inputs the voice signal to the voice output means;
(4) Facial facial expression that forms facial expression in accordance with the emotion image synthesis data that forms the facial image of the character and the dialogue character file in response to the input of the dialogue character file. Character expression processing unit that creates data and inputs the combined image of the face image and the facial expression data to the display means as the image display data
And
The dialogue management unit arbitrarily selects a dialogue pattern S as the dialogue attitude from among a plurality of preset dialogue patterns each time the utterance character file is input, and the dialogue corresponding to the dialogue pattern S It has a response dialogue system that outputs a character file and a spontaneous speech system,
In the spontaneous utterance system,
(1) Spontaneous speech conditions including at least one of the hobby of the speaker, a life pattern incorporating a cat's unique behavior, and the requested behavior of the cat-type conversation robot that the speaker is aware of responding in advance. A spontaneous utterance condition setting means to be set;
(2) Condition establishment determining means for outputting a condition satisfaction signal when the spontaneous utterance condition set by the spontaneous utterance condition setting means is established;
(3) Spontaneous utterance means for receiving the condition establishment signal and outputting the spontaneous utterance character file set in the spontaneous utterance condition corresponding to the condition establishment signal as the dialogue character file
And
The spontaneous utterance condition setting means is further provided with a watch start condition for executing the watch of the speaker as the spontaneous utterance condition, and the watch start condition is determined from a start time set in a time zone when the speaker wakes up. The spontaneous utterance character file set for the watch start condition is set to occur at least once before the end time set in the time period when the speaker goes to bed, and the personal information of the speaker is stored in the personal information of the speaker. Ru der what constitutes a specific question based.
By setting it as such a structure, a maintenance and update can be performed for every process part which comprises a control apparatus.
Every time an utterance character file created from the uttered voice is input to the dialogue management unit, the dialogue pattern S is selected as the dialogue attitude in the response dialogue system of the dialogue management unit, so the cat-type conversation robot receives the utterance voice. It is possible to make a response by changing the dialogue attitude every time.
By providing a self-speaking means, the cat-type conversation robot responds to the utterance from the speaker in both directions (utterance from the speaker to the cat-type conversation robot, utterance from the cat-type conversation robot to the speaker) ) Conversation is possible. Also, tell the cat-type conversation robot to talk to the speaker from the cat-type conversation robot and make the cat play alone so that the cat will snag and pamper the owner. Can be made.
Here, the frequency of talking to the speaker from the cat-type conversation robot and the frequency of the cat-type conversation robot speaking to the self can be determined by the spontaneous utterance conditions. Moreover, the topic that the cat-type conversation robot speaks to the speaker and the topic of the self-speaking can be set by the spontaneously uttered character file.
Here, the specific question based on the personal information of the speaker is, for example, for the speaker such as the name of the speaker, the date of birth, the name of the parent, sibling, or child, the password that has been confirmed in advance. This is a question that can be easily answered correctly and is difficult for a third party to answer correctly. Accordingly, the correct answer rate of the speaker is normally 100%, and the occurrence of an incorrect answer indicates that there is a high possibility that the speaker has a change in physical condition (abnormality).

In the cat-type conversation robot according to the present invention, the cat-like conversation robot further includes an imaging unit that captures the speaker, and the control device uses the image of the speaker obtained by the imaging unit, It is preferable that a display position adjustment unit is provided that adjusts the direction of the display surface and causes the face image of the character displayed on the display surface to face the speaker.
As a result, the speaker (user) can easily grasp the change in facial expression during the character dialogue.

In the cat-type conversation robot according to the present invention, the character's face image may be a cat's animated face image.
Thus, the speaker can set the character's face according to his / her preference. The face image of the character can be created in accordance with the request of the speaker, or the speaker can be selected from a plurality of face image candidates prepared in advance.

In the cat-type conversation robot according to the present invention, the plurality of interaction patterns are:
(1) a normal dialogue pattern indicating the dialogue attitude in response to a topic included in the utterance character file;
(2) a changed topic dialogue pattern indicating the dialogue attitude to respond with a topic different from the topic of the utterance character file;
(3) an ignoring dialogue pattern indicating the dialogue attitude that makes no response to the input of the utterance character file;
(4) It may have a rejection dialogue pattern indicating the dialogue attitude that causes dialogue rejection with respect to input of the utterance character file.

When a normal dialogue pattern is selected as the dialogue attitude, it responds to the topic of the utterance character file (speech voice file), and can cause the cat-like conversation robot to have a submissive aspect of the cat. When the changed topic dialogue pattern is selected, the cat responds to a topic different from the topic of the utterance character file, and can cause an unexpected aspect of the cat to the cat-type conversation robot. In addition, when the neglected dialogue pattern is selected as the dialogue attitude, there is no response even when talking to the cat-like conversation robot, and a cat-independent robot can be brought to a high level of independence, and the rejection dialogue pattern is selected as the dialogue attitude. The conversation is rejected, and the cat-like conversation robot can cause a cat's intimidating (non-obedient) aspect. As a result, the speaker can communicate with the cat-type conversation robot with an appropriate sense of distance.

The “topic different from the topic possessed by the utterance character file” refers to having a topic different from the topic possessed by the utterance character file and a topic that is weakly related to the topic possessed by the utterance character file. If the frequency of responding on different topics is increased, a cat having a strong personality can be realized in a cat-type conversation robot, and if the frequency of responding on a less relevant topic is increased, a cat having a low personality can be realized in a cat-type conversation robot.
Here, the topic that is weakly related to the topic of the utterance character file refers to the case where the subject field is the same but the target is different, for example, when the topic is Japanese food, such as Asia, Africa, Europe, etc. It refers to talking about foreign cuisine.

In the cat-type conversation robot according to the present invention, selection probabilities based on the character of the cat are set in advance for the normal conversation pattern, the changed topic conversation pattern, the neglected conversation pattern, and the rejection conversation pattern, respectively. Is preferred.
In order to make each dialogue pattern occur with a selection probability based on the character of the cat, normal dialogue pattern (cat obedience), change topic dialogue pattern (cat unexpectedness), neglect dialogue pattern (cat independence), rejection dialogue A pattern (cat's intimidation) can be generated in a cat-type conversation robot without a sense of incongruity. By adjusting the selection probability of each dialogue pattern, the ratio of obedience, unexpectedness, independence, and intimidation can be changed, and the character of the cat can be characterized (formation of the cat's personality). Become.

In the cat-type conversation robot according to the present invention, when the utterance character file includes a specific word registered in advance, and when the utterance character file including the specific word is input, the selection of the normal dialogue pattern is performed. The probability is preferably set higher than 50%.
As a result, if the owner wants to be a cat partner, the cat will usually have a chance to interact with the cat by putting a cat-specific specific word into the utterance, just like the cat likes it (for example, cat catering). You can enjoy a conversation with a conversation robot.

In the cat-type conversation robot according to the present invention, the response dialogue system includes:
(1) A plurality of separate character files having a topic different from that of the input speech character file, a plurality of ignored character files corresponding to dialogue ignorance, and a plurality of rejection character files corresponding to dialogue refusal, respectively. Character file database to store and output on demand,
(2) Dialog response processing means for creating and outputting a plurality of response character files by inputting the spoken character file and the separate character file,
(3) a normal dialogue unit that selects a response character file A from the plurality of response character files output from the dialogue response processing unit by inputting the utterance character file and outputs the selected response character file as the dialogue character file;
(4) Selecting the different character file W from the plurality of different character files stored in the character file database, inputting the selected character file W to the dialogue response processing means, and outputting the plurality of responses output from the dialogue response processing means A change topic type dialogue means for selecting a response character file B from a character file and outputting it as the dialogue character file;
(5) Ignore interaction means for selecting an ignore character file C from the plurality of ignore character files stored in the character file database and outputting the selected ignore character file as the dialog character file;
(6) Rejection-type dialogue means for selecting a rejection character file D from the plurality of rejection character files stored in the character file database and outputting it as the dialogue character file can be provided.
As a result, the cat-like conversation robot can realize a dialogue attitude that specifically expresses the character of the cat.

In the cat-type conversation robot according to the present invention, the voice input processing unit includes voice detection means for creating the utterance voice file from the received signal, and voice recognition processing for creating and outputting the utterance character file from the utterance voice file. Means,
The speech recognition processing means and the dialogue response processing means are each provided on a cloud, and input the utterance speech file to the speech recognition processing means, output of the utterance character file from the speech recognition processing means, and the utterance character The file and the input of the separate character file W to the dialogue response processing means, and the output of the response character file from the dialogue response processing means to the normal type dialogue means and the changed topic type dialogue means are respectively via information communication lines. Is preferable.

If the speech recognition processing means and the dialogue response processing means are provided on the cloud, a large-scale database can be connected, and hardware update and application software update and improvement can be appropriately performed. For this reason, the speech recognition processing means can quickly and accurately convert an utterance voice file to an utterance character file, and the dialog response processing means can obtain a response character file having an accurate content in response to the content of the utterance character file. Can be easily created.

In the cat-type conversation robot according to the present invention, it is preferable that the response character file A includes a question related to the topic of the utterance character file.
As a result, since the dialogue continues in the form of answering the question, it becomes easy for the robot to narrow down the topic, and the dialogue can be continued easily.

In cats type conversation robot according to the present invention, the prior SL controller, wherein determining the correctness of a speaker of the answer to a specific question, erroneous answers first to output the first abnormal signal when generated in It is preferable that an alarm unit is provided .

In the cat-type conversation robot according to the present invention, it is preferable that the spontaneous utterance character file is created in advance for each spontaneous utterance condition and stored in a spontaneous utterance character file database provided in the spontaneous utterance system.
This allows the cat-type conversation robot to talk on topics that match the speaker's preferences and preferences, or can make the cat-type conversation robot (cat) make a request for something. It is easy to create an opportunity to talk with a cat or take care of a cat-type conversation robot.

In the cat-type conversation robot according to the present invention, the sentence included in the dialogue character file is output to the voice output processing unit via ending processing means for performing ending processing that adds “Nyan” to the ending of the sentence. It is preferable.
Thereby, "Nyan" is uttered at the end of the sentence, and the image as a cat can be improved.

In the cat-type conversation robot according to the present invention, the control device receives the utterance voice by the voice input means after the conversation voice is uttered every time the conversation voice is uttered in a preset time zone. And detecting whether or not a response state change has occurred in which a deviation between the reference standby time of the speaker and the standby time obtained in advance exceeds a set allowable value. A second alarm unit is provided for outputting a second abnormality signal when the cumulative number of occurrences of the response state change after the first dialogue is established reaches a preset abnormal response determination value. Preferably it is.

Here, the reference waiting time is a statistic obtained by measuring the waiting time in the normal state of the speaker a plurality of times and performing statistical processing, for example, an average value, median value, or mode value of the waiting time distribution. . The deviation is a difference between the standby time and the reference standby time, and the allowable value can be set to any one of σ, 2σ, or 3σ using, for example, the standard deviation σ of the standby time distribution.
Waiting time from when the voice is output by the voice output means of the cat-type conversation robot to when the voice of the speaker is received by the voice input means of the cat-type conversation robot (from the time the speaker is spoken until the response is made) Time) is considered to be a measurement that reflects the dialogue processing ability affected by the physical condition of the speaker. For this reason, the deviation exceeding the allowable value indicates that the response state at the time of dialogue of the speaker is changing. The fact that the cumulative number of occurrences of the response state change has reached the abnormal response determination value indicates that a new (abnormal) dialogue response state has occurred in the speaker, and the physical condition change ( It can be determined that there is a high possibility that an abnormality) has occurred.

In the cat-type conversation robot according to the present invention, the control device has a certainty factor that quantitatively indicates a probability of the utterance character file output from the voice input processing unit to the dialogue management unit with respect to the utterance voice file. When the occurrence of the low certainty state where the certainty factor is equal to or less than the preset abnormality certainty level is detected and the cumulative number of occurrences of the low certainty state reaches the preset abnormal cumulative number It is preferable that a third alarm unit for outputting a third abnormality signal is provided.

When the speech input processing unit converts an utterance speech file created from the received signal into an utterance character file, if the sentence (character) cannot be uniquely determined for the speech (the confidence level at the time of conversion (the utterance speech file (utterance (Speech) (if the probability value of the probability of recognition) is not 100%), a plurality of spoken character files are provided as candidates in descending order of confidence, and usually the first candidate (the confidence is the highest) ) An utterance character file is input to the dialogue management unit.
Here, if the method of creating the utterance character file in the voice input processing unit is fixed, the same utterance character file is always obtained with the same certainty factor for the same utterance voice file (utterance voice). Therefore, when the certainty factor evaluated by the voice input processing unit is obtained for various utterance voice files (uttered voices) of the normal speaker, the distribution of the certainty factor quantitatively determines the conversation state of the normal speaker. It becomes one of the scales evaluated. For this reason, if the abnormality certainty is set to a value smaller than the minimum value of the certainty distribution, the low certainty state in which the abnormality during creation of the utterance character file is equal to or less than the certainty is generated. This indicates that a change has occurred in the conversation state of the speaker, that is, the speaker is not in a normal state. The fact that the cumulative number of occurrences of the low confidence state has reached the abnormal cumulative number indicates that there is a high possibility that a physical condition change (abnormality) has occurred as the conversation state is changed by the speaker. .
In addition, since the certainty degree with respect to the speech voice file (speech voice) of the speaker in a normal state is generally about 90%, for example, the abnormality certainty level can be set to a value of about 70% confidence level. Further, the cumulative number of abnormal times can be set to a value of about 5 times, for example.

In the cat-type conversation robot according to the present invention, it has a pseudo ego, and the conversational attitude is changed every time an utterance voice is received like the character of a cat. Therefore, an unexpected dialogue voice is output. It becomes easy to change in the dialogue.
In addition, when talking with a cat-type conversation robot, the face image of the character set as the robot's talker can be displayed on the display means, and the facial expression during the character's dialogue can be changed slightly depending on the content of the dialogue. As a result, the speaker can easily communicate with the cat-type conversation robot.

Is provided with the spontaneous speech it means to the dialogue management unit in the control unit, a conversation starting from speech to cat type communication robots from two-way conversation between the speaker and the cat-type communication robots (utterer, from cat-type communication robots Conversation starting from utterance to the speaker) can be established, and conversation opportunities can be improved. As a result, it is possible to create a situation where a cat-type conversation robot and a speaker are associated with each other for a long time. For example, it is possible to eliminate the feeling of loneliness that there is no talking partner and to reduce the stress of association with a cat-type conversation robot (machine). It becomes possible.
In addition, when any one or more of the first to third alarm units are provided in the control device, a slight abnormality that is not normal to the speaker during the conversation between the speaker and the cat-type conversation robot. It is possible to detect the occurrence of the condition at an early stage, and it becomes possible to increase the level of peace of mind and safety of the speaker.

It is a block diagram which shows the structure of the cat-type conversation robot which concerns on the 1st Embodiment of this invention. It is a block diagram which shows the structure of the control apparatus of the cat-type conversation robot. It is a block diagram which shows the structure of the audio | voice input process part of the cat-type conversation robot. It is a block diagram which shows the structure of the response dialog system | strain of the dialog management part of the same cat-type conversation robot. It is a block diagram which shows the structure of the dialog management part of the cat-type conversation robot. It is a block diagram which shows the structure of the spontaneous utterance system | strain of the dialogue management part of the same cat type conversation robot. It is a block diagram which shows the structure of the audio | voice output process part of the cat-type conversation robot. It is a block diagram which shows the structure of the character expression process part of the same cat type conversation robot. It is explanatory drawing of the incidental apparatus of the cat-type conversation robot. It is a flowchart of the dialogue processing of the same cat type conversation robot. It is a flowchart of the response dialog process in dialog step 3 of a dialog process. It is a flowchart of the spontaneous speech process in the dialog step 3 of a dialog process. It is a block diagram which shows the structure of the cat-type conversation robot which concerns on the 2nd Embodiment of this invention. It is a block diagram which shows the structure of the control apparatus of the cat-type conversation robot.

Next, embodiments of the present invention will be described with reference to the accompanying drawings for understanding of the present invention.
As shown in FIG. 1, the cat-type conversation robot 10 according to the first embodiment of the present invention has a pseudo ego and receives the utterance voice of the user (speaker) of the cat-type conversation robot 10. A conversation robot having a cat-like character that changes the dialogue attitude, and is set as a microphone 11 (an example of a voice input means) that receives a user's uttered voice and outputs a received signal, and a robot-side talker A display 12 (an example of a display unit) that displays a face image of a character during dialogue, a speaker 13 (an example of an audio output unit) that generates dialogue voice for the user, and a dialogue attitude that is set by receiving a received signal While creating voice data that forms dialogue voice based on the character and inputting it to the speaker 13, image display data that changes the facial expression of the character during dialogue is created and displayed. And a control unit 14 to be input to 12.
Here, the character face image is set by selecting one of a plurality of cat anime face images prepared in advance. It should be noted that the character face image can be arbitrarily created according to the user's request.

Further, the cat-type conversation robot 10 has a camera 15 (an example of an imaging unit) that captures a user, and the control device 14 uses the user's image obtained by the camera 15 to display the direction of the display surface of the display 12. And a display position adjusting unit 16 is provided to make the character face image displayed on the display 12 face the user. Here, the display position adjustment unit 16 obtains the user's three-dimensional position with respect to the display 12 (for example, the center position of the display surface) from the user's image, and sets the direction of the display surface of the display 12 (for example, the center position of the display surface). A correction data calculator 17 for calculating correction data for adjusting the direction of the established normal), and a movable holding base 18 on which the display 12 is mounted and the direction of the display surface of the display 12 is changed based on the correction data. Have.

As shown in FIG. 2, the control device 14 includes a voice detection unit 25 that converts a received signal output from the microphone 11 into an utterance voice file, and a voice recognition processing unit that generates and outputs an utterance character file from the utterance voice file. The voice input processing unit 20 provided with 19 is activated upon receiving an input of an utterance character file, and each time an utterance character file is input, a dialogue pattern S as a dialogue attitude among a plurality of preset dialogue patterns. And a dialog management unit 22 having a response dialog system 21 for generating and outputting a dialog character file as a basis of dialog voice corresponding to the dialog pattern S.

Further, the control device 14 receives the input of the dialogue character file, creates voice data from the dialogue character file, converts it into a voice signal, and inputs it to the speaker 13, and a face that forms the face image of the character Estimate the emotion of the character from the dialogue character file by receiving the image synthesis data and the dialogue character file, create facial expression data that forms facial expressions according to the emotion, and combine the facial image synthesis data and the facial expression data And a character expression processing unit 24 that inputs the image display data to the display 12.

As shown in FIG. 3, the voice input processing unit 20 includes a voice detection unit 25 that detects a time section including a voice from the received signal output from the microphone 11 as a voice section and outputs the voice section as an utterance voice file; A transmission means 27 for inputting (transmitting) the uttered voice file to the voice recognition processing means 19 via the information communication line 26 (for example, an optical line, an ADSL line, a cable TV line, etc.), and an information communication line from the voice recognition processing means 19 Receiving means 28 for receiving and outputting an utterance character file output (transmitted) through the terminal 26.
Here, when the speech recognition processing means 19 converts an utterance voice file (utterance voice) into an utterance character file, if the sentence (character) cannot be uniquely determined for the voice, the certainty factor (the utterance character file A plurality of utterance character files are provided (output) as candidates in descending order of the probability of the utterance voice file quantitatively). Therefore, the receiving means 28 outputs the utterance character file having the maximum certainty among the plurality of output utterance character files to the dialogue management unit 22 as the utterance character file corresponding to the utterance voice file.
By providing the speech recognition processing means 19 on the cloud (Internet), a large-scale database can be connected to the speech recognition processing means 19, and hardware updates and application software updates and improvements are appropriately performed. Can do. For this reason, the voice recognition processing means 19 can perform an accurate and quick conversion from the utterance voice file to the utterance character file.

As shown in FIG. 4, the response dialogue system 21 includes a specific word registration means 29 for registering and storing a specific word that is important in selecting the dialogue attitude of the cat-type conversation robot 10, and an utterance character file. A function that determines whether or not a specific wording exists, and when there is no specific wording, whether or not the intention of the utterance character file matches the specific wording, and the intention of the utterance character file that has the specific wording When a word matches a specific wording, the specific wording is output, and when there is no specific wording or the intention of the utterance character file does not match the specific wording, a specific wording with a function to output information without a specific wording A determination unit 30 is provided.
In the following description, a case where a specific word exists in the utterance character file or a case where the intention of the utterance character file matches the specific word will be simply referred to as a case where the specific word exists in the utterance character file.

The response dialogue system 21 includes a plurality of dialogue patterns, for example, as the character of the cat that the cat-type conversation robot 10 has.
(1) A normal dialogue pattern indicating a dialogue attitude in response to a topic included in an utterance character file in response to a cat showing an obedient character,
(2) A changed topic dialogue pattern indicating a dialogue attitude that responds with a topic different from the topic of the utterance character file in response to the cat exhibiting unexpected behavior,
(3) An ignoring dialogue pattern indicating a dialogue attitude in which no response is made to a cat (in response to the input of an utterance character file) in response to the cat showing strong independence,
(4) Corresponding to the cat showing a threatening attitude, the cat that registers the four dialogue patterns of the rejection dialogue pattern indicating the dialogue attitude that causes the dialogue rejection even when talking (to the input of the utterance character file) Characteristic registration means 31 is provided. The dialogue attitude of the cat-type conversation robot 10 reflecting the character of the cat can be realized by the dialogue pattern registered in the cat characteristic registration means 31.

In the response dialogue system 21, selection probabilities for registering selection probabilities based on the character of the cat for the normal dialogue pattern, the changed topic dialogue pattern, the neglect dialogue pattern, and the rejection dialogue pattern registered through the cat characteristic registration means 31. Registration means 32 is provided.
The selection probability registration means 32 determines the ratio of selection probabilities for each dialogue pattern according to the cat's personality assumed in the cat-type conversation robot 10 when there is no specific wording in the utterance character file, and each dialogue pattern. The cat characteristic in which the selection probability of each dialogue pattern is adjusted so that the sum of the selection probabilities becomes 100% is set. Further, the selection probability registration means 32, when a specific word is present in the utterance character file, makes the selection probability of the normal dialogue pattern larger than the selection probability of other dialogue patterns, and changes the topic dialogue pattern, the ignored dialogue pattern, and the rejection A specific wording cat characteristic in which the ratio of each selection probability of the dialogue pattern is reduced is set. For example, the normal conversation pattern is less than 50% in the selection probability of the cat characteristic, and the normal interaction pattern is higher than 50%, preferably 70% or more in the selection probability of the cat characteristic for specific wording.
In addition, even if one cat characteristic for specific wording is set for a plurality of specific wordings, a plurality of specific wordings are classified into a plurality of groups (for example, the cat-type conversation robot 10 does not allow the right to select a dialogue attitude) A group of type specific words and a group of cat specific type words) may be set for each group or may be set for each specific word.

The response dialogue system 21 obtains the cat characteristic registered in the selection probability registration unit 32 when the information without the specific wording is output, and when the specific wording information is output from the specific wording determination unit 30. The selection probability acquisition means 33 for acquiring the specific wording cat characteristic registered in the selection probability registration means 32, and the selection probability of each dialogue pattern possessed by the cat characteristic or the specific wording cat characteristic acquired by the selection probability acquisition means 33 Based on the above, dialogue pattern selection means 34 is provided for selecting a dialogue pattern S when an utterance character file is input to the response dialogue system 21.
The dialogue pattern selection means 34 can determine the dialogue pattern S from, for example, a random number generated when an utterance character file is input and a selection probability of each dialogue pattern acquired by the selection probability acquisition means 33. .

For example, as the selection probability of each dialogue pattern possessed by the cat characteristic, the selection probability of the normal dialogue pattern is 40%, the selection probability of the changed topic dialogue pattern is 25%, the selection probability of the ignore dialogue pattern is 15%, and the rejection dialogue pattern is selected. Probability is set to 20% (according to cat behavior pattern analysis results).
In addition, the specific wording “call me” is an absolute obedience specific wording, the selection probability of the normal dialogue pattern is 100%, the selection probability of the changed topic dialogue pattern is 0%, the selection probability of the ignore dialogue pattern is 0%, and The rejection dialog pattern selection probability is set to 0%.
Furthermore, the specific words “Let's play” and “Let's talk” are set as cat-playing specific words, the selection probability of the normal dialogue pattern is 80%, the selection probability of the changed topic dialogue pattern is 8%, and the selection probability of the neglected dialogue pattern is 5 %, The rejection dialog pattern selection probability is set to 7%.

By setting in this way, the normal dialogue pattern is always selected as the dialogue pattern S when there is “Call Mr. XX” in the utterance character file created from the utterance voice. If the conversation for making a telephone call is established and the cat-type conversation robot 10 is provided with a telephone function, it is possible to make a call to Mr. XX via the cat-type conversation robot 10.
Further, when “Let's play” and “Let's talk” exist in the utterance character file created from the utterance voice, the selection probability of the normal dialogue pattern selected as the dialogue pattern S is 80%, and the cat-type conversation robot 10 Opportunities to enjoy dialogue with
On the other hand, when “calling”, “playing”, and “speaking” do not exist in the utterance character file created from the utterance voice of the owner of the cat-type conversation robot 10, the normal dialogue selected as the dialogue pattern S The pattern selection probability is 40%, and there is a case where the conversation with the cat-type conversation robot 10 cannot be realized (the character of the cat showing the unexpectedness, the independence, and the threatening attitude appears).

The response dialogue system 21 includes a plurality of different character files having a topic different from that of the input utterance character file, a plurality of ignored character files corresponding to dialogue ignorance, and a plurality of rejection characters corresponding to dialogue rejection. Each file is stored and output upon request (another character file when a changed topic dialogue pattern is selected, an ignored character file when an ignoring dialogue pattern is selected, or a rejection when a refusal dialogue pattern is selected. A character file database 35 (which outputs character files respectively) and an interactive response processing means 36 for generating and outputting a plurality of response character files by inputting a speech character file and another character file are provided.
The dialog response processing means 36 is arranged on the cloud (Internet) via the information communication line 26. By providing the dialogue response processing means 36 on the cloud, a large-scale database can be connected to the dialogue response processing means 36, and hardware updates and application software updates and improvements can be appropriately performed. For this reason, the dialogue response processing means 36 can create a dialogue character file having an accurate content in response to the content of the utterance character file.

The response dialogue system 21 is activated in response to the selection of the normal dialogue pattern as the dialogue pattern S, and inputs the utterance character file to the dialogue response processing means 36 on the cloud via the information communication line 26. A normal dialogue in which a plurality of response character files output from the dialogue response processing means 36 are acquired via the information communication line 26, and the response character file A is selected from the plurality of response character files and output as a dialogue character file. The means 37 and the dialogue pattern S are activated in response to the selection of the changed topic dialogue pattern, and another character file W is selected from among a plurality of different character files stored in the character file database 35, and dialogue response processing is performed. The response character file B is selected from the plurality of response character files input to the means 36 and output from the dialog response processing means 36, and the dialog character is selected. Change topic dialogue means 38 for outputting as prevent file provided.

Here, it is preferable that the dialogue response processing means 36 has a characteristic of outputting a plurality of response character files including questions related to the topic of the utterance character file in response to the input of the utterance character file. As a result, the response character file A includes a question related to the topic of the utterance character file, and the dialogue is continued in response to the question. As a result, it becomes easy for the cat-type conversation robot 10 to narrow down topics, and it is easy to continue the conversation.
It should be noted that the dialogue response processing means 36 is edited by editing the utterance character file so that the normal dialogue means 37 includes a question related to the topic of the utterance character file in the response character file A output from the dialogue response processing means 36. An editing function may be provided.

Further, the response dialogue system 21 is activated in response to the selection of the ignore dialogue pattern as the dialogue pattern S, and selects the ignore character file C from the plurality of ignore character files stored in the character file database 35. Ignore-type dialogue means 39 that outputs as a dialogue character file, and a rejection character file that is activated in response to the selection of a rejection dialogue pattern as the dialogue pattern S and is rejected from a plurality of rejection character files stored in the character file database 35 Rejection type dialogue means 40 for selecting D and outputting it as a dialogue character file is provided.
Then, the sentences included in the dialogue character files respectively output from the normal dialogue means 37, the changed topic dialogue means 38, the ignore dialogue means 39 , and the rejection dialogue means 40 are as shown in FIG. The data is output to the voice output processing unit 23 via the ending processing means 41 that performs ending processing that adds “Nyan” to the ending.

As shown in FIG. 5, the dialogue management unit 22 further includes a spontaneous utterance system 42. Then, as shown in FIG. 6, the spontaneous utterance in the system 42, high users of admiration hobby, cat's crowded by Moody your own behavior life patterns, and cat-type conversation robot 10 that the user is aware that the response ( Spontaneous utterance condition setting means 43 for setting a spontaneous utterance condition such as a requested action of cat), and a condition establishment determination means for determining whether or not the spontaneous utterance condition is satisfied and outputting a condition satisfaction signal when the condition is satisfied 44 is provided.
Further, the spontaneous utterance system 42 receives the condition establishment signal (when the spontaneous utterance condition is established), and registers and stores the spontaneous utterance character file set in the spontaneous utterance condition corresponding to the condition establishment signal in advance. When the spontaneous utterance character file database 45 and the condition establishment determination means 44 determine that the spontaneous utterance condition is satisfied, the corresponding spontaneous utterance character file 45 is extracted from the spontaneous utterance character file database 45 provided in the spontaneous utterance system 42. Spontaneous utterance means 46 for outputting as a dialogue character file is provided. As shown in FIG. 5, the sentence included in the dialogue character file output from the spontaneous utterance means 46 is subjected to voice output processing via the ending processing means 41 for performing ending processing to add “Nyan” to the ending of the sentence. Is output to the unit 23.

For example, the lower limit value of the remaining charge level of the driving battery for the cat-type conversation robot 10 is set as the spontaneous utterance condition, and the spontaneous utterance when the remaining charge level of the battery reaches the lower limit value (the spontaneous utterance condition is satisfied). “Character battery level is low” is registered as a character file and stored in the spontaneous utterance character file database 45. In this case, when the remaining charge amount detector (not shown) provided in the battery informs the condition establishment determination means 44 that the remaining charge amount of the battery has reached the lower limit value, the spontaneous utterance means 46 causes the spontaneous utterance character. The spontaneously uttered character file “battery remaining is low” is extracted from the file database 45 and is input to the ending processing means 41 as a dialogue character file and ending is processed to “battery remaining battery is low”. It is output to the audio output processing unit 23.

A scheduled date is set for each maintenance item of the cat-type conversation robot 10 as a spontaneous utterance condition, and a maintenance item such as “Today wipe your face” as a spontaneous utterance character file (when the spontaneous utterance condition is satisfied) Is the day to be received ”is stored in the spontaneous utterance character file database 45. In this case, a condition establishment signal is output by the condition establishment determination unit 44 on the corresponding day scheduled for maintenance by the calendar function provided in the cat-type conversation robot 10, and the spontaneous utterance from the spontaneous utterance character file database 45 by the spontaneous utterance unit 46. The text file “Today is the day to wipe your face” is extracted and input to the ending processing means 41 as a dialogue character file and ending to “Today is the day to have your face wiped”. 23.

The upper limit value (for example, 8 hours) of the non-input duration of the uttered voice (received signal from the microphone 11) to the voice input processing unit 20 is set as the spontaneous speech condition, and the non-input duration has reached the upper limit value As a corresponding spontaneous utterance character file, “Today we are not speaking for 8 hours” is registered and stored in the spontaneous utterance character file database 45. In this case, when it is notified to the condition establishment determination means 44 by the clock function provided in the cat-type conversation robot 10 that the uninput continuation time has reached the upper limit value, the spontaneous utterance means 46 makes a spontaneous call from the spontaneous utterance character file database 45. The utterance character file “Today we are not speaking for 8 hours” is extracted and input to the ending processing means 41 as a dialogue character file, and the ending is processed to “Today we are not speaking for 8 hours”. The data is output to the output processing unit 23.
By setting the spontaneous speech conditions as described above, it is possible to create a conversation opportunity based on the cat-type conversation robot 10 having the owner take care (request behavior).

The spontaneous utterance condition is an incoming call signal output from a telephone mounted on the cat-type conversation robot 10, and the spontaneous utterance character file corresponding to the time when the incoming signal is received (when the spontaneous utterance condition is satisfied) “It is a telephone” is registered in the spontaneous utterance character file database 45. In addition, the spontaneous utterance means 46 is searched for the name XX of the other party from the telephone number by using the telephone function, and the name of the search result is displayed in XX of “Mr. XX is a phone call” extracted from the spontaneous utterance character file database 45. Create and output a spontaneous utterance character file with XX substituted. In this case, when the output of the incoming signal is confirmed by the condition establishment determination means 44, the spontaneous speech character file “Call from Mr. XX” is extracted from the spontaneous speech character file database 45, and the conversational character is transmitted from the spontaneous speech system 42. As a file, “It is a phone call from Mr. XX” is output, and the ending processing means 41 processes the ending to “From Mr. XX, it is a phone call” and outputs it to the voice output processing unit 23.
Note that special services such as nuisance call rejection are also processed using the telephone function installed in the cat-type conversation robot 10.

When receiving an incoming signal of an e-mail transmitted via an information communication line 26 to a computer mounted on the cat-type conversation robot 10 as a spontaneous speech condition, when an incoming signal is input (when the spontaneous speech condition is satisfied) Is registered in the spontaneous utterance character file database 45 as a spontaneous utterance character file corresponding to. Note that special services such as spam mail rejection are processed using the electronic mail function. In addition, a process for outputting, as a spontaneous utterance character file, a combination of the mail text and “mail has arrived” extracted from the spontaneous utterance character file database 45 is registered in the spontaneous utterance means 46.
Therefore, when the reception of the incoming signal is confirmed by the condition establishment determining means 44, the spontaneous utterance means 46 extracts the spontaneous utterance character file “mail has arrived” from the spontaneous utterance character file database 45, and from the spontaneous utterance system 42. , A mail message text that says “mail has arrived” is created as a spontaneous utterance character file, output as a dialogue character file, ending processed by the ending processing means 41, and output to the voice output processing unit 23.
By setting the spontaneous utterance conditions as described above, the convenience of daily life of the owner of the cat-type conversation robot 10 is improved, and an opportunity for conversation with the cat-type conversation robot 10 can be created.

For example, by setting the spontaneous utterance condition at a specific time on a specific day, various processes performed in response to the spontaneous utterance condition, for example, using the schedule management function of a cat-type conversation robot that reads out a section of a book, sings Extract the schedule of today and read it out repeatedly. Tell the cat-type conversation robot 10 to speak (contents spoken in the past from the cat-type conversation robot 10 (contents of the dialogue character file input to the voice output processing unit 23)). , And the like are registered in the spontaneous utterance means 46.
Accordingly, when the spontaneous utterance condition is established by the calendar function and the clock function provided in the cat-type conversation robot 10, the spontaneous utterance character file corresponding to the spontaneous utterance is transmitted from the spontaneous utterance system 42. Is created, output as a dialogue character file, ending processed by the ending processing means 41, and output to the voice output processing unit 23.
As a result, it is possible to enjoy watching the cat-type conversation robot 10 playing alone, and to create an opportunity for conversation with the cat-type conversation robot 10.
Note that the cat-type conversation robot 10 may set an action such as turning on a television switch using a remote control function of a television receiver, for example, instead of uttering as a solo game.

As shown in FIG. 6, the dialogue management unit 22 records a dialogue character file output from the response dialogue system 21 and input to the ending processing means 41 and a dialogue character file output from the spontaneous utterance system 42. A file database 47 is provided. Furthermore, it is activated in response to the establishment of a spontaneous utterance condition that allows the cat-type conversation robot 10 to speak to itself, and a dialogue character file stored in the dialogue character file database 47 is arbitrarily selected to the spontaneous utterance character file database 45. An interactive character file extracting means 48 having a function of inputting is provided. As a result, it is possible to easily create a spontaneously uttered character file when the cat-type conversation robot 10 speaks alone.

As shown in FIG. 7, the voice output processing unit 23 generates voice data from the dialogue voice file, converts the dialogue character file into a dialogue voice file, converts the dialogue data into a voice signal, and outputs the voice signal to the speaker 13. Audio conversion means 50. Thereby, the cat-type conversation robot 10 can receive the user's utterance voice and utter the conversation voice, and can utter the conversation voice to the user when the spontaneous utterance condition is satisfied.

As shown in FIG. 8, the character expression processing unit 24 provided in the control device 14 stores a facial image database that stores a plurality of prepared cat facial images and image element data groups that form the animated facial images. 51 and a plurality of anime face images of cats (for example, normal facial expressions of cats) are extracted from the face image database 51 and displayed on the display 12, and a character is selected by selecting one specific anime face image R by the user. A face image selection means 52 to be set as a face image, and an image composition means 53 for extracting an image element data group for a specific anime face image R from the face image database 51 and outputting it as face image composition data. Yes.
Further, the character facial expression processing unit 24 estimates the emotion of the character from the dialogue character file output from the dialogue management unit 22, and creates emotional expression data 54 that forms facial expression data corresponding to the emotion. Image display means 55 for generating image display data for forming a facial expression at the time of dialogue of the character by combining the synthesized data and the facial expression data and outputting it to the display 12 is provided.

The emotion estimation means 54 is provided with an emotion database in which psychological states (relationships of various feelings such as pleasure, discomfort, joy, anger, sadness, etc.) are associated with a plurality of sentences P, respectively. In addition, the emotion estimation means 54 uses the psychological state and facial expression change amount (the position of each part forming a normal facial expression as a reference position, and the change direction and change from the reference position for each part of the face. A facial expression database created by seeking the correspondence relationship of (distance) is provided.
For this reason, when a dialogue character file is input to the emotion estimation means 54, a sentence P having the same meaning as the sentence T included in the dialogue character file is extracted from the database, and the psychological state of the extracted sentence P is expressed as the sentence T. Estimate the emotion of (dialog character file). When the purpose of the sentence T is composed of a combination of a plurality of sentences P, each sentence P constituting the purpose of the sentence T is extracted and the contribution rate (weighting rate) of each sentence P is calculated. The sum of the corrected psychological states obtained by adjusting the psychological state of P by the contribution rate is estimated as the emotion of the sentence T (dialog character file).

Then, when the emotion of the sentence T included in the dialogue character file is estimated, a facial expression change amount that matches or is most similar to the estimated emotional psychological state (sum of the corrected psychological state) is extracted in the facial expression database, The extracted facial expression change amount is used as facial expression data of the sentence T.
When the dialogue character file is not input to the character facial expression processing unit 24, that is, when facial expression data is not created, the image display data matches the facial image composite data, and therefore a specific animated facial image R (normally on the display 12). Is displayed.
When emotion cannot be estimated from the dialogue character file input to the character expression processing unit 24, for example, in the case of onomatopoeia, the expression state when the onomatopoeia is generated is set as face expression data.
As a result, the cat-type conversation robot 10 can perform a conversation while changing the facial expression of the character.

As shown in FIG. 9, the cat-type conversation robot 10 includes a camera device 57 that performs face authentication based on processing and analysis of an image obtained by a camera 56 (an example of another imaging unit), and a camera device 57 that obtains the face. A monitor display device 58 used as a touch panel for displaying various images and making various settings of the cat-type conversation robot 10, and a human sensor device 60 for checking the presence of the user via the human sensor 59 are provided. ing.
Further, the cat-type conversation robot 10 is provided with a user information database 61 for registering information on the user and related persons (for example, face images of the user and related persons, names of persons concerned, telephone numbers, addresses, etc.). It has been. The user information database 61 is also used by the dialog response processing means 36 via the information communication line 26 as necessary.

When the cat-type conversation robot 10 is provided with the camera 56 and the camera device 57, a person concerned of the user uses a display device 62 provided at a separate location to recognize the owner's behavior, visit an outsider, etc. Monitoring can be performed.
When the human-type sensor device 60 is provided in the cat-type conversation robot 10, a person concerned with the user can use the display device 62 to check the user's occupancy and watch it.
Furthermore, if the cat-type conversation robot 10 is provided with a monitor display device 58, for example, a warning or warning information such as “the battery level is low” will be displayed to the user. In addition to voice, contact information such as can be displayed and notified.

Here, when the monitor display device 58 is connected to the dialogue management unit 22 of the control device 14, the dialogue character file can be displayed on the monitor display device 58 as necessary, and the user can interact with the cat-type conversation robot 10. Voice can be confirmed as text. Further, when the monitor display device 58 is connected to the voice input processing unit 20 of the control device 14, the utterance character file can be displayed on the monitor display device 58 as necessary, and the user can recognize the voice of the cat-type conversation robot 10. Can be confirmed as a character. The monitor display device 58 can be connected to the voice input processing unit 20 and the dialogue management unit 22, respectively, and the monitor display device 58 may also be used as the display 12.

The operation of the cat-type conversation robot 10 according to the first embodiment of the present invention will be described.
Prior to dialogue with the cat-type conversation robot 10, a plurality of dialogue attitudes (normal dialogue pattern, changed topic dialogue pattern, ignored dialogue pattern, and (Rejection dialogue pattern) each selection probability is set, and one specific anime face image R is selected from a plurality of cat face animation images prepared in advance and set as a character face image (interaction above). Pre-step).

As shown in FIG. 10, when the cat-type conversation robot 10 is activated to perform a conversation, the facial expression composite data of a specific anime face image R is output from the character expression processing unit 24 to the display 12, and the character of the character is displayed on the display 12. A face image is displayed. Then, the voice input processing unit 20 receives the user's uttered voice and creates an uttered voice file, and the uttered voice file is input to the voice recognition processing means 19 and converted into an uttered character file and output (dialogue step 1). .
As shown in FIG. 9, when the monitor display device 58 is connected to the voice input processing unit 20 of the control device 14, the utterance character file can be displayed on the monitor display device 58.

In response to the input of the output utterance character file, a dialogue pattern S is selected from a plurality of preset dialogue patterns to determine the dialogue attitude (dialogue step 2), and the response character file corresponding to the dialogue pattern S Any one of A, B, the ignored character file C, and the rejected character file D is output as a dialogue character file (dialogue step 3). The output dialogue character file is input to the voice output processing unit 23 and the character expression processing unit 24. The voice output processing unit 23 outputs a voice signal obtained by converting the voice data formed from the dialogue character file to the speaker 13. The facial expression data corresponding to the emotion is generated from the character facial expression processing unit 24 by estimating the emotion of the character, and is displayed on the display 12 as image display data that forms the facial facial expression during the dialogue of the character in combination with the facial image synthesis data. Is output (dialogue step 4). As a result, the facial image of the character displayed on the display 12 can change the facial expression during the dialogue in synchronization with the dialogue voice emitted from the speaker 13.
As shown in FIG. 9, when the monitor display device 58 is connected to the dialogue management unit 22 of the control device 14, the dialogue character file can be displayed on the monitor display device 58.

In the selection of the dialogue pattern S in the dialogue step 2, as a plurality of dialogue patterns, a normal dialogue pattern indicating a dialogue attitude in response to a topic included in the utterance character file (when the cat shows obedience), and an utterance character file include Changed topic dialogue pattern (when cat shows unexpected behavior) that shows dialogue attitude that responds with a topic different from the topic that it has, and ignore dialogue pattern that shows dialogue attitude that becomes unresponsive by input of utterance character file ( And a rejection dialogue pattern (when the cat shows a threatening attitude toward the owner) indicating a dialogue attitude that causes dialogue rejection by inputting the utterance character file. The selection probability is set based on the character of the cat in each of the normal dialogue pattern, the changed topic dialogue pattern, the ignored dialogue pattern, and the rejection dialogue pattern, and the dialogue pattern S is changed to the normal dialogue pattern, the changed topic dialogue pattern, the ignored dialogue pattern, And the character of the cat is made to appear naturally by making the rejection dialogue pattern stochastically selected.

In dialogue step 3, as shown in FIG. 11, when a normal dialogue pattern is selected, response characters selected from a plurality of response character files output from dialogue response processing means 36 to which an utterance character file has been inputted. File A is output as an interactive character file.
When the changed topic dialogue pattern is selected, another character file W having a topic different from that of the utterance character file is selected from the character file database 35, and the dialogue response process in which the different character file W is input. The response character file B selected from the plurality of character files output from the means 36 is output as an interactive character file.
When the ignore dialogue pattern is selected, the ignore character file C corresponding to the ignore dialogue selected from the character file database 35 is output as a dialogue character file.
When the rejection dialogue pattern is selected, the rejection character file D corresponding to the dialogue rejection selected from the character file database 35 is output as a dialogue character file.
Thereby, the dialogue which expressed the character of the cat concretely is realizable.

For example, when the user utters “tell me today's weather”, an utterance voice file is created from the received signal in the voice input processing unit 20, and the utterance voice file is input to the voice recognition processing means 19 via the information communication line 26. Is done. Then, the spoken character file created by the voice recognition processing means 19 is output to the voice input processing unit 20 via the information communication line 26. Next, the spoken character file is input from the voice input processing unit 20 to the dialogue management unit 22.

In the dialogue management unit 22, since the utterance character file is input, the response dialogue system 21 is activated. First, it is determined whether or not a specific word registered in the utterance character file exists. Since there is no specific wording in "Tell me today's weather", the dialog pattern selection probability is 40% for the normal dialogue pattern, 25% for the changed topic dialogue pattern, 15% for the ignore dialogue pattern, and the rejection dialogue pattern 20%.

When a normal dialogue pattern is selected as the dialogue pattern S, the utterance character file is input to the dialogue response processing means 36 via the information communication line 26, and the dialogue response processing means 36 interprets the intention of the utterance character file. Then, for example, a weather search is performed on the Internet, and a plurality of response character files including the weather search result are created and output to the dialog management unit 22 via the information communication line 26. In the dialogue management unit 22, the response character file A contains a question related to the topic of the utterance character file from among the plurality of received response character files, for example, “Sunny. The dialog character file is selected. Then, it is output from the dialogue management unit 22 to the voice output processing unit 23 and the character facial expression processing unit 24 as “It is sunny.

The voice output processing unit 23 forms a dialog voice file from “It is sunny, isn't going anywhere”, converts voice data created from the dialog voice file into a voice signal and outputs it to the speaker 13. At this time, when the emotion of the character estimated from the dialogue character file by the character facial expression processing unit 24 is an emotion that is likely to be desired, facial expression data corresponding to this emotion is created and combined with the facial image synthesis data during character dialogue. It is output to the display 12 as image display data forming a facial expression. In this way, the facial expression of the character displayed on the display 12 can be changed to a greedy expression in synchronization with the dialogue voice “Sunny weather, not going somewhere” emitted from the speaker 13. .

When the changed topic dialogue pattern is selected as the dialogue pattern S, another character file W of a topic different from the topic of the utterance character file (tell me today's weather) is selected from the character file database 35, and another character file is selected. When the response character file B selected from the plurality of response character files output from the interactive response processing means 36 to which W is input is, for example, “Hungry is empty”, the interactive character file is “Hungry. " Then, the dialogue management unit 22 outputs “Hungry Nyan” as a dialogue character file to the voice output processing unit 23 and the character expression processing unit 24.

The voice output processing unit 23 forms a dialogue voice file from “Hungry Nyan”, converts voice data created from the dialogue voice file into a voice signal, and outputs the voice signal to the speaker 13. At this time, when the emotion of the character estimated from the dialogue character file by the character facial expression processing unit 24 is an unpleasant emotion, facial expression data corresponding to this emotion is created and combined with the facial image synthesis data during the character dialogue. It is output to the display 12 as image display data forming a facial expression. Thus, the facial expression of the character displayed on the display 12 can be changed to an unpleasant expression in synchronization with the dialogue voice “Hungry Nyan” emitted from the speaker 13.

When the ignore dialogue pattern is selected as the dialogue pattern S, if the ignore character file C corresponding to the ignore dialogue selected from the character file database 35 is, for example, “I don't know”, the dialogue character file is “I don't know”. It becomes. Then, “not knowing Nyan” is output from the dialogue management unit 22 to the voice output processing unit 23 and the character expression processing unit 24 as a dialogue character file.

The voice output processing unit 23 forms a dialogue voice file from “don't know”, converts voice data created from the dialogue voice file into a voice signal, and outputs the voice signal to the speaker 13. At this time, if the character's emotion estimated from the dialogue character file by the character facial expression processing unit 24 is a painful emotion, facial expression data corresponding to this emotion is created and combined with the facial image synthesis data, It is output to the display 12 as image display data for forming a facial expression. Thereby, the facial expression of the character displayed on the display 12 can be made into a troublesome expression in synchronization with the dialogue voice “I don't know” uttered from the speaker 13.

When the rejection dialogue pattern is selected as the dialogue pattern S, if the rejection character file D corresponding to the dialogue rejection selected from the character file database 35 is, for example, “Sher, My-Oh”, the dialogue character file is “ "Sher, Myoo". Then, “sher, my oo” is output as a dialog character file from the dialog management unit 22 to the voice output processing unit 23 and the character expression processing unit 24 (since “sher” and “my oo” are not sentences, The ending processing means 41 does not act).

The voice output processing unit 23 forms a dialogue voice file from “Sher, My-Oh”, converts voice data created from the dialogue voice file into a voice signal, and outputs the voice signal to the speaker 13. At this time, the emotion of the character cannot be estimated from the dialogue character file input to the character expression processing unit 24. For this reason, the expression state at the time of issuing “Sher, Myoo” becomes the facial expression data of the character, and is output to the display 12 as image display data that forms the facial expression at the time of dialogue of the character in combination with the facial image synthesis data. The Accordingly, the facial expression of the character displayed on the display 12 can be changed in synchronization with the dialogue voice “Sher, My-Oh” emitted from the speaker 13.

As shown in FIG. 12, in the cat-type conversation robot 10, a plurality of spontaneous utterance conditions (for example, life patterns and required behaviors) are set in the spontaneous utterance condition setting means 43, and a spontaneous utterance character file is set for each spontaneous utterance condition. It is set in advance and stored in the spontaneous utterance character file database 45.
Then, when the cat-type conversation robot 10 is activated, the facial expression composite data of the specific anime facial image R is output from the character facial expression processing unit 24 to the display 12, and the facial image of the character is displayed on the display 12 (spontaneous speech Step 1).

The condition establishment determination means 44 confirms whether or not the conditions are established among a plurality of spontaneous utterance conditions (spontaneous utterance step 2), and the spontaneous utterance character file corresponding to the spontaneous utterance conditions for which the spontaneous utterance conditions are established is the spontaneous utterance means. 46 is extracted from the spontaneous utterance character file database 45 and output as a dialogue character file (spontaneous utterance step 3). The output dialogue character file is input to the voice output processing unit 23 and the character expression processing unit 24. The voice output processing unit 23 converts the dialogue character file into a dialogue voice file, and is formed from the dialogue voice file. A voice signal obtained by converting the voice data is output to the speaker 13, and the facial expression data corresponding to the emotion is generated from the character facial expression processing unit 24 by estimating the emotion of the character. Is output to the display 12 as image display data forming the facial expression (spontaneous speech step 3).
As a result, the facial image of the character displayed on the display 12 can change the facial expression during the dialogue in synchronization with the dialogue voice emitted from the speaker 13.

By selecting the spontaneous utterance condition, the character of the cat can be characterized. For example, the cat-type conversation robot 10 can perform a dialogue corresponding to the slipping and sweetness of the cat.
Further, various information is acquired from the user information database 61, and the cat-type conversation robot 10 is made to talk about a topic that matches the user's preference and taste of the cat-type conversation robot 10, or the cat-type conversation robot 10 It is possible to make a remark requesting something, and to create an opportunity for conversation with the cat-type conversation robot 10 and for taking care of the cat-type conversation robot 10.

As shown in FIG. 13, the cat-type conversation robot 63 according to the second embodiment of the present invention is watched by the user as a spontaneous utterance condition as compared with the cat-type conversation robot 10 according to the first embodiment. The spontaneous utterance character file set for the watching start condition constitutes a specific question based on the personal information of the user. In addition to the input processing unit 20, the dialogue management unit 22, the voice output processing unit 23, and the character expression processing unit 24, the correctness of the user's answer to the specific question is determined, and a first abnormality signal is output when an erroneous answer occurs. A feature is that a first alarm unit 65 is provided to output to a registered person registered in advance.

Furthermore, the cat-type conversation robot 63 emits a dialogue voice each time a dialogue voice is produced in the preset time zone, compared to the cat-type conversation robot 10 according to the first embodiment. The waiting time until the uttered voice is received by the microphone 11 is measured, and whether or not a response state change occurs in which the deviation between the user's reference waiting time and the waiting time determined in advance exceeds a set allowable value is determined. A second alarm that outputs a second abnormality signal when the cumulative number of occurrences of response state changes after the first dialogue is established with the user reaches a preset abnormal response determination value Unit 66 and a certainty factor quantitatively indicating the certainty of the utterance character file output from the voice input processing unit 20 to the dialogue management unit 22 is obtained, and the certainty factor is equal to or less than a preset abnormality certainty factor. When A third alarm unit 67 is provided for detecting whether or not a low certainty state has occurred and outputting a third abnormality signal when the cumulative number of occurrences of the low certainty state reaches a preset abnormal cumulative number. It is a feature.
For this reason, with regard to the cat-type conversation robot 63, the same components and means as those of the cat-type conversation robot 10 are denoted by the same reference numerals and description thereof is omitted, and the first to third alarm units 65 to 67 are omitted. Only explained.

As shown in FIG. 14, the first alarm unit 65 is provided in the answer information storage means 68 storing correct answer information for the spontaneous utterance character file (specific question) set for each watching start condition, and the spontaneous utterance system 42. The specific condition set for the watch start condition that has been confirmed to be activated is activated upon receipt of a condition fulfillment signal that is output when the watch start condition that has been confirmed to be fulfilled by the established condition fulfillment judging means 44. Acquire correct answer information from the answer information storage means 68 and confirm the correctness by comparing the contents of the utterance character file created by inputting the received signal of the user's utterance voice (answer related to the specific question) to the voice input processing unit 20 Determining means 69 and a first abnormality output means 70 for outputting a first abnormality signal to a related person when the determination means 69 determines that the answer is incorrect. Note that the first abnormal signal is output to the person concerned via the information communication line 26.

The watching start condition for performing the watching of the user is, for example, from the start of the dialog with the cat-shaped conversation robot 63 (for example, from the start time set in the time zone when the user wakes up) until the dialog ends (for example, It is set to occur at least once during the period until the end time set in the time when the user goes to bed.
The specific question based on the user's personal information is, for example, a user's name, date of birth, parent, sibling, or child name, a question related to a password that has been confirmed in advance, and a plurality of questions are prepared in advance, When one is established, one is arbitrarily extracted through the spontaneous utterance means 46 . For the user, the specific question is a content that can be easily answered correctly, so the correct answer rate is usually 100%. Therefore, if an erroneous answer occurs in response to a specific question, the person concerned receives the first abnormality signal, can notice the user's physical condition change (early abnormality), and take appropriate measures to the user. Is possible.

As shown in FIG. 14, the second alarm unit 66 outputs the output time when the voice signal of the dialogue voice is output from the voice output processing unit 23 and the reception signal of the user's utterance voice in response to the dialogue voice. A standby time detection unit 71 is provided for detecting the input time when the input signal is input to the input processing unit 20 and obtaining the time difference between the input time and the output time to obtain the standby time. Further, the second alarm unit 66 calculates the standby time distribution by measuring the standby time of the user in the normal state a plurality of times in advance, calculates the average value of the standby time and the standard deviation σ, and calculates the average value of the standby time. Reference data forming means 72 for storing a reference waiting time, a value (3σ) three times the standard deviation σ as an allowable value, a waiting time obtained from the waiting time detecting means 71, and a reference waiting time obtained from the reference data forming means 72 After the first dialogue with the user is established, the number of occurrences of response state changes is detected by detecting the occurrence of response state changes exceeding the allowable value. And a second abnormality output means 73 for outputting a second abnormality signal to the concerned person when the accumulated number reaches the set abnormal response determination value. Note that the second abnormal signal is output to the person concerned via the information communication line 26.

The waiting time until the user speaks and responds from the robot side also changes depending on the content of the dialogue, so the waiting time distribution obtained by conducting various dialogues with the user in the normal state is the same as that of the user in the normal state. This is considered to be a standard for quantitatively evaluating the response state. Each standby time constituting the standby time distribution is almost in the range where the reference standby time −3σ is the lower limit and the reference standby time + 3σ is the upper limit. Therefore, if the deviation obtained from the standby time obtained from the standby time detection means 71 is in the range of the reference standby time −3σ to the reference standby time + 3σ, it is determined that no abnormality has occurred in the user. On the other hand, if the deviation is outside the range of the reference standby time −3σ to the reference standby time + 3σ, it is determined that an abnormality has occurred in the user, and the second abnormality signal is output. By receiving this, it is possible to realize that an abnormal dialog response state has occurred in the user, that is, that the user has a change in physical condition (abnormality), and it is possible to perform appropriate measures on the user. Become.
When an abnormality occurs in the user, the user's dialogue response state is in a lowered state, so that the standby time obtained from the standby time detection means 71 becomes long, and the deviation exceeds the reference standby time + 3σ. .

As shown in FIG. 14, the third alarm unit 67 acquires the certainty factor of the utterance character file output from the voice input processing unit 20 to the dialogue management unit 22 from the voice input processing unit 20. have. Further, the third alarm unit 67 obtains and obtains, in advance, a certainty degree evaluated by the voice input processing unit 20 (voice recognition processing means 19) for various utterance voice files (uttered voices) of the user in the normal state. A certainty factor distribution is created from the certainty factor, a minimum value is obtained, an abnormality certainty factor setting unit 75 that sets and stores a value smaller than the minimum value as an abnormal certainty factor, and a certainty factor obtaining unit 74. Is compared with the abnormality certainty degree acquired from the abnormality certainty degree setting means 75, the presence or absence of a low certainty state where the certainty degree is equal to or less than the abnormal certainty degree is detected, and the cumulative number of occurrences of the low certainty state is calculated. And a third abnormality output means 76 for outputting a third abnormality signal to the concerned person when the accumulated number reaches the abnormality accumulation number.
Here, for a value smaller than the minimum value, for example, a plurality of certainty distributions are obtained, the minimum value of each certainty distribution is extracted, and a minimum value distribution composed of the extracted minimum values is obtained. The estimated minimum value estimated from the obtained minimum value distribution can be used. Note that the third abnormal signal is output to the person concerned via the information communication line 26.

If the creation method of the utterance character file in the voice input processing unit 20 is fixed, the same utterance character file is always obtained with the same certainty factor for the same utterance voice file (utterance voice), so that the user in the normal state When interacting with the cat-shaped conversation robot 63, the certainty factor when the utterance character file is created from the user's utterance voice is within the range of the certainty factor distribution created by the abnormality certainty factor setting means 75, The value always exceeds the certainty of abnormality.
On the other hand, when an abnormality occurs in the user, the user's dialog state changes, so the confidence level when the utterance character file is created from the user's uttered voice is lowered, and a low confidence level state that is equal to or lower than the abnormal confidence level occurs. Will do. Then, when the cumulative number of occurrences of the low confidence state occurring in the user reaches the abnormal cumulative number, the third abnormal output means 76 outputs a third abnormal signal to the related person, and the related person receives the third abnormal signal. By receiving this, it is possible to notice a change in the physical condition of the user (early abnormality), and it is possible to perform an appropriate treatment on the user.

As described above, the present invention has been described with reference to the embodiment. However, the present invention is not limited to the configuration described in the above-described embodiment, and the matters described in the scope of claims. Other embodiments and modifications conceivable within the scope are also included.
Furthermore, the present invention includes a combination of components included in the present embodiment and other embodiments and modifications.
In the cat-type conversation robot according to the second embodiment of the present invention, the first to third alarm units are provided, but any one of the first to third alarm units, or any two Combinations may be provided.

10: Cat-shaped conversation robot, 11: Microphone, 12: Display, 13: Speaker, 14: Control device, 15: Camera, 16: Display position adjustment unit, 17: Correction data calculator, 18: Movable holding base, 19: Voice recognition processing means, 20: voice input processing section, 21: response dialogue system, 22: dialogue management section, 23: voice output processing section, 24: character expression processing section, 25: voice detection means, 26: information communication line, 27: Transmission means, 28: Reception means, 29: Specific word registration means, 30: Specific word determination means, 31: Cat characteristic registration means, 32: Selection probability registration means, 33: Selection probability acquisition means, 34: Dialog pattern Selection means, 35: character file database, 36: dialogue response processing means, 37: normal dialogue means, 38: change topic dialogue means, 39: ignore dialogue means, 40: rejection Type dialogue means, 41: ending processing means, 42: spontaneous utterance system, 43: spontaneous utterance condition setting means, 44: condition establishment determination means, 45: spontaneous utterance character file database, 46: spontaneous utterance means, 47: dialogue character file Database: 48: Dialogue character file extraction means, 49: Speech synthesis means, 50: Speech conversion means, 51: Face image database, 52: Face image selection means, 53: Image composition means, 54: Emotion estimation means, 55: Image Display means, 56: camera, 57: camera device, 58: monitor display device, 59: human sensor, 60: human sensor device, 61: user information database, 62: display device, 63: cat-type conversation robot, 64: control device, 65: first alarm unit, 66: second alarm unit, 67: third alarm unit, 68: answer information storage unit, 69: determination unit, 70 1st abnormality output means, 71: Standby time detection means, 72: Reference data formation means, 73: 2nd abnormality output means, 74: Certainty factor acquisition means, 75: Abnormal certainty degree acquisition means, 76: Third Abnormal output means

Claims (14)

Have the ego, such as the pseudo-pet, a cat-type conversation robot with the personality of the cat to change the dialogue attitude to the time it receives the speech of the speaker,
Voice input means for receiving the uttered voice and outputting a received signal;
A display means for displaying a face image at the time of dialogue of the character set as a dialogue person on the robot side;
Voice output means for generating dialogue voice for the speaker;
Image display data for changing the facial expression of the character's facial image during dialogue while creating voice data forming the dialogue voice based on the dialogue attitude set in response to the received signal and inputting the voice data into the voice output means create and have a control device to be input to the display means,
The control device
(1) a voice input processing unit that converts the received signal output from the voice input means into an utterance voice file, creates an utterance character file from the utterance voice file, and outputs the utterance character file;
(2) a dialogue management unit that receives the input of the spoken character file and creates and outputs a dialogue character file that is a basis of the dialogue voice;
(3) a voice output processing unit that receives input of the dialogue character file, forms the voice data from the dialogue character file, converts the voice data into a voice signal, and inputs the voice signal to the voice output means;
(4) Facial facial expression that forms facial expression in accordance with the emotion image synthesis data that forms the facial image of the character and the dialogue character file in response to the input of the dialogue character file. Character expression processing unit that creates data and inputs the combined image of the face image and the facial expression data to the display means as the image display data
And
The dialogue management unit arbitrarily selects a dialogue pattern S as the dialogue attitude from among a plurality of preset dialogue patterns each time the utterance character file is input, and the dialogue corresponding to the dialogue pattern S It has a response dialogue system that outputs a character file and a spontaneous speech system,
In the spontaneous utterance system,
(1) Spontaneous speech conditions including at least one of the hobby of the speaker, a life pattern incorporating a cat's unique behavior, and the requested behavior of the cat-type conversation robot that the speaker is aware of responding in advance. A spontaneous utterance condition setting means to be set;
(2) Condition establishment determining means for outputting a condition satisfaction signal when the spontaneous utterance condition set by the spontaneous utterance condition setting means is established;
(3) Spontaneous utterance means for receiving the condition establishment signal and outputting the spontaneous utterance character file set in the spontaneous utterance condition corresponding to the condition establishment signal as the dialogue character file
And
The spontaneous utterance condition setting means is further provided with a watch start condition for executing the watch of the speaker as the spontaneous utterance condition, and the watch start condition is determined from a start time set in a time zone when the speaker wakes up. The spontaneous utterance character file set for the watch start condition is set to occur at least once before the end time set in the time period when the speaker goes to bed, and the personal information of the speaker is stored in the personal information of the speaker. cat type conversation robot, characterized in der Rukoto constitutes a specific question based. 2. The cat-type conversation robot according to claim 1, further comprising imaging means for photographing the speaker, and the control device uses the speaker's image obtained by the imaging means to display the display means. A cat-type conversation robot characterized in that a display position adjustment unit is provided for adjusting the direction of the display surface of the character so that the face image of the character displayed on the display surface faces the speaker. 3. The cat-type conversation robot according to claim 1, wherein the character's face image is a cat's anime face image. The cat-type conversation robot according to any one of claims 1 to 3 , wherein the plurality of interaction patterns are:
(1) a normal dialogue pattern indicating the dialogue attitude in response to a topic included in the utterance character file;
(2) a changed topic dialogue pattern indicating the dialogue attitude to respond with a topic different from the topic of the utterance character file;
(3) an ignoring dialogue pattern indicating the dialogue attitude that makes no response to the input of the utterance character file;
(4) A cat-type conversation robot characterized by having a rejection dialogue pattern indicating the dialogue attitude that causes dialogue rejection with respect to input of the utterance character file. 5. The cat-type conversation robot according to claim 4 , wherein selection probabilities based on a character of a cat are set in advance for each of the normal conversation pattern, the changed topic conversation pattern, the ignore conversation pattern, and the rejection conversation pattern. A cat-type conversation robot characterized by that. 6. The cat-type conversation robot according to claim 5 , wherein a specific word registered in advance exists in the utterance character file, and when the utterance character file including the specific word is input, the normal conversation pattern A cat-type conversation robot characterized in that the selection probability is set higher than 50%. The cat-type conversation robot according to claim 6 , wherein the response dialogue system includes:
(1) A plurality of separate character files having a topic different from that of the input speech character file, a plurality of ignored character files corresponding to dialogue ignorance, and a plurality of rejection character files corresponding to dialogue refusal, respectively. Character file database to store and output on demand,
(2) Dialog response processing means for creating and outputting a plurality of response character files by inputting the spoken character file and the separate character file,
(3) a normal dialogue unit that selects a response character file A from the plurality of response character files output from the dialogue response processing unit by inputting the utterance character file and outputs the selected response character file as the dialogue character file;
(4) Selecting the different character file W from the plurality of different character files stored in the character file database, inputting the selected character file W to the dialogue response processing means, and outputting the plurality of responses output from the dialogue response processing means A change topic type dialogue means for selecting a response character file B from a character file and outputting it as the dialogue character file;
(5) Ignore interaction means for selecting an ignore character file C from the plurality of ignore character files stored in the character file database and outputting the selected ignore character file as the dialog character file;
(6) A cat having rejection type dialogue means for selecting a rejection character file D from the plurality of rejection character files stored in the character file database and outputting it as the dialogue character file. Type conversation robot. 8. The cat-type conversation robot according to claim 7 , wherein the voice input processing unit includes voice detection means for creating the utterance voice file from the received signal, and voice recognition for creating and outputting the utterance character file from the utterance voice file. Processing means,
The speech recognition processing means and the dialogue response processing means are each provided on a cloud, and input the utterance speech file to the speech recognition processing means, output of the utterance character file from the speech recognition processing means, and the utterance character The file and the input of the separate character file W to the dialogue response processing means, and the output of the response character file from the dialogue response processing means to the normal type dialogue means and the changed topic type dialogue means are respectively via information communication lines. Cat-type conversation robot characterized by 9. The cat-type conversation robot according to claim 8 , wherein the response character file A includes a question related to the topic of the utterance character file. In cats type conversation robot according to any one of claims 1-9, in the prior SL controller, first when said determining the correctness of a speaker of the answer to a specific question, erroneous answer occurred 1 A cat-type conversation robot characterized in that a first alarm unit for outputting an abnormal signal is provided. The cat-type conversation robot according to any one of claims 1 to 10 , wherein the spontaneous utterance character file is created in advance for each spontaneous utterance condition, and is stored in the spontaneous utterance character file database provided in the spontaneous utterance system. Cat-type conversation robot characterized by being stored. The cat-type conversation robot according to any one of claims 1 to 11 , wherein a sentence included in the dialogue character file is subjected to ending processing means for performing ending processing to add "Nyan" to the ending of the sentence. A cat-type conversation robot that is output to the voice output processing unit. The cat-type conversation robot according to any one of claims 1 to 12 , wherein the control device is configured to generate the conversation voice after the conversation voice is produced each time the conversation voice is produced in a preset time zone. The waiting time until the uttered voice is received by the input means is measured, and the occurrence of a response state change in which the deviation between the reference waiting time of the speaker and the waiting time obtained in advance exceeds a set allowable value And the second abnormal signal is output when the cumulative number of occurrences of the response state change after the first dialogue with the speaker reaches the preset abnormal response determination value. A cat-type conversation robot characterized in that a second alarm unit is provided. The cat-type conversation robot according to any one of claims 1 to 13 , wherein the controller is configured to confirm whether the utterance character file output from the voice input processing unit to the dialogue management unit is the utterance voice file. A certainty factor that quantitatively indicates the likelihood is acquired, the presence / absence of a low certainty state in which the certainty factor is equal to or lower than a preset abnormality certainty factor is detected, and the cumulative number of occurrences of the low certainty state is preset. A cat-type conversation robot characterized in that a third alarm unit is provided for outputting a third abnormality signal when the accumulated number of abnormalities is reached.

Images