KR20060049041A - Interactive robot pet - Google Patents

Abstract

Even if there are limitations on the number of phonetic phrases or the number of waiting phrases, the interactive pet robot that provides a new interactive pet robot capable of facilitating conversation has a control unit 9 which performs processing according to the description of the program read out from the storage unit. The program defines the progression of conversation with the user as a branch, and describes the contents of a question, a plurality of options to answer the questions, and an action for each of the options. When the content of the question is output in voice, a plurality of choices corresponding to the question are displayed on the display 3 as candidates for the answer to the question. When one of the plurality of options displayed on the display 3 is pronounced by the user, voice recognition is performed to specify one option corresponding to the user's pronunciation, and to perform an action corresponding to the one option. Respond to the answer as an interactive pet robot's next reaction.

Interactive Pet Robot, Conversation, Voice Output, Display, Voice Recognition

Description

Interactive Pet Robot {INTERACTIVE ROBOT PET}

1 is an external front view of an interactive pet robot.

2 is an external side view of an interactive pet robot.

3 is a control block diagram of an interactive pet robot.

4 is a flowchart showing the flow of painting.

5 is a diagram illustrating a display example of an option that is a candidate for an answer to a question.

[Description of Codes for Main Parts]

1 Interactive Pet Robot 2 Robot Body

2a torso 3 display

4 microphone 5 person sensor

6 forehead touch sensor 7 switch

8 Speakers 9 Controls

10 Voice recognition unit 11 Main control unit

12 masks ROM 13 SRAM

14 Externally Mounted ROM

Patent Document 1: Japanese Patent Application Laid-Open No. 2002-351305

The present invention relates to an interactive pet robot, and more particularly to a pet robot suitable for language learning.

Background Art Conventionally, an interactive pet robot that communicates with a user is known, and as one kind thereof, it is also known to be used for learning English conversational language. In addition, Patent Literature 1 below discloses a language training robot that includes a speech recognition engine and translates a spoken native language into a foreign language. The robot has an exterior shape that mimics the shape of a duck or penguin, and its head is provided with a display screen. The facial expressions (eyes, noses and mouths) of the face are displayed on the display screen, and the displayed facial expressions change as if the translated facial expressions are shuffled in accordance with the speech of the translated language.

By the way, in such an interactive pet robot, how to promote without congestion with a user becomes an important point in improving product purchasing power. To this end, it is considered that the number of pronunciation phrases pronounced by the robot and the number of atmospheric phrases that the robot can hear increase the degree of freedom of conversation. In this case, however, in addition to the need for a high speed microcomputer to recognize the user's pronunciation, the size of the program is enormous, which makes it very difficult to produce a low-cost band. On the other hand, in the conventional relatively low-cost product, the pronunciation of the user is often not recognized because of the above-mentioned limitation of the number of phrases, and the conversation is easily stagnated. As a result, there has been a problem in that the communication between the interactive pet robot and the user is directed.

This invention is made | formed in view of such a situation, The objective is to provide the new interactive pet robot which can promote a conversation, even if there is a restriction of the number of phonetic phrases and a waiting phrase.

In addition, another object of the present invention is to increase the communication feeling with the interactive pet robot, and to maintain the user's desire to learn.

In order to solve this problem, according to the first aspect of the present invention, the interactive pet robot is a character robot body, a microphone mounted on the robot body, a speaker mounted on the robot body, and a robot mounted on the robot body. It has a display, a storage unit that stores a program, and a control unit that performs processing in accordance with the description of a program built into the robot body and read from the storage unit.

Here, the program stipulates the progression of conversation with the user as the branching part by the user's selection. This program describes the contents of a question, a plurality of options for answering the full text of the question, and an action for each of the options. In addition, when the content of the question is output from the speaker as a voice, as a candidate for answering the question, the control unit performs a first process of displaying on the display a plurality of choices corresponding to the question. When one of the plurality of options displayed on the display is pronounced by the user, the controller performs voice recognition using the pronunciation of the user's full text obtained from the microphone, thereby identifying one option corresponding to the user's pronunciation. At the same time, a second process is performed in which the action corresponding to this one option is determined as the response the interactive pet robot should take next to the answer.

Here, in the first processing in the interactive pet robot according to the first aspect of the present invention, it is preferable that the controller enumerates the full text of the plurality of options together with the contents of the question and displays them on the display. In addition, in this first process, the control unit may highlight and display the stress portion of the accent in the full text of the plurality of options on the display.

In the first aspect of the present invention, it is preferable that the action outputs the pronunciation from the speaker as a voice in response to the answer.

In the first aspect of the present invention, it is preferable that the control unit is housed in the trunk portion of the robot body in which the largest internal space is secured in the robot body, and the display is mounted in front of the trunk portion of the robot body.

In the first aspect of the present invention, the controller may perform a third process of displaying the spelling and the example of a plurality of words on the display in order at regular intervals, and at the same time outputting the pronunciation of the words displayed in sequence from the speaker. .

In a first aspect of the invention, the action may further comprise displaying the content of the pronunciation on the display as a response to the answer.

In the first process according to the first aspect of the present invention, the control unit performs voice recognition using the user's full pronunciation obtained from the microphone or operates a switch connected to the control unit. A fourth process of outputting audio from the speaker as at least one example audio can also be performed.

In the fourth process in the first aspect of the present invention, the control unit may highlight and display an example voice among the full text of the plurality of options on the display.

On the other hand, according to the second aspect of the present invention, the interactive pet robot includes a character robot body, a microphone mounted on the robot body, presentation means mounted on the robot body to present information to the user, and a program. And a control unit for processing according to the description of the program read in from the storage unit. Here, the program stipulates the progression of conversation with the user as the branching part by the user's selection. This program describes the contents of a question, a plurality of options that provide a full answer to the question, and an action for each of the options. In addition, when the content of the question is presented to the user through the presentation means, as a candidate for answering the question, the controller performs a first process of presenting to the user through the presentation means a plurality of options corresponding to the question. . When one of the plurality of options displayed on the display is pronounced by the user, the controller performs voice recognition using the pronunciation of the user's full text obtained from the microphone, thereby identifying one option corresponding to the user's pronunciation. At the same time, a second process is performed in which the action corresponding to this one option is determined as the response that the interactive pet robot should take next to the answer.

Here, in the second aspect of the present invention, the presentation means is preferably at least one of a speaker and a display.

According to the present invention, a plurality of options that are candidates for answers to the questions of the interactive pet robot are presented to the user in a specialized manner. The user may select an appropriate one from a plurality of options presented as a full text and pronounce the full text as it is. On the other hand, in the system for performing voice recognition, since the number of variations spoken by the user is as many as the number of choices, the recognition can be easily performed without requiring a high speed microcomputer. As a result, even if the product is relatively inexpensive, which has a limitation on the number of pronunciation phrases and waiting phrases, conversation can be promoted without causing the user to feel stress. In addition, since the information required for answering the question is presented by the pet robot, the user can proceed with the conversation while facing the pet robot. Accordingly, it is possible to increase the communication feeling with the pet robot and effectively maintain the user's motivation to learn.

1 is a front view of an interactive pet robot according to the present embodiment, and FIG. 2 is a side view thereof. The interactive pet robot 1 has a character robot body 2 and a display 3 mounted on the robot body 2. The robot body 2 made of plastic has an external shape in which a bear, which is an example of a character, is deformed cutely. The robot body 2 mainly consists of a head, a trunk and a limb, and a space for accommodating an electronic device is provided therein. In the trunk | drum 2a of the robot main body 2, the largest internal space is secured in the robot main body 2, in order to accommodate the control part mentioned later. The display 3 is a well-known small display such as, for example, liquid crystal or organic EL, and is mounted on the front of the robot body 2 body portion 2a. The reason for arranging the display 3 in front is to ensure the visual confirmation of the user while facing the character, and the reason for arranging it on the trunk portion 2a is to store it inside the trunk portion 2a. This is to shorten the connection distance with the controlled control unit as much as possible.

3 is a control block diagram of the interactive pet robot 1. The control system of the interactive pet robot 1 is comprised of the display 3 mentioned above, the various sensors 4-7, the speaker 8, the control part 9, and the various storage parts 12-14. The microphone 4 is mounted at an appropriate part of the robot body 2, and the interpersonal sensor 5 for detecting a user's pronunciation is mounted at an appropriate part of the robot body 2, so that the interactive pet robot 1 Detect whether there is anyone around. The forehead touch sensor 6 is mounted on the forehead of the head of the robot body 2, and detects whether the user touched the forehead. The four switches 7 are mounted in four positions of the right hand, left hand, right foot and left foot of the robot body 2, and detect whether or not the user has touched these parts. By these sensors 4-7, the system side can recognize the act as a communication (for example, touching a forehead, grasping hands and the like) performed by the user.

The control unit 9 is composed of a voice recognition unit 10 and a main control unit 11. The voice recognition unit 10 performs voice recognition using the pronunciation of the user obtained from the microphone 4 as an input, and outputs the recognition result to the main control unit 11. The speech recognition process using the user's pronunciation as an input is well known and thus description thereof is omitted here. The main control unit 11 mainly uses the recognition result from the voice recognition unit 10, and adds the detection signals from the sensors 5 to 7 to the display unit 3 and the speaker 8, as appropriate. To control. In the mask ROM 12 connected to the main control unit 11, a program (main program) that defines a procedure for communicating with a user is stored. The SRAM connected to the main control unit 11 is a working memory of the main control unit 11. In addition, the externally mounted ROM connected to both the voice recognition unit 10 and the main control unit 11 is a storage unit in an additional cartridge detachable to the robot body 2. The externally mounted ROM stores a program (extension program) that provides the above-described extension function of the main program.

4 is a flowchart showing an example of a procedure of conversation performed by the program. This program stipulates the progression of conversation with the user by branching by the user's choice. The main control unit 11 performs processing in the following order according to the description of the program read from the mask ROM 12.

First, the standby state of step 1 includes "Let's talk." And "Wake up." Or three choices of " Play. &Quot; The user selects any of these options and pronounces the full text. The voice recognition unit 10 performs voice recognition with input of the user's full pronunciation obtained from the microphone 4 and outputs the recognition result to the main control unit 11. The main control unit 11 specifies one option ("Let's talk.", "Wake up." Or "Play.") Corresponding to the user's pronunciation in accordance with the recognition result from the speech recognition unit 10. . The main control unit 11 then determines the action corresponding to the specified choice as a reaction that the pet robot 1 should take next. For example, the specified option is "Let's talk." Or, in the case of "Wake up.", The pronunciation of step 2 is spoken out from the speaker 8, and in the case of "Play.", The pronunciation of step 10 is spoken out.

Subsequently, Steps 2 to 5 form a series of flows of questions from the pet robot 1, the user's answer, and the pet robot 1's response to the pet robot 1, which forms the core of conversation (communication). In this regard, the program describes the contents of a question, a plurality of options that provide a full answer to the question, and a series of actions, each of which is an action for each option. Specifically for the question "Hi. How are you? My friend.", "I'm fine.", "Great!" And three options (full text) corresponding to "Not so good." Again, "I'm fine." And Great! "Options correspond to random actions by voice output" That's great! "And That's good, but I have a headache." I'm sorry to hear that.I hope you will feel better soon. "

According to the description of this program, in step 2, the main control unit 11 controls the speaker 8, so that the question "Hi. How are you? My friend." Is output from the speaker 8 as voice. Subsequently, in step 3, the main control unit 11 controls the display 3 so that the full text of the three options corresponding to the question is displayed on the display 3 as candidates for answers to the question.

5 is a diagram illustrating a display example of an option that is a candidate for an answer to a question. In this display example, the content of the voiced question, that is, "Hi. How are you? My friend." Is displayed at the top, and "I'm fine.", "Great! And" Not so good below it. 3 options are listed and displayed in full text. As a result, the user can grasp the correspondence between the contents of the question and the contents of the option at a glance. In this display example, the user's attention is promoted and the learning efficiency is further enhanced, and the stress portion of the accent in the text of the option is highlighted by changing the color or size of the font. The user selects any of these options and pronounces the full text.

In this case, the pet robot 1 may be configured to pronounce each of the choices spoken by the user as an example voice. For example, in the state shown in FIG. 5, a user performs predetermined operation with respect to the switch 7. In this way, in response to this operation, the main control unit 11 controls the speaker 8, and at least one option among the full text of the option is output from the speaker 8 as an exemplary voice. When all of the example audio outputs are completed, the process returns to the state shown in FIG.

Moreover, in addition to the operation of the switch 11, the start of example voice can also recognize the words "example!" From the microphone 4 from the microphone 4, for example. In addition, after this "example!", The voice number is recognized from the microphone 4 by the number 4 indicating the option "1", and only the third of the options is output as the example voice from the speaker 8.

In addition, when the pet robot 1 pronounces this example voice, it is also possible to highlight and display on the display 3 which option is pronounced as the example voice. For example, one option (for example "I'm fine.") Currently being displayed on the display 3 is pronounced as an exemplary voice from the speaker 8. At this time, the main control unit 11 controls the display 3 and highlights and displays the letter (or option) corresponding to this one option. In addition, the highlighting method includes not only changing the color and size of the font with respect to the character (or option), but also underlining, changing the font, or making the text bold.

The voice recognition unit 10 performs voice recognition using the user's full pronunciation obtained from the microphone 4 and outputs the recognition result to the main control unit 11. The main control unit 11 according to the recognition result from the speech recognition unit 10, one option corresponding to the user's pronunciation ("I'm fine.", "Great!" Or "Not so good.") Specifies. The main control unit 11 then determines the action corresponding to the specified option as the reaction that the pet robot 1 should take next. The specified option is "I'm fine." Or " Great! &Quot;, the process proceeds to step 4, in which one of " That's great " and That's good, but I have a headache. &Quot; is randomly selected, and this is output from the speaker 8. If the specified option is "Not so good." Proceed to Step 5, select "Oh, really? I'm sorry to hear that. I hope you will feel better soon. ”

In step 4, when the voice is output as "That's great.", The flow advances to step 10, where the question "What do you want to do?" On the other hand, if the voice is outputted in Step 4 as "that's good, but I have a headache.", The voice is outputted as "Please touch my head gently." In step 6, and the user waits for action (step 7 In the state of waiting for this action, when the user touches the forehead of the pet robot 1, this action is detected by the forehead touch sensor 6. Accordingly, in step 8, the interactive pet robot ( In response to 1), "Thank you my friend. After the voice is outputted, the process proceeds to step 10. In response to this, when the user touches other than the forehead and a sensor other than the forehead touch sensor 6 detects this, step 9 In response to the interactive pet robot 1, "Please touch my head. Try again. "And return to the standby state of step 7. As a result, the loops of steps 7 and 9 are repeated until the user touches the forehead.

If the voice is output in step 10 as " What do you want do? &Quot; For example, selecting a favorite fruit section results in a conversation about the interactive pet robot 1 and the foods that the user likes.

In the above-described conversational procedure, when the user pronounces "See you later.", It is set to forcibly return to the waiting state of Step 1. In addition, when the user pronounces "Go back.", It is set to forcibly return to Step 10.

In addition, in the above procedure of conversation, when the pet robot 1 outputs a response of a question or an answer, the pronunciation content can be displayed on the display 3. For example, in step 2, when the content " Hi How are you? My friend. &Quot; is output from the speaker 8, the main control unit 11 controls the display 3, whereby the pronunciation content is pronounced. The question "Hi How are you? My friend." Is shown on the display 3.

In addition to the above, an additional cartridge having an externally mounted ROM 14 may be used as an interviewer for an English proficiency test class 3, which assumes that the robot is an interviewer and displays a problem card on the display in order to further improve English learning ability. There is something virtual. In addition, a "flash card game" may be used to learn pronunciation of words and spelling thereof. In the latter case, the main control unit 11 displays the spelling and the view of the words on the display 3 (for example, the spelling of the Book and the view of the book) in order at regular intervals, and simultaneously reproduces the pronunciation of the displayed words. Audio is output from (8). The robot will say "Good." If the user pronounces it correctly, or "Try again." Answer the back. In addition, various series are available, such as those based on practical paintings assuming "shopping abroad."

As described above, according to the present embodiment, a plurality of options that are candidates for answers to the questions of the interactive pet robot 1 are presented to the user in a specialized manner. The user may select an appropriate one from among a plurality of presented options and pronounce the full text as it is. On the other hand, in the speech recognition unit 10, since the user's pronunciation is limited to the number of choices, the recognition can be performed easily and at high speed without requiring a high speed microcomputer. As a result, even if the product is relatively inexpensive, which has a limitation on the number of pronunciation phrases and waiting phrases, it is possible to promote conversation without causing the user to feel stress by presenting a specialized option.

In addition, according to the present embodiment, since the information required for answering the question is presented from the interactive pet robot 1, the user can converse without referring to other information while facing the pet robot 1. You can proceed. Thereby, the communication feeling with the pet robot 1 can be improved, and the user's willingness to learn can be effectively maintained.

In addition, in the above-described embodiment, the operation of the interactive pet robot 1 has been described as an example of learning English conversation, but the present invention is not limited to this, but can be widely applied to conversational learning of languages of each country.

In addition, the action which the interactive pet robot 1 should take is not limited to the audio output from the speaker 8. For example, if the limbs of the interactive pet robot 1 are movable, they may be operated as an action, or when the luminous body is mounted, it may be flickered.

In addition, in the above-mentioned embodiment, although the option which is a candidate for answering a question is displayed in full on the display 3, it is also possible to present this to a user by the full audio output by the speaker 8. In terms of promoting conversation, however, it is preferable to display on the display 3 that does not require time for pronunciation than when the interactive pet robot 1 pronounces a choice for a question each time.

The present invention provides a novel interactive pet robot capable of facilitating conversation even if there are restrictions on the number of phonetic phrases and waiting phrases. In addition, it is possible to maintain a sense of communication with the interactive pet robot and keep the user's motivation to learn.

Claims (11)

In the interactive pet robot, Character type robot body, A microphone mounted to the robot body, A speaker mounted on the robot body, A display mounted to the robot body, The order of the conversation with the user is defined by the branching part by the user's selection, and the contents of a certain question, a plurality of options for answering the full text of the question, and each of the options A storage unit for storing the described program corresponding to the action of A control unit which is built in the robot body and performs processing according to the description of the program read from the storage unit; Including, The control unit When the content of the question is output from the speaker as a voice, as a candidate for the answer to the question, a first process of displaying the plurality of options corresponding to the question on the display in full, When any one of the plurality of options displayed on the display is pronounced by the user, voice recognition is performed by inputting the user's full voice obtained from the microphone, and one option corresponding to the user's pronunciation is input. At the same time, performing a second process of determining the action corresponding to the one option as the response the interactive pet robot should take next to the answer. Interactive pet robot. The method of claim 1, In the first processing, the controller enumerates and displays on the display the full text of the plurality of options simultaneously with the content of the question. The method of claim 1, In the first processing, the controller is characterized by highlighting the stress portion of the intonation among the full text of the plurality of options to display on the display. The method of claim 1, And wherein said action outputs a voice from said speaker as a response to said answer. The method of claim 1, The controller is accommodated in the body portion of the robot body is secured the largest internal space in the robot body, The display is an interactive pet robot, characterized in that mounted on the front of the body portion of the robot body. The method of claim 1, And the control unit displays a spelling and a view of the plurality of words on the display in order at regular intervals, and performs a third process of outputting the pronunciation of the words displayed in the order from the speaker as voice. robot. The method of claim 4, wherein And the action further comprises displaying on the display the contents of the pronunciation as a response to the answer. The method of claim 1, In the first processing, the control unit performs one or more of the full texts of the plurality of options by performing voice recognition using the pronunciation of the full text of the user obtained from the microphone or operating a switch connected to the control unit. An interactive pet robot characterized by outputting sound from the speaker as an exemplary voice. The method of claim 8, In the first processing, the controller is characterized by highlighting the example voice among the full text of the plurality of options to display on the display. In the interactive pet robot, Character type robot body, A microphone mounted to the robot body, Presentation means mounted on the robot body for presenting information to the user, The order of conversation with the user is defined in the branching section by the user's selection, and the content of a question, a plurality of options for the full answer to the question, and actions for each of the options are described. A storage unit containing a stored program, and A control unit which is built in the robot body and performs processing according to the description of the program read from the storage unit Including, The control unit When the content of the question is presented to the user through the presentation means, as a candidate for the answer to the question, a first process of presenting the plurality of options corresponding to the question to the user through the presentation means in full; Do it, When any one of the plurality of options displayed on the display is pronounced by the user, voice recognition is performed by inputting the user's full pronunciation obtained from the microphone to identify one option corresponding to the user's pronunciation. And at the same time, performing a second process of determining the action corresponding to the one option as the response the interactive pet robot should take next to the answer. Interactive pet robot. The method of claim 10, And said presenting means is at least one of a speaker and a display.

Images