KR101505078B1 - Method for providing quiz game service in movable robot and movable robot apparatus - Google Patents

Abstract

The present invention relates to a method of providing a quiz game service in a mobile robot and a mobile robot therefor. A method of providing a quiz game service to a plurality of users in a mobile robot according to the present invention includes a first problem output step of outputting a problem to a screen at a position where a screen is exposed to the problem descriptor; A correct answer confirming step of confirming whether a correct answer voice is recognized for the question being outputted; A location recognizing step of re-selecting a user who has uttered the correct answer voice as a problem descriptor and recognizing a position of the re-selected problem descriptor when the correct answer voice is recognized as the confirmation result; Moving to a position distant from the recognized position by a predetermined distance so that the screen is exposed to the re-selected problem descriptor; And a next problem output step of outputting the next problem on the screen in the moved area.

Description

METHOD FOR PROVIDING QUIZ GAME SERVICE IN MOVABLE ROBOT AND MOVABLE ROBOT APPARATUS BACKGROUND OF THE INVENTION 1. Field of the Invention [0001]

The present invention relates to a mobile robot technology, and more particularly, to a method of providing a quiz game service in a mobile robot and a mobile robot therefor.

As mobile robots are developed and released, users can use mobile robots at home. Such a mobile robot drives a touch screen type display unit, a speaker, a wheel, and the like, and moves according to a user's operation or outputs a content designated by the user to the display unit. The following patent document discloses an educational mobile robot having an event editing function.

However, the conventional mobile robot can not provide various contents to the users, and provides only uniform service to the users. That is, the conventional mobile robot has a main function to move according to a user's command, to connect to the Internet to play an Internet game, or to output multimedia contents such as IPTV to a screen. Accordingly, service research for a mobile robot that can cause a user's interest is continuing.

Korean Patent Publication No. 10-2011-0026560

SUMMARY OF THE INVENTION The present invention has been proposed in order to solve such conventional problems, and it is an object of the present invention to provide a method of providing a quiz game service in a mobile robot capable of enjoying a quiz game among a plurality of users through a mobile robot, have.

Other objects and advantages of the present invention will become apparent from the following description, and it will be understood by those skilled in the art that the present invention is not limited thereto. It will also be readily apparent that the objects and advantages of the invention may be realized and attained by means of the instrumentalities and combinations particularly pointed out in the appended claims.

According to a first aspect of the present invention, there is provided a method of providing a quiz game service to a plurality of users in a mobile robot, the method comprising the steps of: An output step; A correct answer confirming step of confirming whether a correct answer voice is recognized for the question being outputted; A location recognizing step of re-selecting a user who has uttered the correct answer voice as a problem descriptor and recognizing a position of the re-selected problem descriptor when the correct answer voice is recognized as the confirmation result; Moving to a position distant from the recognized position by a predetermined distance so that the screen is exposed to the re-selected problem descriptor; And a next problem output step of outputting the next problem on the screen in the moved area.

According to a second aspect of the present invention, there is provided a mobile robot providing a quiz game service to a plurality of users, the mobile robot comprising: a display unit for outputting a question; Storing a plurality of problems; A problem-solving unit for extracting a problem from the storage unit at a location where the display unit is exposed to the problem descriptor and outputting the extracted problem to the display unit; A correct answer determining unit for determining whether a correct answer voice for the question in the output is recognized and, when a correct answer voice is recognized, a user who has uttered the correct answer voice as a correct answer; And re-selecting the correct answer identified by the correct answer determination section as a problem descriptor, recognizing the repositioned problem descriptor, and instructing the re-selected problem descriptor to a position spaced apart from the recognized position by a predetermined distance, And a descriptor selection unit for moving the mobile robot. When the movement of the mobile robot is completed in the direction of the reselected problem descriptor, the trouble provider extracts the next problem from the storage unit and outputs the extracted problem to the display unit .

According to a third aspect of the present invention, there is provided a mobile robot for providing a quiz game service to a plurality of users, the mobile robot comprising: a display unit for outputting a problem; Storing a plurality of problems; A plurality of microphones mounted on left and right sides of the mobile robot, respectively; A problem-solving unit for extracting a problem from the storage unit at a location where the display unit is exposed to the problem descriptor and outputting the extracted problem to the display unit; A correct answer determining unit for determining whether a correct answer voice for the question is recognized and, when a correct answer voice is recognized, a user who has uttered the correct answer voice as a correct answer; A voice direction analyzer for analyzing a frequency of the correct answer voice received from the plurality of microphones to determine a speaking direction of the correct answer voice; And a face recognizing unit for recognizing the face of the problem descriptor and the position of the problem descriptor by changing the photographing angle in the speaking direction of the correct answer voice analyzed by the voice direction analyzing unit, And a descriptor selection unit for moving the mobile robot to a position distant from the recognized position by a predetermined distance so that the display unit is exposed to the selected problem descriptor, The control unit extracts the next problem from the storage unit, and outputs the extracted problem to the display unit.

The present invention has the advantage of diversifying the service of the mobile robot and increasing the utilization of the mobile robot by implementing a quiz game service that users can enjoy using the mobile robot.

In addition, the present invention induces the mobile robot to move to the correct answer position of the quiz game and instructs the correct answer person to explain the next problem, thereby not only causing interest of the user but also improving the user's immersion level of the quiz game.

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments of the invention and, together with the description, serve to explain the principles of the invention. And shall not be construed as limited to such matters.
1 is a block diagram of a mobile robot providing a quiz game service according to an embodiment of the present invention.
2 is a flowchart illustrating a method of providing a quiz game service to a user in a mobile robot according to an embodiment of the present invention.
3 is a diagram showing a mobile robot that outputs a problem in front of a problem descriptor.
4 is a view showing a configuration of a mobile robot according to another embodiment of the present invention.
5 is a flowchart illustrating a method of providing a quiz game service to a user in a mobile robot according to another embodiment of the present invention.

The foregoing and other objects, features and advantages of the present invention will become more apparent from the following detailed description of the present invention when taken in conjunction with the accompanying drawings, in which: There will be. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise. Also, the terms "part,"" module, "and the like, which are described in the specification, refer to a unit for processing at least one function or operation, and may be implemented by hardware or software or a combination of hardware and software.

1 is a block diagram of a mobile robot providing a quiz game service according to an embodiment of the present invention.

1, a mobile robot 100 according to the present invention includes a camera 101, a driving unit 102, a storage unit 103, a microphone 104, a display unit 105, a participant recognition unit 106, A descriptor selection unit 107, a problem provisioning unit 108, a correct answer determination unit 109, and a game result providing unit 110.

The camera 101 includes a lens and uses this lens to take a surrounding image. The camera 101 is rotatable, and the subject can be enlarged or reduced and photographed.

The driving unit 260 includes a moving means such as a wheel and moves the mobile robot 100 under the control of the participant recognition unit 106 or the descriptor selection unit 107.

The storage unit 103 stores map data in which coordinate information of each room is recorded, and stores position information for each user participating in the game. In addition, the storage unit 103 stores a plurality of quiz information in which the problem information and the correct answer information are recorded together. In addition, the storage unit 103 stores user information in which a face image, a voice pattern, and a name are mapped on a user-by-user basis.

The microphone 104 is a microphone for receiving a voice of a user, and a plurality of microphones may be mounted on the mobile robot 100. When there are two microphones 104, the first microphone is installed on the left side of the mobile robot 100, and the second microphone is installed on the right side of the mobile robot 100.

The display unit 105 displays various information processed by the mobile robot 100 as display means such as a liquid crystal display (LCD), an organic EL display (organic electroluminescence display), an LED (Light Emitting Diode) . Preferably, the display unit 105 is a touch screen, and further receives an operation signal from a user by performing a function of the input unit.

The participant recognition unit 106 recognizes each user participating in the game and performs a function of grasping the position of each user. Specifically, the participant recognizing unit 160 rotates the camera 101 to capture a face image of each user participating in the game when a quiz game start request is received from a specific user. The participant recognizing unit 106 recognizes each user participating in the game by confirming the captured face image of each user and the user name mapped to the user information of the storage unit 103 respectively. In addition, the participant recognizing unit 106 identifies the area where each user is located on the photographed image, compares the position area of each user with the map data of the storage unit 103, (I.e., coordinate information), and stores the position information for each user in the storage unit 103. [

Meanwhile, when the participant recognition unit 106 captures a face image that does not coincide with the face image stored in the user information of the storage unit 103 by more than the threshold value, it is determined that the unregistered new user participates in the quiz game , Receives the voice and name from the new user, maps the name of the new user, the voice pattern, and the face image of the new user that has already been photographed, and stores it in the user information of the storage unit 103. That is, if the face of the user participating in the game is not recognized, the participant recognition unit 106 acquires the name, the voice pattern, and the face image of the user and stores it in the user information of the storage unit 103.

The descriptor selection unit 107 selects a problem descriptor and controls the driving unit 102 to move the mobile robot 100 to a position spaced a predetermined distance (for example, 20 cm) from the selected problem descriptor. That is, the descriptor selection unit 107 confirms the position information of the problem descriptor based on the user-specific position information of the storage unit 103 and controls the driving unit 102 to separate the problem descriptor from the problem descriptor by a certain distance And moves the mobile robot 100 to a position where the robot 100 is positioned. Preferably, the descriptor selection unit 107 controls the driving unit 102 so that the display unit 105 of the mobile robot 100 on which the problem is outputted is exposed only to the problem descriptor, and the mobile robot 100 is displayed on the front face of the problem descriptor .

Meanwhile, the descriptor selection unit 107 may select a user located near the front of the mobile robot 100 as a problem descriptor before the first problem is output, and may select a problem descriptor randomly among users participating in the game . The descriptor selection unit 107 re-determines the correct user as a quiz descriptor, checks the position information of the re-selected quiz descriptor in the storage unit 103, and then controls the driving unit 102 And moves the mobile robot 100 to a place separated from the selected problem descriptor by a predetermined distance (for example, 20 cm).

When the mobile robot 100 is located at a position spaced apart from the problem descriptor by a certain distance, the trouble remover 108 extracts any one of the plurality of problems stored in the storage unit 103 and outputs the extracted problem to the display unit 105 , Causing the quiz game to proceed between users.

The correct answer determining section 109 includes a speech recognition module 109a for recognizing the user's voice and uses the speech recognition module 109a to identify a user who has uttered the correct answer out of the users other than the problem descriptor . Specifically, the correct answer determining section 109 confirms the correct answer to the question being outputted to the display section 105 in the storage section 103, and determines whether or not the voice corresponding to the correct answer is received from the microphone 104, Lt; RTI ID = 0.0 > 109a. ≪ / RTI > The correct answer determination section 109 preferably confirms the speech pattern of the problem descriptor in the storage section 103 and continuously monitors the voice of another user except the speech pattern of the problem descriptor. When the voice corresponding to the correct answer is recognized through the voice recognition module 109a, the correct answer determining section 109 compares the voice pattern matched with the pattern of the voice to a threshold value (for example, 70%) or more and a user name mapped And the number of correct answers for this user is increased by '1' or the quiz score is increased.

When the last question is solved, the game result providing unit 110 confirms the number of correct answers or the number of quizzes per user, and stores the number of correct answers or the number of quizzes perceived by the user in the storage unit 103 together with the current date and time . Also, the game result providing unit 110 outputs the number of correct answers or quiz scores per user to the display unit 105, thereby recognizing the quiz game results to a plurality of users.

2 is a flowchart illustrating a method of providing a quiz game service to a user in a mobile robot according to an embodiment of the present invention.

3 is a diagram showing a mobile robot that outputs a problem in front of a problem descriptor.

Referring to FIGS. 2 and 3, the mobile robot 100 receives a quiz game start request from any one of a plurality of users participating in the game (S201).

Then, the participant recognizing unit 106 sequentially rotates the camera 101 in a predetermined direction (e.g., clockwise or counterclockwise) to sequentially capture images of the users participating in the game, and acquires the face images of the respective users (S203). Alternatively, the participant recognizing unit 106 may control the driving unit 102 to rotate the mobile robot 100 by 360 degrees, sequentially capture the faces of the users participating in the game, and acquire a face image of each user. Preferably, the participant recognizing unit 106 may acquire a face image of each user by enlarging and temporarily storing a face region for each user in the entire image captured through the camera 101. [

Then, the participant recognizing unit 106 determines whether or not the face image matching the captured face image of the user with a threshold value (for example, 70%) is stored in the user information of the storage unit 103 (S205). That is, the participant recognizing unit 106 confirms whether the face image of the user participating in the game is registered in the storage unit 103 in advance.

Then, when the participant recognizing unit 106 photographs a face image that does not coincide with the face image stored in the user information of the storage unit 103 by more than the threshold value, it is determined that the unregistered new user participates in the quiz game , And outputs to the display unit 105 a message requesting the user to input information. Then, the participant recognizing unit 106 receives the name and voice of the new user through the microphone 104 and input means (e.g., a touch screen), analyzes the voice, and outputs a voice of a new user's voice, After the pattern is confirmed, the name of the new user, the voice pattern, and the captured face image of the new user are mapped and stored in the user information of the storage unit 103 to complete the registration of the new user (S207).

The participant recognition unit 106 stores the user name mapped to each face image in the storage unit 103 when the photographed face image of the user is registered in the user information of the storage unit 103 or the registration of the new user is completed, And identifies the participant of the game. Next, the participant recognizing unit 106 confirms the area where each user is located on the photographed image, and analyzes the positional area for each user, which is thus verified, by comparing with the map data of the storage unit 103, (I.e., coordinate information) on the space and stores it in the storage unit 103 (S209).

Next, the participant recognition unit 106 instructs the descriptor selection unit 107 to proceed with the quiz game.

Then, the descriptor selection unit 107 selects one of the users participating in the game as a problem descriptor (S211). At this time, the descriptor selection unit 107 can select a user located near the front (i.e., camera front) of the user as a problem descriptor, or arbitrarily select any one of a plurality of users as a problem descriptor.

Next, the descriptor selection unit 107 confirms the position information of the selected problem descriptor on the basis of the user-specific position information stored in the storage unit 103, and controls the driving unit 102 to set a distance To move the mobile robot 100 to a position spaced apart. At this time, the descriptor selection unit 107 controls the driving unit 102 to position the mobile robot 100 on the front face of the problem descriptor so that the display unit 105 of the mobile robot 100 outputting the problem is exposed only to the user . 3 (a), the descriptor selection unit 107 selects a user as a problem descriptor, and the screen of the mobile robot 100 (that is, the display unit) The mobile robot 100 is moved to a position spaced apart from the problem descriptor 31 by a predetermined distance (for example, 20 cm) by controlling the driving unit 102 so that the mobile robot 100 is exposed only to the user.

The descriptor selection unit 107 moves the mobile robot 100 to the problem descriptor, and then requests the problem provision unit 108 to provide a problem.

Then, the trouble provider (108) extracts any one of the plurality of problems stored in the storage unit (103) and outputs the extracted problem to the display unit (105) (S213). The problem may be a word itself, a sentence describing the correct answer, or an image of a person / animal. In addition, if the problem is a word or an image, the problem descriptor describes the word or image (e.g., an animal, etc.) to another user and asks for the correct answer to the problem. In addition, when the above problem is a sentence of a question text explaining the correct answer, the problem descriptor can request another user to solve the problem by reading the sentence output to the display unit 105. [

Referring to FIG. 3 (b), for example, the trouble remover 108 outputs the word "butterfly" to the display unit 105, which is exposed only to the problem descriptor (ie, user 31). The problem descriptor then causes the other user 32, 33, 34 to describe the word "butterfly" so that the other user 32, 33, 34 speaks the correct answer (ie, the butterfly).

When a problem is output to the display unit 105 in this way, the correct answer determination unit 109 confirms the correct answer to the question being output to the display unit 105 in the storage unit 103, and determines whether or not the speech that matches the correct answer is recognized It is continuously monitored by using the speech recognition module 109a to determine whether or not a voice corresponding to the correct answer is recognized (S215, S217). The correct answer determination section 109 preferably confirms the speech pattern of the problem descriptor in the storage section 103 and continuously monitors the voice of another user except the speech pattern of the problem descriptor.

The correct answer determining section 109 recognizes the voice pattern matching the correct answer with the voice recognition module 109a and stores the voice pattern matching the pattern of the voice with a threshold value (for example, 70% or more) In the user information of the user. In step S219, the correct answer determining unit 109 identifies the user who has uttered the correct answer (i.e., the correct answer) by confirming the name of the user mapped with the confirmed voice pattern in the user information of the storage unit 103. [ At this time, the correct answer determining unit 109 may output a voice message to the speaker (not shown) notifying that the identified user is the correct user.

Next, the correct answer determining section 109 increases the number of correct answers of the identified user by '1' (S221). Alternatively, the correct answer determination unit 109 may increase the quiz score of the identified user by the score assigned to the question. Next, the correct answer determining unit 109 checks whether the correct answer is the last question based on the preset number of quizzes (S223). If the question is the last question, the correct answer determining unit 109 instructs the game result providing unit 110 to output the game result do.

Then, the game result providing unit 110 confirms the number of correct answers or the number of quizzes per user (S225), and stores the confirmed number of correct answers or the quiz score per user in the storage unit 103 together with the current date and time. Then, the game result providing unit 110 outputs the number of correct answer or quiz score per user to the display unit 105, thereby recognizing the quiz game result to a plurality of users (S227). At this time, the game result providing unit 110 may output a voice message to the speaker (not shown) informing that the user having the highest number of correct answers or the user having the highest quiz score is the first speaker.

On the other hand, in step S223, if the correct answer is not the last question, the correct answer determination unit 109 transmits the name of the user identified as the correct answer to the descriptor selection unit 107, (107).

Then, the descriptor selection unit 107 confirms the name of the user received from the correct answer determination unit 109, and re-selects the user (i.e., correct answer) as a quiz descriptor (S229). Then, the descriptor selection unit 107 confirms the position information of the re-selected quiz descriptor in the storage unit 103 (S231). Next, the descriptor selection unit 107 controls the driving unit 102 to move the mobile robot 100 to a position spaced a certain distance (for example, 20 cm) from the re-selected problem descriptor (S233). At this time, the descriptor selection unit 107 controls the driving unit 102 so as to expose the mobile robot 100 to the re-selected problem descriptor so as to be exposed only to the problem descriptor of the display unit 105 of the mobile robot 100, Place it on the front. Preferably, the descriptor selection unit 107 controls the driving unit 102 so that the mobile robot 100 looks in the direction of the re-selected problem descriptor based on the position information of the re-selected problem descriptor, And then moves the mobile robot 100 to a position spaced apart from the position of the re-selected problem descriptor by a predetermined distance (for example, 20 cm).

Referring to FIG. 3B, the correct answer determining unit 109 recognizes that the user 32 is the correct answer when the user 32 has uttered the correct answer "NAVIGATION". Then, the descriptor selection unit 107 re-selects the correct answer 32 as a problem descriptor, and confirms the position information of the correct answer 32 from the user-specific position information of the storage unit 103. [ The descriptor selection unit 107 controls the driving unit 102 to move the mobile robot 100 to a position spaced apart by a predetermined distance (for example, 20 cm) from the position of the re-selected problem descriptor .

When the movement of the mobile robot 100 is completed, the descriptor selection unit 107 instructs the problem provision unit 108 to output a problem, extracts a problem other than the previously outputted problem from the storage unit 103, 105 (S235).

Then, the correct answer determining section 109 confirms the correct answer to the question being outputted to the display section 105 in the storage section 103, and whether or not the voice corresponding to the correct answer is recognized is determined by using the speech recognition module 109a The process proceeds to step S215 where the monitoring is continuously performed.

Meanwhile, the mobile robot 100 according to the present invention may analyze the voice phase and intensity of the correct answer person to check the position of the correct answer person.

4 is a view showing a configuration of a mobile robot according to another embodiment of the present invention.

Among the constituent elements shown in Fig. 4, the constituent elements having the same reference numerals in Fig. 1 perform the same functions as the constituent elements explained with reference to Fig. 1 and Fig. Therefore, only the components having the reference numerals different from those of FIG. 1 will be described among the components shown in FIG.

4, a mobile robot 400 according to another embodiment of the present invention includes a camera 101, a driving unit 102, a storage unit 103, a microphone 104, a display unit 105, A descriptor selection unit 407, a problem provisioning unit 108, a correct answer determination unit 109, and a game result providing unit 110. [

The voice direction analyzing unit 406 analyzes the frequency, phase, and strength of the voice recognized as a correct answer in conjunction with the voice recognition module 109a to confirm the direction in which the correct answer voice is uttered. Specifically, the voice direction analyzing unit 406 identifies the frequency region of the correct answer voice recognized by the voice recognition module 109a. If the correct answer voice is a high frequency (e.g., a frequency of 3000 Hz or more), each microphone 104 The difference of the strength of the right answer voice received at the right ear speaker. In addition, if the difference between the right and left microphones is greater than or equal to a preset threshold value, the voice direction analyzer 406 determines that the direction of the microphone (left or right) And transmits the determined correct voice direction information to the descriptor selection unit 407. [ On the other hand, if the difference between the right speech strengths received from the two microphones 104 is less than a predetermined threshold strength, the speech direction analyzing unit 406 determines that the direction in which the correct answer speech is the backward direction of the mobile robot 400 And transmits the backward direction information to the descriptor selection unit 407. [

The voice direction analyzing unit 406 analyzes the time difference (that is, the phase difference) when the right answer voice is received from the right microphone and the left microphone when the correct answer voice recognized by the voice recognition module 109a is a low frequency (for example, And checks whether the calculated time difference is less than a predetermined threshold time (for example, 0.8 millimeter seconds). If the time difference between the right microphone and the right microphone received by the right microphone is greater than or equal to a preset threshold time, the direction of the microphone in which the correct answer is first received is the direction in which the correct answer is uttered And transmits the determined correct voice direction information to the descriptor selection unit 407. On the other hand, if the time difference between the left microphone 104 and the right microphone received by the right voice is less than a predetermined threshold time, the voice direction analyzing unit 406 determines that the direction in which the correct voice is uttered is the backward direction of the mobile robot 400 And transmits the backward direction information to the descriptor selection unit 407. [

On the other hand, if the voice recognized as a correct answer corresponds to an intermediate frequency (for example, a frequency exceeding 1500 Hz and less than 3000 Hz), the voice direction analyzing unit 406 transmits a message to the descriptor selection unit 407 indicating that direction confirmation is impossible .

The descriptor selection unit 407 selects the problem descriptor and recognizes the position of the problem descriptor based on the video shot by the camera 101 and the correct voice direction information received from the voice direction analysis unit 406, And moves the mobile robot 400 to a position spaced apart by a predetermined distance (for example, 20 cm).

Specifically, the descriptor selection unit 407 re-selects the correct answer as a problem descriptor, and based on the correct voice direction information received from the voice direction analysis unit 406, the camera 101 is set in the correct voice direction (i.e., And changes the photographing angle of the camera 101 to the direction of the problem descriptor and recognizes the face of the problem descriptor re-selected through the camera 101. [ On the other hand, when the descriptor selection unit 407 receives the message informing that the direction check is impossible to the descriptor selection unit 407, the descriptor selection unit 407 rotates the camera 101 in a predetermined direction (e.g., right or left) The faces of all the users participating in the process are sequentially photographed, and then the faces of the re-selected problem descriptor are recognized by analyzing the plurality of captured face images. In addition, the descriptor selection unit 407 recognizes the position of the problem descriptor based on the direction in which the face of the problem descriptor is recognized and the distance between the problem descriptor, and then controls the driving unit 102 to change the position of the problem descriptor And moves the mobile robot 400 to a spaced position. Meanwhile, the descriptor selection unit 407 selects a user located in front of the mobile robot 400 as a problem descriptor before the first problem is output.

5 is a flowchart illustrating a method of providing a quiz game service to a user in a mobile robot according to another embodiment of the present invention.

Referring to FIG. 5, the mobile robot 400 receives a quiz game start request from the user (S501) while being positioned in front of a user who will describe the first problem. At this time, it is preferable that the display unit 105 of the mobile robot 400 to which the problem is output is exposed only to the user. That is, the user who described the first problem places the mobile robot 400 in front of him / herself in a state in which the display unit 105 of the mobile robot 400 is exposed only to himself / herself, , The user inputs a quiz game start menu and requests the mobile robot 400 to start the quiz game.

3, the mobile robot 400 receives a quiz game start request from the user 31 in a state of being positioned in front of the user 31 to explain the first problem among a plurality of users, And receives an operation signal.

The descriptor selection unit 407 then captures the face image of the user located on the front side using the camera 101 (S503), and the face image having the similarity degree to the photographed face image (for example, 70% It is confirmed whether or not it is stored in the user information of the storage unit 103 (S505).

The descriptor selection unit 407 determines that the user is not registered in the front position when the face image having the degree of similarity to the photographed face image is not stored in the user information of the storage unit 103, And outputs a message requesting input (i.e., name and voice) to the display unit 105. The descriptor selection unit 407 receives the user's name and voice from a user located in front of the mobile robot 400 and analyzes the voice to check the voice pattern of the voice of the new user, The name of the new user, the voice pattern, and the captured face image of the new user are mapped and stored in the user information of the storage unit 103 to complete the registration of the new user (S507).

The descriptor selection unit 407 then stores the face image matching the face image of the user with the face image equal to or higher than the threshold value in the user information of the storage unit 103 or when registration of the user located on the front face is completed, The user located at the front of the mobile robot 400 is identified by checking the face image and the mapped name in the user information of the storage unit 103 (S509). Next, the descriptor selection unit 407 selects the identified user as the quiz descriptor (S511), and requests the problem provisioning unit 108 to provide a problem.

Then, the trouble providing unit 108 extracts any one of the plurality of problems stored in the storage unit 103 and outputs the extracted problem to the display unit 105 (S513).

When the problem is output to the display unit 105, the correct answer determining unit 109 confirms the correct answer to the question being output to the display unit 105 in the storage unit 103, (S515, S517) by using the voice recognition module 109a. The correct answer determination section 109 preferably confirms the speech pattern of the problem descriptor in the storage section 103 and continuously monitors the voice of another user except the speech pattern of the problem descriptor.

The correct answer determining section 109 determines whether or not a voice corresponding to the correct answer is recognized for the first time through the voice recognition module 109a and stores the voice pattern matching the pattern of the voice with a threshold value (for example, 70% ) From the user information. Next, the correct answer determining unit 109 identifies the user who has uttered the correct answer (i.e., the correct answer) by confirming the name of the user mapped with the verified voice pattern in the user information of the storage unit 103 (S519) .

Next, the correct answer determining section 109 increases the number of correct answers of the identified user by '1' (S521). Alternatively, the correct answer determination unit 109 may increase the quiz score of the identified user by the score assigned to the question. Next, the correct answer determining unit 109 checks whether the correct answer is the last question based on the preset number of quizzes (S523). If it is the last question, the correct answer determining unit 109 instructs the game result providing unit 110 to output the game result do.

Then, the game result providing unit 110 checks the correct answer frequency or quiz score per user (S525), and stores the confirmed correct answer frequency or quiz score in the storage unit 103 together with the current date and time. Then, the game result providing unit 110 outputs a quiz game result to the plurality of users by outputting the number of correct answers or quiz score per user to the display unit 105 (S527).

On the other hand, in step S523, if the correct answer is not the last question, the correct answer determination unit 109 transmits the name of the user identified as the correct answer to the descriptor selection unit 107, (107).

Then, the descriptor selection unit 107 confirms the name of the user received from the correct answer determination unit 109 and re-selects the user (i.e., the correct answer) as a quiz descriptor (S529). Then, the voice direction analysis unit 406 Ask for an analysis of this uttered direction. Then, the voice direction analyzing unit 406 analyzes the phase and intensity of the voice recognized as a correct answer, and analyzes the direction in which the voice is uttered (S531). Then, the analyzed direction (e.g., backward, Direction to the descriptor selection unit 407. [ Specifically, the voice direction analyzing unit 406 confirms whether the correct answer voice recognized by the voice recognition module 109a is a high frequency, an intermediate frequency, or a low frequency. When the voice corresponds to a high frequency (for example, a frequency of 3000 Hz or more), the voice direction analyzing unit 406 checks the strength of the correct answer voice received from each of the microphones 104 provided on both sides, Lt; / RTI > If the difference between the sound intensity of the right microphone and the sound intensity of the left microphone is greater than or equal to a predetermined threshold intensity, the microphone direction (left or right) direction in which the sound intensity is larger is the direction . For example, the voice direction analyzing unit 406 may determine that the difference between the right and left microphone strengths is greater than or equal to a predetermined threshold strength, and that the strength of the right answer voice received at the left microphone is greater than the strength of the right answer voice received at the right microphone , It is determined that the direction of the right speech is the utterance direction in the left direction. On the other hand, if the difference between the sound intensities of the right microphone and the left microphone is less than a predetermined threshold difference, the voice direction analyzing unit 406 determines that the direction in which the correct answer voice is uttered is the backward direction of the mobile robot 400.

The voice direction analyzing unit 406 analyzes the time difference of the right voice reached to the right microphone and the left microphone when the correct voice recognized by the voice recognition module 109a corresponds to a low frequency (for example, a frequency of 1500 Hz or less) I.e., the phase difference) is less than a preset threshold time (for example, 0.8 millimeter seconds). Next, the voice direction analyzing unit 406 checks whether the microphone received first by the correct answer voice is a left or right microphone if the difference in time between arrival of the correct answer voice in each of the right microphone and the left microphone is more than a preset threshold time , And determines that the direction of the microphone is the direction in which the correct answer voice is uttered. On the other hand, if the difference in time between arrival of the correct answer voice in the right microphone and the left microphone is less than a preset threshold time, the direction in which the correct answer voice is uttered is the backward direction of the mobile robot 400 .

On the other hand, if the voice recognized as a correct answer corresponds to an intermediate frequency (for example, a frequency exceeding 1500 Hz and less than 3000 Hz), the voice direction analyzing unit 406 transmits a message to the descriptor selection unit 407 indicating that direction confirmation is impossible .

Next, the descriptor selection unit 407 extracts the face image mapped with the name of the user re-selected as the problem descriptor from the user information of the storage unit 103, The camera 101 is rotated to change the photographing angle of the camera 101 to the direction of the re-selected problem descriptor (i.e., correct answer) (S533). For example, the descriptor selection unit 407 rotates the camera 101 by 90 degrees to the right when receiving the right direction from the voice direction analyzing unit 406, rotates the camera 101 by 90 degrees to the left when receiving the left direction, The camera 101 may be rotated 180 degrees so as to photograph the backward direction.

Next, the descriptor selection unit 407 acquires the face image of the user through the rotated camera 101 and confirms the similarity between the face image and the face image of the extracted user (i.e., the user re-selected as the problem descriptor) And recognizes whether or not the degree of similarity is equal to or greater than a threshold value (e.g., 70%), thereby recognizing the face of the user re-selected as the problem descriptor (S535). On the other hand, when the descriptor selection unit 407 receives the message informing that the direction confirmation is impossible to the descriptor selection unit 407, the descriptor selection unit 407 rotates the camera 101 by 360 degrees in a predetermined direction And recognizes the face of the re-selected problem descriptor by checking the similarity of the face image of the user who has been re-selected as the problem descriptor of each user thus obtained.

Next, the descriptor selection unit 407 extracts, from the image photographed through the camera 101, the re-selected question descriptor ((the right answer candidate)) if the face image whose agreement degree with the re- I.e., the face of the correct answer), and measures the distance of the correct answer. At this time, the descriptor selection unit 407 can analyze the image of the problem descriptor photographed for face recognition, and can measure the distance between the mobile robot 400 and the problem descriptor. May be used to measure the distance between the mobile robot 400 and the problem descriptor. Next, the descriptor selection unit 407 recognizes the position of the re-selected problem descriptor on the basis of the direction recognized by the face of the re-selected problem descriptor and the distance between the problem descriptor (S537).

Next, the descriptor selection unit 407 controls the driving unit 102 to rotate the mobile robot 400 so that the mobile robot 400 looks in the direction in which the face of the re-selected problem descriptor is recognized. Next, the descriptor selection unit 407 controls the driving unit 102 to move the mobile robot 400 to a position spaced a predetermined distance (for example, 20 cm) from the position of the re-selected problem descriptor (S539). The descriptor selection unit 407 controls the driving unit 102 to move the mobile robot 400 by controlling the driving unit 102 so that the display unit 105 is positioned on the front face of the reselected user.

When the movement of the mobile robot 400 is completed, the descriptor selection unit 407 instructs the problem provision unit 108 to output a problem, extracts a problem other than the previously outputted problem from the storage unit 103, 105 (S541).

Then, the correct answer determining section 109 confirms the correct answer to the question being outputted to the display section 105 in the storage section 103, and whether or not the voice corresponding to the correct answer is recognized is determined by using the speech recognition module 109a Proceed to step S515 for continuous monitoring.

On the other hand, if the correct pattern is not stored in the user information of the storage unit 103, the correct answer determining unit 109 determines that the user does not agree with the pattern of the recognized speech, It is determined that the user is an unregistered user, and a message requesting input of user information is output to the display unit 105 or the speaker. Then, the correct answer determining unit 109 captures a face from the user who has uttered the correct answer, receives the name, maps the pattern of the recognized voice as the correct answer, the face image and the name of the user, .

While the specification contains many features, such features should not be construed as limiting the scope of the invention or the scope of the claims. In addition, the features described in the individual embodiments herein may be combined and implemented in a single embodiment. Conversely, various features described in the singular < Desc / Clms Page number 5 > embodiments herein may be implemented in various embodiments individually or in combination as appropriate.

Although the operations have been described in a particular order in the figures, it should be understood that such operations are performed in a particular order as shown, or that all described operations are performed to obtain a sequence of sequential orders, or a desired result . In certain circumstances, multitasking and parallel processing may be advantageous. It should also be understood that the division of various system components in the above embodiments does not require such distinction in all embodiments. The above-described program components and systems can generally be implemented as a single software product or as a package in multiple software products.

The method of the present invention as described above can be implemented by a program and stored in a computer-readable recording medium (CD-ROM, RAM, ROM, floppy disk, hard disk, magneto optical disk, etc.). Such a process can be easily carried out by those skilled in the art and will not be described in detail.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. The present invention is not limited to the drawings.

100, 400: mobile robot 101: camera
102: driving unit 103:
104: microphone 105:
106: participant recognition unit 107, 407: descriptor selection unit
108: Problem Solving 109: Correct Answer Government
109a: Speech recognition module 110:
406: Voice direction analyzing unit

Claims (19)

A method of providing a quiz game service to a plurality of users in a mobile robot,
A first problem output step of outputting a problem to the screen at a position where the screen is exposed to the problem descriptor;
A correct answer confirming step of confirming whether a correct answer voice is recognized for the question being outputted;
A location recognizing step of re-selecting a user who has uttered the correct answer voice as a problem descriptor and recognizing a position of the re-selected problem descriptor when the correct answer voice is recognized as the confirmation result;
Moving to a position distant from the recognized position by a predetermined distance so that the screen is exposed to the re-selected problem descriptor; And
And outputting a next question on the screen in the moved area. The method for providing a quiz game service in a mobile robot, The method according to claim 1,
The position recognition step may include:
And recognizing the position of the re-selected problem descriptor on the basis of the stored user-specific location information. 3. The method of claim 2,
Before the first question output step,
Identifying each user by recognizing faces of each user participating in the game using a camera; And
Further comprising confirming and storing position information of each of the recognized users with reference to map data in which coordinates information of a space in which the quiz game is played is recorded, and storing the quiz game service in the mobile robot Way. The method of claim 3,
Wherein the identifying comprises:
And if the face of the user who participated in the game is not recognized, acquires and stores the voice pattern, the name and the face image of the unrecognized user. 4. The method according to any one of claims 1 to 3,
The position recognition step may include:
Identifying a pattern of the correct answer voice and identifying a user who has uttered the correct answer by confirming the user name mapped with the pattern of the correct answer voice in the user information being stored; And
And increasing a number of correct answers or a quiz score of the identified user. 6. The method of claim 5,
After the next problem output step,
And checking and outputting a correct answer number or a quiz score for each user participating in the quiz game when the quiz game ends, and outputting the quiz game. A mobile robot for providing a quiz game service to a plurality of users,
A display unit for outputting a problem;
Storing a plurality of problems;
A problem-solving unit for extracting a problem from the storage unit at a location where the display unit is exposed to the problem descriptor and outputting the extracted problem to the display unit;
A correct answer determining unit for determining whether a correct answer voice for the question in the output is recognized and, when a correct answer voice is recognized, a user who has uttered the correct answer voice as a correct answer; And
And a control unit that recognizes the position of the re-selected problem descriptor by re-selecting the correct answer identified by the correct answer determination unit as a problem descriptor, And a descriptor selection unit for moving the robot,
Wherein when the movement of the mobile robot is completed in the direction of the reselected problem descriptor, the problem providing unit extracts the next problem from the storage unit and outputs the extracted problem to the display unit. 8. The method of claim 7,
The storage unit stores location information for each user,
Wherein the descriptor selection unit recognizes the position of the re-selected problem descriptor based on the per-user location information. 9. The method of claim 8,
Recognizing the faces of each user participating in the game using the camera, identifying each user, checking the position information of each recognized user with reference to the map data in which the coordinate information of the space in which the quiz game is performed is recorded, And a participant recognition unit for storing the participant information in a storage unit. 10. The method of claim 9,
The participant recognizing unit,
And if the face of the user participating in the game is not recognized, acquires the voice pattern, the name and the face image of the unrecognized user, and stores the voice pattern, the name and the face image in the storage unit. 9. The method of claim 8,
Wherein,
Identifying a user who has uttered the correct answer by checking the user name mapped with the pattern of the correct answer voice in the storage unit, and increasing the correct answer frequency or quiz score of the identified user. 12. The method of claim 11,
And a game result providing unit for confirming and outputting a correct answer number or a quiz score for each user participating in the quiz game when the quiz game ends. A mobile robot for providing a quiz game service to a plurality of users,
A display unit for outputting a problem;
Storing a plurality of problems;
A plurality of microphones mounted on left and right sides of the mobile robot, respectively;
A problem-solving unit for extracting a problem from the storage unit at a location where the display unit is exposed to the problem descriptor and outputting the extracted problem to the display unit;
A correct answer determining unit for determining whether a correct answer voice for the question is recognized and, when a correct answer voice is recognized, a user who has uttered the correct answer voice as a correct answer;
A voice direction analyzer for analyzing a frequency of the correct answer voice received from the plurality of microphones to determine a speaking direction of the correct answer voice; And
The face recognition unit recognizes the face and the position of the problem descriptor by re-selecting the correct answer identified by the correct answer determination unit as the problem descriptor, changing the photographing angle in the speaking direction of the correct answer voice analyzed by the voice direction analyzing unit, And a descriptor selection unit for moving the mobile robot to a position spaced apart from the recognized position by a predetermined distance so that the display unit is exposed to the problem descriptor,
Wherein when the movement of the mobile robot is completed in the direction of the reselected problem descriptor, the problem providing unit extracts the next problem from the storage unit and outputs the extracted problem to the display unit. 14. The method of claim 13,
The voice direction analyzing unit,
If the difference between the right answer voice and the right answer voice received from the microphone installed on the left side face and the microphone installed on the right side face is higher than a predetermined threshold strength, Is determined to be the ignition direction of the mobile robot. 14. The method of claim 13,
The voice direction analyzing unit,
If the difference between the correct answer voice and the right answer speech strength received from the microphone installed on the left side face and the microphone installed on the right side face is lower than a predetermined threshold strength, then the speaking direction of the correct answer voice is the backward direction of the mobile robot The mobile robot comprising: 14. The method of claim 13,
The voice direction analyzing unit,
If the time difference of the correct answer voice received by the microphone provided on the left side face and the microphone provided on the right side face is lower than a preset threshold time, the direction of the microphone where the correct answer voice is first received is the speech of the correct answer voice Direction of the mobile robot. 14. The method of claim 13,
The voice direction analyzing unit,
If the time difference of the correct answer speech received by the microphone provided on the left side face and the microphone provided on the right side face is lower than a preset threshold time, the speech direction of the correct answer voice is determined to be the backward direction of the mobile robot Wherein the mobile robot is a mobile robot. 18. The method according to any one of claims 13 to 17,
Wherein,
Identifying a user who has uttered the correct answer by checking the user name mapped with the pattern of the correct answer voice in the storage unit, and increasing the correct answer frequency or quiz score of the identified user. 18. The method according to any one of claims 13 to 17,
The descriptor selection unit
Recognizing a face of the re-selected problem descriptor based on the face image by checking the face image of the user mapped with the pattern of the correct answer voice in the storage unit and recognizing the face of the re- And recognizes the position of the re-selected problem descriptor on the basis of the position of the problem descriptor.

Images