JP2022163281A - robot - Google Patents

Abstract

To provide a robot capable of communicating with a human more closely than a conventional robot that is simply operated following music.SOLUTION: A rhythm robot 10 includes: a feature amount detection unit 32 for detecting a feature amount of an aggregate of a plurality of sounds when the aggregate of the plurality of sounds uttered from a user Ua is recorded by a recording unit 18 and acquired by a sound acquisition unit 31; and an output control unit 38 for executing control to output an aggregate of a plurality of sounds having a feature amount the same as the detected feature amount or a feature amount, a part of which is in common with the detected feature amount toward the user Ua in a mode determined by an output mode determination unit 36.SELECTED DRAWING: Figure 3

Description

The present invention relates to robots.

Japanese Patent Laid-Open No. 2002-200001 describes a motion control device that aims to keep the motion of a robot following the music even when the tempo of the music changes. The motion control device calculates the current bar and beat based on the tick, time base, and time signature included in the MIDI information of the music being played. determines whether or not it is time to perform a specific action. Then, an operation instruction is output based on the determination processing result.
Patent Literature 2 describes a robot device intended to improve entertainment. The robot device extracts a rhythm from music based on the supplied music data, determines the range of the average moving speed of each arm based on the rhythm, and selectively reads out motion patterns that match the range.

JP 2017-196675 A Japanese Patent Application Laid-Open No. 2005-231012

"Robots" for humans are said to be distinct from general electrical appliances. In other words, it can be said that robots are close to, or can substitute for, family and friends, caring for people's minds through communication, which is not possible with ordinary electrical appliances. In addition, it can be said that such an existence is the original significance of the robot's existence. However, in robots that follow music and move as in Patent Documents 1 and 2, it is necessary to make large-scale movements such as limbs and body movements in order to fully communicate with people. In addition, there was a limit to the variation of expressions used for communication.

SUMMARY OF THE INVENTION An object of the present invention is to provide a robot capable of communicating with a person more strongly than a conventional robot that only moves according to music.

According to the invention recited in claim 1, when a set of first plurality of sounds emitted from the outside is input, detection means for detecting a feature amount of the set of first plurality of sounds; an output means for outputting a second plurality of sets of sounds having a feature amount that is the same as or partly common to the feature amount that is set to the outside in a predetermined manner.
In the invention described in claim 2, the detection means acquires a set of a plurality of collision sounds or a melody composed of a plurality of sounds as the set of the first plurality of sounds, and obtains the plurality of collision sounds. or the feature amount of each of the melody consisting of a plurality of sounds, and the output means directs the melody or rhythm sound as the second set of sounds to the outside in a predetermined manner. 2. The robot according to claim 1, which outputs by
The invention recited in claim 3 is the robot according to claim 2, wherein the output means outputs the melody or rhythm sound to the outside in a manner selected by the user.
According to the fourth aspect of the invention, the melody or rhythm sound output to the outside by the output means is a set of a plurality of collision sounds as the first set of sounds or a plurality of sounds. 4. The robot according to claim 3, wherein the melody is a melody or rhythm sound obtained by performing predetermined processing on the melody.
The invention recited in claim 5 further comprises receiving means for receiving an input of information relating to characteristics of a user, and said outputting means outputs said melody in a mode in consideration of the information relating to said characteristics of said user received by said receiving means. Alternatively, the robot according to claim 2, which outputs rhythm sounds to the outside.

ADVANTAGE OF THE INVENTION According to this invention, the robot which can take stronger communication with a person can be provided compared with the conventional robot which only follows music and moves.

It is a figure which shows the hardware constitutions of the rhythm robot system to which this Embodiment is applied. FIG. 2 is a diagram showing the hardware configuration of a rhythm robot; FIG. FIG. 4 is a diagram showing a functional configuration of a rhythm robot; FIG. It is a figure which shows the functional structure of a server. 4 is a flow chart showing the flow of processing of the rhythm robot; 4 is a flow chart showing the flow of server processing. FIG. 10 is a diagram showing a specific example of a mode of a set of sounds output from a rhythm robot in response to a set of sounds uttered by a user; FIG. 4 is a diagram showing a specific example of a user interface; (A) is a diagram showing a specific example of a user interface displayed on the rhythm robot and the user terminal when user information is input. (B) is a diagram showing a specific example of a user interface displayed on the rhythm robot and the user terminal when setting the output mode.

[Hardware configuration of the rhythm robot system]
BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
FIG. 1 is a diagram showing the hardware configuration of a rhythm robot system 1 to which this embodiment is applied.
The rhythm robot system 1 is a system that implements a "rhythm robot service" (hereinafter referred to as "this service") provided by a service provider to users Ua and Ub. This service entertains the user Ua by using a rhythm robot 10 that responds to a set of sounds uttered by the user Ua and outputs a set of sounds that match the set of sounds. Service. A rhythm robot system 1 that implements this service includes a rhythm robot 10, a user terminal 50, and a server 70, which are connected to a network 90 such as the Internet.

The user Ua emits a set of sounds toward the rhythm robot 10 while interacting with the rhythm robot 10, and enjoys the response of the rhythm robot 10 to the set of sounds. The user Ua of the present embodiment includes infants and elderly people. The "set of multiple sounds" emitted by the user Ua includes a set of multiple collision sounds, a melody composed of multiple sounds, and the like. Examples of the "set of multiple collision sounds" include rhythm sounds such as clapping that are generated when parts of the user Ua's body collide, and rhythm sounds that are generated when playing musical instruments such as castanets and tambourines. mentioned. The "melody consisting of a plurality of sounds" includes, for example, a set of sounds such as a humming sound produced by singing by the user Ua, and a set of sounds produced by playing a musical instrument such as a recorder or a keyboard harmonica.

Also, the user Ub is a person who performs input operations for various settings of the rhythm robot 10 . Examples of the user Ub in the present embodiment include mothers, nursery teachers, and caregivers who are in a position to manage or protect the user Ua. Infants and the elderly as user Ua, and mothers, nursery teachers, and caregivers as user Ub use this service to realize support for healthy child-rearing and support for maintaining the health of the elderly. . In this specification, when it is not necessary to distinguish between the user Ua and the user Ub, they are collectively referred to as "user U". The user U also includes a person who has not yet started using this service but wishes to use this service.

A rhythm robot 10 that constitutes the rhythm robot system 1 generates a set of sounds that have the same or a part of the same features as a set of sounds emitted by the user Ua, and generates various variations such as rhythm sounds and singing. output in the form. Specifically, when the user Ua clap, hum, or sing a set of sounds in a certain rhythm, the rhythm robot 10 adjusts the rhythm to the rhythm, tempo, or the like. Outputs and sings the rhythm sound of Hereinafter, the mode of output when the rhythm robot 10 outputs a set of sounds will be referred to as "output mode". The details of the variation of the output mode will be described later with reference to FIG.

Basically, the rhythm robot 10 determines, as an output mode, the mode of a set of sounds that are the same as or partly common to the feature amount, based on the feature amount of the set of sounds uttered by the user Ua. and output. At this time, the rhythm robot 10 can take into consideration the user information of the user Ua when determining the output mode. The user Ua or the user Ub can arbitrarily set whether or not to take the user information into consideration when determining the output mode. If the user information is taken into consideration when determining the output mode, the rhythm robot 10 acquires the user information of the user Ua. "User information" means information about the user Ua. The user information of the user Ua includes, for example, the user Ua's name, address, age, gender, name and genre of favorite music, and other information. A specific example in which user information is taken into account when determining the output mode will be described later with reference to FIG.

The rhythm robot 10 acquires user-related information received as a result of an input operation by the user Ua or the user Ub as user information on the user Ua, and stores and manages it in the user information DB 41 . Note that the "input operation" here includes a manual input operation to the user interface displayed on the screen of the rhythm robot 10, a voice input operation to a microphone or the like, and a gesture input operation to a camera or the like.

In addition to the information input by the user Ua or the user Ub, user Ua's utilization history of the service, such as the history of the set of sounds output from the rhythm robot 10, is also acquired as user information. Furthermore, in the case where the user Ua has separately registered user information in another service other than this service, and there is a provision regarding the interchange of the user information of the user Ua between this service and the other service. Sometimes. In such a case, subject to the consent of the user Ua or the user Ub who acts for the user Ua, the information already registered as the user information of the user Ua in other services may also be used as the user information of the user Ua in this service. is obtained. Specifically, the user information of the user Ua is acquired from an external server (not shown) such as a server that manages other services.

Further, when the user Ua or the user Ub designates a part of the output mode, the rhythm robot 10 generates a plurality of sounds having the same feature amount or a part thereof as a set of sounds emitted by the user Ua. A set of sounds is output in an output mode designated by user Ua or user Ub. The reason why "partial" of the output mode can be specified is as follows. In other words, assuming that "all" of the set of sounds output from the rhythm robot 10 can be designated in advance, the set of sounds emitted by the user Ua and the set of sounds output from the rhythm robot 10 can be designated in advance. This is because the relevance to the collection of the information may become weak, and the purpose of this service, which is to communicate through sound, may be lost.

Specifically, for example, it is assumed that "high-tempo rhythm sound" is specified as part of the output mode. In this case, even if a setting is made to the effect that the user information is taken into consideration when determining a part of the output mode, and the fact that the age of the user Ua is 85 years old is included in the user information in advance, The specified output mode of "high tempo rhythm sound" is preferentially output. In the case where both the setting that the user information of the user Ua is taken into consideration when determining the output mode and the designation of a part of the output mode are performed in advance, it is possible to determine which one should be applied preferentially. , can be preset by the user Ua or the user Ub. It should be noted that the setting regarding such priority application and the specification of a part of the output mode described above are both performed by the user Ua or the user Ub through input operations.

Also, the rhythm robot 10 stores and manages various kinds of information in a database. For example, as described above, the acquired user information of the user Ua is stored and managed in the user information DB 41 provided in one area of the storage unit 13 shown in FIG. 2, which will be described later. Also, for example, the rhythm robot 10 stores and manages a plurality of pieces of content information provided by the server 70 in a content information DB 42 provided in one area of the storage unit 13 shown in FIG. 2, which will be described later. The “content information” is data of songs to be sung as candidates for a set of sounds output from the rhythm robot 10 . The content information includes information stored in advance in each of the content information DB 42 and the content information DB 82 of the server 70, which will be described later, and information obtained as appropriate from an external server or the like (not shown). The content information is associated with identification information that uniquely identifies the content, and is managed in such a manner that it can be extracted at any time using this identification information as a key.

The rhythm robot 10 can function as a network type robot that constitutes the rhythm robot system 1 as described above, but it can also temporarily function as a stand-alone type robot in places where the communication environment is poor. In addition, it can be made to function as a stand-alone type robot that does not have a communication function from the beginning.

A user terminal 50 that configures the rhythm robot system 1 is configured by a smart phone, a tablet, a personal computer, or the like. The user terminal 50 is possessed by the user Ub or placed in a space where the user Ub lives or works. The user terminal 50 receives an input operation from the user Ub. For example, the user terminal 50 accepts an input operation for registering user information in this service. Note that the “input operation” here includes a manual input operation to the user interface displayed on the screen of the user terminal 50, a voice input operation to a microphone or the like, and a gesture input operation to a camera or the like.

When the user terminal 50 is composed of a smart phone, a tablet, or a personal computer, dedicated application software (hereinafter referred to as “dedicated application”) that enables use of this service can be installed on the user terminal 50 . In addition, even if the dedicated application is not installed, the service can be used by accessing a dedicated website that enables the use of the service using the browser function of the user terminal 50.例文帳に追加

The server 70 that configures the rhythm robot system 1 is an information processing device that controls the entire system, and provides the user terminal 50 with a dedicated application, for example. The server 70 also stores and manages various kinds of information in a database. Specifically, the server 70 stores the acquired user information in a user information DB 81 provided in one area of a storage section (not shown) having the same function as the storage section 13 of FIG. 2, which will be described later. to manage. In addition, the server 70 stores and manages the acquired content information in a content information DB 82 provided in one area of a storage unit (not shown) having the same function as the storage unit 13 of FIG. 2, which will be described later. . The server 70 transmits part or all of the information stored and managed in these databases to the rhythm robot 10 and the user terminal 50 as necessary.

As described above, user information and content information are stored in databases of rhythm robot 10 and server 70, respectively. Not limited. For example, the information stored in the database of the rhythm robot 10 and the information stored in the database of the server 70 are completely synchronized at a predetermined timing (eg, real time, hourly, minutely, secondly). It may be configured to In the case of such a configuration, it is possible to further enhance the variation of the form of the set of sounds output from the rhythm robot 10 .

Also, for example, the rhythm robot 10 does not acquire user information on its own, and only one or more pieces of content information arbitrarily selected by the user Ub from among the information stored in the database of the server 70 are provided to the rhythm robot 10. It may be configured to With such a configuration, the amount of information stored by the rhythm robot 10 can be minimized, so the load on the database of the rhythm robot 10 can be reduced.

[Configuration of rhythm robot]
FIG. 2 is a diagram showing the hardware configuration of the rhythm robot 10. As shown in FIG.
The rhythm robot 10 is composed of a so-called communication robot that incorporates a computer device. The rhythm robot 10 has a control section 11 that is a CPU (Central Processing Unit) that controls the entire robot, a memory 12 such as a RAM (Random Access Memory) that is used as a work area for calculation, and programs and various setting data. It has a storage unit 13 which is a storage device such as an HDD (Hard Disk Drive) used for storage and a semiconductor memory. It also has a communication unit 14 that transmits and receives data via the network 90 . Further, an operation unit 15 such as a touch panel for receiving input operations from the user U, a display unit 16 such as a liquid crystal display for displaying images and text information to the user U, and a display control unit for controlling the display unit 16. 17. It also has a recording unit 18 such as a microphone for recording sounds emitted by the user, and an audio output unit 19 such as a speaker for outputting audio to the user U. FIG. Further, it has an imaging unit 20 including a camera or the like for capturing an image of the gesture of the user U and acquiring it as information of a still image or a moving image.

The hardware configuration of the user terminal 50 that constitutes the rhythm robot system 1 is similar to the hardware configuration of the rhythm robot 10 shown in FIG. The hardware configuration of the server 70 that constitutes the rhythm robot system 1 is similar to the hardware configuration of the rhythm robot 10 shown in FIG. ing. Therefore, descriptions of the hardware configurations of the user terminal 50 and the server 70 are omitted.

FIG. 3 is a diagram showing the functional configuration of the rhythm robot 10. As shown in FIG.
The rhythm robot 10 has a sound acquisition section 31 that acquires information on a set of sounds, and a feature amount detection section 32 that detects a feature amount of the set of sounds. It also has a user information acquisition unit 33 that acquires the user information of the user Ua, and a user information storage unit 34 that stores the user information of the user Ua. Also, an output mode accepting unit 35 that accepts specification of the mode of the set of sounds output by the rhythm robot 10, and an output mode determination unit 36 that determines the mode of the set of sounds output by the rhythm robot 10. have It also has a processing unit 37 that processes the form of the set of sounds output by the rhythm robot 10, and an output control unit 38 that controls the output of the set of sounds.

When a set of sounds emitted from the outside by user Ua's actions such as clapping, humming, and singing is input, the set of input sounds is recorded by the recording unit 18 shown in FIG. 2 described above. The sound acquisition unit 31 acquires information on a set of recorded sounds.

The feature amount detection unit 32 detects feature amounts of a set of sounds in the information acquired by the sound acquisition unit 31 . Specifically, the feature amount detection unit 32 detects, for example, a feature amount of a set of multiple collision sounds and a feature amount of a melody composed of a plurality of sounds as the feature amount of the set of multiple sounds. The "feature amount of a set of sounds" includes tempo, rhythm, volume, tone, speed, and the like. Note that details of the feature amount of a set of sounds will be described later with reference to FIG. 7 .

The user information acquisition unit 33 acquires the user information of the user Ua input by the input operation of the user Ua or the user Ub. In addition, the user information acquisition unit 33 acquires the usage history of this service by the user Ua as user information. In addition, the user information acquisition unit 33 acquires information that has been approved by the user Ua (or the user Ub who acts for the user Ua) among the information already registered as the user information of the user Ua in other services. Acquired as user information of the user Ua in the service.

The user information storage unit 34 stores and manages the user information of the user Ua acquired by the user information acquisition unit 33 in the user information DB 41 . Specifically, the user information storage unit 34 associates the user information with identification information that uniquely identifies the user Ua, and manages the user information in a manner that can be extracted at any time using the identification information as a key.

The output mode accepting unit 35 accepts designation of part of the output mode. Specifically, when an input operation for specifying a part of the output mode is performed, the output mode accepting unit 35 accepts the specification. As described above, the input operation includes a manual input operation to a user interface, an input operation by voice to a microphone or the like, an input operation by a gesture to a camera or the like, and the like. A specific example of the user interface for designating the output mode will be described later with reference to FIG. 8(B).

The output mode determining unit 36 determines an output mode for a plurality of sound sets having the same or partially common feature amount as the feature amount of the set of sounds detected by the feature amount detection unit 32 . Further, when the specification of the output mode is received by the output mode receiving section 35, the output mode determination section 36 makes a determination according to the specification. In addition, when the output mode determination unit 36 is set to take user information into account when determining the output mode, the output mode determination unit 36 makes a determination according to the setting. In addition, the output mode determination unit 36 may determine the output mode based on, for example, a predetermined selection criterion or a result of AI (artificial intelligence) learning the usage history of the user Ua. Further, when a part of the output mode is determined by the server 70, the output mode determining unit 36 reflects the content of the determination by the server 70 when determining the output mode.

The processing unit 37 performs processing for making the output mode the output mode determined by the output mode determination unit 36 . Specifically, for example, when the determination of the output mode determining unit 36 is in accordance with the designation received by the output mode receiving unit 35, the processing unit 37 causes the output mode receiving unit 35 to set the output mode to Perform processing to achieve the specified output mode. Further, for example, when the determination of the output mode determination unit 36 is in accordance with the setting to the effect that the user information is taken into consideration when determining the output mode, the processing unit 37 determines the output mode to be based on the user information. Processing for output mode is performed. It should be noted that there is no particular limitation as to what method the processing unit 37 uses to process the set of sounds. may In this case, the processing unit 37 processes a set of sounds by methods such as waveform editing, noise removal, volume adjustment, frequency adjustment, sound pressure adjustment, breath removal, pitch adjustment, intonation adjustment, and timbre adjustment.

The output control section 38 performs control to output a set of sounds in the output mode determined by the output mode determination section 36 . Specifically, the output control unit 38 controls the audio output unit 19 shown in FIG. The timing at which the output control unit 38 outputs a set of sounds is not particularly limited. For example, when information on a set of sounds uttered by the user Ua is acquired, the output mode may be determined and processed immediately, and the sounds may be output from the audio output unit 19 . Alternatively, for example, after information on a set of sounds is acquired, the output mode may be determined and processed while a preset time elapses, and output from the sound output unit 19. good. In this case, the "preset time" can be arbitrarily set by the user Ua or the user Ub, for example, "after 1 second" or "after 3 seconds".

[Server configuration]
FIG. 4 is a diagram showing the functional configuration of the server 70. As shown in FIG.
The server 70 includes a user information acquisition section 71 that acquires user information, a user information storage section 72 that stores user information, and a user information transmission control section that controls transmission of part or all of the user information to the rhythm robot 10. 73. It also has an output mode accepting section 74 that accepts designation of a part of the mode of a set of sounds to be output by the rhythm robot 10, and an output mode determining section 75 that determines a part of the output mode. It also has an output mode transmission control section 76 for controlling transmission of the content of the determination to the rhythm robot 10 .

The user information acquisition unit 71 acquires the user information of the user Ua input by the user U's input operation. In addition, the user information acquisition unit 71 acquires the usage history of this service by the user Ua as the user information of the user Ua. In addition, the user information acquisition unit 71 acquires information that has been approved by the user Ua (or the user Ub who acts for the user Ua) among the information that has already been registered as the user information of the user Ua in other services. Acquired as user information of the user Ua in the service.

The user information storage unit 72 stores and manages the user information of the user Ua acquired by the user information acquisition unit 71 in the user information DB 81 . Specifically, the user information storage unit 72 associates the user information with identification information that uniquely identifies the user Ua, and manages the user information in a manner that can be extracted at any time using the identification information as a key.

The user information transmission control section 73 controls transmission of part or all of the user information stored in the user information DB 81 to the rhythm robot 10 . The user Ua or Ub can arbitrarily set whether or not to transmit user information from the server 70 to the rhythm robot 10 and the items of user information to be transmitted.

The output mode accepting unit 74 accepts designation of a part of the output mode. Specifically, when an input operation for specifying a part of the output mode is performed, the specification is accepted. This input operation includes a manual input operation to the user interface of the user terminal 50, a voice input operation to a microphone or the like, a gesture input operation to a camera or the like, and the like. A specific example of the user interface for specifying part of the output mode will be described later with reference to FIG. 8(B).

When the output mode accepting portion 74 accepts the specification of a part of the output mode, the output mode determining portion 75 makes a determination according to the specification. In addition, when the output mode determination unit 75 is set to consider the user information when determining the output mode, the output mode determination unit 75 makes a determination according to the setting. In addition, the output mode determination unit 75 may determine a part of the output mode, for example, based on predetermined selection criteria or results of machine learning using AI (artificial intelligence). When part of the output mode is determined by the output mode determination section 75 , the output mode transmission control section 76 performs control to transmit the determined content to the rhythm robot 10 .

[Rhythm robot processing]
Next, the processing of the rhythm robot 10 will be explained using FIG.
FIG. 5 is a flow chart showing the processing flow of the rhythm robot 10. As shown in FIG.
When the user information of the user Ua is input by the input operation of the user Ua or the user Ub (YES in step 101), the user information acquiring unit 33 acquires the user information of the user Ua input by the input operation of the user Ua or the user Ub. Information is obtained (step 102). The user information of the user Ua acquired by the user information acquisition unit 33 is stored and managed in the user information DB 41 by the user information storage unit 34 . On the other hand, if the user information of the user Ua has not been input (NO in step 101), the process proceeds to step 103 for determination.

When a part of the output mode is specified by the input operation of the user Ua or the user Ub (YES in step 103), the output mode accepting unit 35 accepts the specification, and the output mode determining unit 36 selects the output mode according to the specification. A portion is determined (step 104). On the other hand, if part of the output mode is not specified (NO in step 103), the process proceeds to step 105 for determination.

When a set of sounds uttered by the user Ua is input (YES in step 105), the recording unit 18 records the set of sounds, and the sound acquisition unit 31 collects the recorded sounds. Get information about the set of . (Step 106). On the other hand, if a set of multiple sounds has not been input (NO in step 105), the determination of step 105 is repeated until a set of multiple sounds is input.

The feature quantity detection unit 32 detects the feature quantity of a set of sounds in the information acquired by the sound acquisition unit 31 (step 107). The output mode determination unit 36 determines the output mode of a plurality of sound sets having the same feature amount or a feature amount that is partially common to the feature amount of the plurality of sound sets detected by the feature amount detection unit 32 (step 108). Here, when the designation of the output mode is received by the output mode receiving unit 35, determination is made according to the designation. In addition, if a setting is made to consider the user information of the user Ua when determining the output mode, the determination is made according to the setting.

The processing unit 37 performs processing to achieve the output mode determined by the output mode determination unit 36 (step 109). Here, when the output mode determined by the output mode determination unit 36 is in accordance with the designation of the user Ua or the user Ub, the processing unit 37 processes a plurality of Process a set of sounds. Further, when the output mode determined by the output mode determination unit 36 is in accordance with the setting to the effect that the user information of the user Ua is taken into consideration, the processing unit 37 determines that the user information of the user Ua is added A set of multiple sounds is processed so as to have an output mode. The output control unit 38 performs control to output a set of sounds in the output mode determined by the output mode determination unit 36 (step 110).

[Server processing]
Next, processing of the server 70 will be described using FIG.
FIG. 6 is a flow chart showing the processing flow of the server 70. As shown in FIG.
When user Ua's user information is input by user U's input operation (YES in step 701), user information acquisition unit 71 acquires user Ua's user information input by user Ua's or user Ub's input operation. (step 702). The user information of the user Ua acquired by the user information acquisition unit 71 is stored and managed in the user information DB 81 by the user information storage unit 72 . The user information transmission control section 73 controls transmission of part or all of the user information of the user Ua stored in the user information DB 81 to the rhythm robot 10 (step 703). On the other hand, if the user information of the user Ua has not been input (NO in step 701), the process proceeds to step 704 for determination.

When a part of the output mode is specified by the input operation of user Ua or user Ub (YES in step 704), output mode accepting unit 74 accepts the specification, and output mode determining unit 75 selects the output mode according to the specification. A portion is determined (step 705). When a part of the output mode is determined, the output mode transmission control section 76 performs control to transmit the content of the determination to the rhythm robot 10 (step 706). On the other hand, if part of the output mode is not specified (NO in step 704), the process ends without part of the output mode being specified.

As described above, according to the rhythm robot system 1 to which the present embodiment is applied, when the user Ua clap or hum in a certain rhythm while interacting with the rhythm robot 10, the rhythm robot 10 It sings a song or outputs a rhythm sound in accordance with the rhythm and tempo as if communicating with the user Ua. At this time, the singing and rhythm sounds output from the rhythm robot 10 are the result of the user Ua clapping or humming toward the rhythm robot 10 and then modulating, harmonizing, and so on. The user Ua can enjoy the change.

Further, as described above, in this service, the output mode can be designated by the input operation of the user Ua or the user Ub. A point worthy of special mention here is that the rhythm robot 10 can acquire the user information of the user Ua and determine the output mode by its own judgment. In other words, the rhythm robot 10 can change the output mode according to the individual characteristics of the user Ua. As a result, it is possible to change to a mode suitable for, for example, the case where the user Ua is an infant and the case where the user Ua is an elderly person. As a result, an infant and an elderly person as the user Ua can enjoy communication with the rhythm robot 10 through sound, which makes it possible to support sound parenting and maintain the health of the elderly.

〔Concrete example〕
Next, a specific example of this service will be described with reference to FIGS. 7 and 8. FIG.
FIG. 7 is a diagram showing a specific example of a set of sounds output from the rhythm robot 10 in response to a set of sounds uttered by the user Ua.

FIG. 7 shows the relationship between the types of sets of sounds emitted by the user Ua's actions, the output modes of the rhythm robot, and variations thereof. For example, when the user Ua clap, the rhythm robot 10 that listens to the clap outputs a rhythm sound that has the same or a part of the feature amount as the user Ua's clapping. At this time, variations of the rhythm sound output from the rhythm robot 10 include tempo, rhythm, volume, tone, speed, specific sound, response to user information, and the like.

Here, it is assumed that the user U has specified the tempo and tone when rhythm sounds are to be output as part of the specification of the output mode. In this case, for example, when the user Ua clapping at a certain tempo and tone, the rhythm robot 10 outputs rhythm sounds processed to a predesignated tempo and tone. It is also assumed that the volume at which rhythm sounds are to be output has been specified as part of the specification of the output mode. In this case, for example, when the user Ua clapping at a certain volume, the rhythm robot 10 outputs rhythm sounds processed to a volume specified in advance.

It is also assumed that the user U has designated a particular sound as a sound when a rhythm sound is to be output as part of the output mode. In this case, for example, when the user Ua clapping at a certain tempo and tone, the rhythm robot 10 outputs a rhythm sound processed into a specific sound specified in advance. Here, the "specific sound" includes the sound of a drum, an electronic sound, a whistle, a clapper, a sound of an object falling into water, an animal's cry, and the like. It is also assumed that the user U has designated a specific voice as a voice when singing is output as part of the output mode. In this case, for example, when the user Ua sings with a certain tempo and tone, the rhythm robot 10 outputs a song processed into a specific voice specified in advance. Here, the "specific voice" includes the voice of a character that is popular with young children.

It is also assumed that user information of the user Ua, such as age, gender, name and genre of favorite music, is taken into consideration when determining the output mode. In this case, the rhythm robot 10 can select and output high-tempo rhythm sounds and singing that infants seem to like, for example, as an output mode that takes into account the user information that the user Ua is "5 years old". Also, for example, as an output mode that takes into account the user information that the user Ua is "85 years old", it is possible to select and output low-tempo rhythm sounds and singing that elderly people seem to like. In this case, the rhythm robot 10 adjusts the tempo of the output rhythm sounds and singing by controlling, for example, a value BPM (Beats Per Minute) representing the number of beats per minute. Specifically, for example, it is assumed that the tempo, which is the characteristic value of the clapping sound of an infant (user Ua), is 120 BPM. In this case, the rhythm robot 10 adjusts the BPM so that a high-tempo rhythm sound of 140 BPM that infants seem to like is output.

FIG. 8 is a diagram showing a specific example of the user interface. FIG. 8A is a diagram showing a specific example of the user interface displayed on the rhythm robot 10 and the user terminal 50 when user information is input. FIG. 8B is a diagram showing a specific example of the user interface displayed on the rhythm robot 10 and the user terminal 50 when setting the output mode.

When user Ua or user Ub (mainly user Ub) registers the user information of user Ua, the user inputs user information into a user interface as shown in FIG. 8A, for example. The user interface illustrated in FIG. 8A can be displayed on the screens of the rhythm robot 10 and the user terminal 50 respectively. The user Ua or the user Ub can arbitrarily select whether or not to register the user information of the user Ua and the items to be registered as the user information of the user Ua. In other words, whether or not the user information of user Ua is registered is not essential information for using this service. be the necessary information.

When user Ua or user Ub (mainly user Ub) specifies the output mode, the user specifies the output mode using a user interface as shown in FIG. 8B, for example. The user interface illustrated in FIG. 8B can be displayed on the screens of the rhythm robot 10 and the user terminal 50 respectively. As shown in FIG. 8B, for example, the output mode can be specified for output target, processing presence/absence, modulation, harmonization, user information application/non-applicability, desired sound/voice, and the like. Note that the output mode items shown in the user interface of FIG. 8B are merely examples.

Among the output mode items shown in the user interface of FIG. 8B, "output target" is an item that specifies the type of user Ua for whom the rhythm robot 10 outputs a set of multiple sounds. . In the example of FIG. 8B, "infant" or "elderly" can be selected as the "output target". When "infant" is selected as the "output target", the output mode is determined taking into consideration that the user Ua is an "infant". Songs for young children such as nursery rhymes are preferentially output. Further, when the "elderly" is selected as the "output target", the output mode is determined in consideration of the fact that the user Ua is an "elderly", so for example the rhythm robot 10 outputs singing. In this case, songs for the elderly such as Enka and Showa Kayo are preferentially output.

Among the output mode items shown in the user interface of FIG. 8(B), "processing presence/absence" is an item that specifies whether or not to process a set of sounds emitted by the user Ua. be. When "yes" is selected for "with or without processing", items such as "modulation", "harmony", "with or without user information application", and "desired sound/voice" become active. Then, the rhythm robot 10 outputs a processed set of a plurality of sounds uttered by the user Ua. On the other hand, when "no" is selected, each item such as "modulation", "harmony", "whether or not user information is applied", and "desired sound/voice" becomes inactive. Then, the set of sounds uttered by the user Ua is output from the rhythm robot 10 like a parrot return without being processed.

Among the output mode items shown in the user interface of FIG. 8(B), "modulation" designates whether or not to add "modulation" to a set of sounds emitted by the user Ua. It is an item to do. When "yes" is selected for "modulation", the rhythm robot 10 outputs a set of sounds uttered by the user Ua that have been "modulated". In this case, it is possible to specify the output mode as listed in the variation item in FIG. 7, for example. On the other hand, if "none" is selected for "modulation", any one or more items other than "modulation" are processed for the manner of a set of a plurality of sounds uttered by user Ua. is output from the rhythm robot 10.

Among the output mode items shown in the user interface of FIG. 8(B), "harmony" is an item for specifying whether or not to add "harmony" to a set of a plurality of sounds uttered by the user Ua. is. When "yes" is selected for "harmony," the rhythm robot 10 outputs a set of sounds uttered by the user Ua with "harmony." On the other hand, if "none" is selected for "harmony," then any one or more items other than "harmony" are processed for the mode of the set of a plurality of sounds uttered by the user Ua. is output from the rhythm robot 10.

Among the items of the output mode shown in the user interface of FIG. 8B, "whether to apply user information" is for setting whether or not user information is taken into consideration when determining the output mode. item. When "yes" is selected for "whether user information is applied", user information is taken into account when the output mode is determined. On the other hand, if "no" is selected for "whether user information is applied", user information is not taken into account when the output mode is determined.

Among the output mode items shown in the user interface of FIG. , characters, animals, and the like. If "yes" is selected for "desired sound/voice", the rhythm robot is a set of sounds uttered by the user Ua converted into sounds/voices of a specific person, character, animal, etc. 10 is output. In addition, as shown in FIG. 8B, on the right side of the area labeled "Please select the sound/voice to be set", a plurality of persons, characters, animals, names of sounds, etc. can be selected. displayed in the form. On the other hand, if "none" is selected, any one or more items other than the "desired sound/voice" are processed for the form of the set of sounds uttered by the user Ua. is output from the rhythm robot 10.

Although the embodiment has been described above, the present invention is not limited to the embodiment described above. Moreover, the effects of the present invention are not limited to those described in the above embodiment. For example, in the above-described embodiment, clapping, humming (singing), and performance by a musical instrument are cited as examples of a set of sounds emitted by the user Ua, but the present invention is not limited to these. Any set of multiple sounds emitted by the user Ua can be targeted.

Further, for example, in the above-described embodiment, the modes of the input operation by the user U are manual input operation, voice input operation, and gesture input operation, but are not limited to these input operations. Any input operation that can input intention can be adopted. In addition, in the above-described embodiment, the user U cannot specify all the output modes in advance. . Further, in the present embodiment described above, the user Ub possesses the user terminal 50, but the user Ua may possess the user terminal 50 as well.

REFERENCE SIGNS LIST 1 Rhythm robot system 10 Rhythm robot 31 Sound acquisition unit 32 Feature amount detection unit 33 User information acquisition unit 34 User information storage unit 35 Output mode reception unit 36 Output mode determination Unit 37 Processing unit 38 Output control unit 50 User terminal 70 Server 71 User information acquisition unit 72 User information storage unit 73 User information transmission control unit 74 Output mode reception unit , 75... Output mode determination unit, 76... Output mode transmission control unit, 90... Network

Claims (5)

detection means for detecting, when a set of a first plurality of sounds emitted from the outside is input, a feature quantity of the set of the first plurality of sounds;
output means for outputting a second set of sounds having a feature amount that is the same as or partly common to the detected feature amount to the outside in a predetermined manner;
A robot with The detection means acquires a set of a plurality of collision sounds or a melody consisting of a plurality of sounds as the set of the first plurality of sounds, and obtains a melody consisting of the set of a plurality of collision sounds or a plurality of sounds. Detect each feature value,
The output means outputs the melody or rhythm sound as the set of the second plurality of sounds to the outside in a predetermined manner,
The robot according to claim 1. The output means outputs the melody or rhythm sound to the outside in a manner selected by the user.
The robot according to claim 2. The melody or rhythm sound output to the outside by the output means is a set of a plurality of collision sounds as the set of the first plurality of sounds, or a melody composed of a plurality of sounds, and is processed in a predetermined manner. is an applied melody or rhythmic sound,
The robot according to claim 3. further comprising receiving means for receiving input of information on user characteristics,
The output means outputs to the outside the melody or rhythm sound in a mode that takes into consideration the information about the characteristics of the user received by the receiving means.
The robot according to claim 2.

Images