WO2019230363A1

WO2019230363A1 - Sound emission system, information processing system, information providing method, and information processing method

Info

Publication number: WO2019230363A1
Application number: PCT/JP2019/019022
Authority: WO
Inventors: 石田　哲朗; 優樹瀬戸
Original assignee: ヤマハ株式会社
Priority date: 2018-05-30
Filing date: 2019-05-14
Publication date: 2019-12-05
Also published as: JP2019207380A; JP7196426B2

Abstract

This sound emission system is provided with: a sound acquisition device for receiving an input from a user; a sound emission device for emitting a sound; and a sound emission control unit for emitting, to the sound emission device, a sound component that represents identification information about information related to a response to the input received by the sound acquisition device.

Description

Sound emission system, information processing system, information providing method, and information processing method

This disclosure relates to a technique for providing information to a terminal device.

Services that provide information to users by voice are widely used. For example, Patent Document 1 discloses a service robot that assists the operation of a vending machine by interacting with a user who uses the vending machine.

Japanese Patent Laid-Open No. 2007-11880

However, with the technology of Patent Document 1, the service robot only utters a voice for dialogue to the user. A user who desires more detailed information related to the content of the voice uttered by the service robot needs to acquire information related to the voice he / she listened to by using a search site by operating a terminal device, for example. In view of the above circumstances, the present disclosure is intended to acquire information related to voice without requiring a complicated operation by the user.

In order to solve the above problems, an information providing method according to a preferred aspect of the present disclosure receives an input from a user, and outputs a sound component representing identification information of related information related to a response to the received input. Let the sound be emitted.
An information processing method according to an example of the present disclosure generates a response to an input by a user, generates related information about the generated response, and stores acoustic data representing an acoustic component representing identification information corresponding to the related information. Related information corresponding to the identification information in response to an information request from the terminal device that transmits to the sound emission system that emits sound according to the acoustic data and receives the identification information by acoustic communication by the sound emission system Is transmitted to the terminal device.
A sound emission system according to an example of the present disclosure includes a reception unit that receives an input from a user, a sound emission device that emits sound, and an acoustic that represents identification information of related information related to a response to the input received by the reception unit. A sound emission control unit that causes the sound emission device to emit the component.
An information processing system according to an example of the present disclosure includes a response generation unit that generates a response to an input by a user, a related information generation unit that generates related information about a response generated by the response generation unit, and the related information generation unit A first communication control unit that transmits acoustic data representing an acoustic component representing identification information of related information generated by the sound emitting system according to the acoustic data, and acoustic communication by the sound emitting system. A second communication control unit that transmits related information corresponding to the identification information to the terminal device in response to an information request from the terminal device that has received the identification information.

It is a block diagram which illustrates the composition of the information service system in a 1st embodiment. It is a block diagram which illustrates the composition of a sound emission system. It is a block diagram which illustrates the composition of a response server. It is a schematic diagram of a related information table. It is a block diagram which illustrates the composition of a signal generation part. It is a block diagram which illustrates the composition of an information service server. It is a block diagram which illustrates the composition of a terminal unit. It is a flowchart which illustrates the whole process of an information provision system.

<First Embodiment>
FIG. 1 is a block diagram illustrating a configuration of an information providing system 100 according to the first embodiment of the present disclosure. As illustrated in FIG. 1, the information providing system 100 according to the first embodiment includes a sound emitting system 20, a response server 30, and an information providing server 40. The information providing system 100 is a computer system for providing various types of information to the user U of the terminal device 50. Specifically, a response to the voice (hereinafter referred to as “uttered voice”) V1 uttered by the user U of the terminal device 50 and information R (hereinafter referred to as “related information”) R related to the response are given to the user U. Provided. The response server 30 communicates with the sound emitting system 20 and the information providing server 40 via a communication network including the Internet, for example. The response server 30 generates a response to the utterance voice V1 of the user U and related information R related to the response. A sound V2 representing the response generated by the response server 30 (hereinafter referred to as “response sound”) is reproduced by the sound emission system 20. Further, the related information R generated by the response server 30 is transmitted to the terminal device 50 by the information providing server 40. Hereinafter, details of the information providing system 100 will be described.

<Sound emission system 20>
FIG. 2 is a block diagram illustrating the configuration of the sound emission system 20. The sound emitting system 20 is a computer system that reproduces the response voice V2 to the uttered voice V1 by the user U of the terminal device 50. A voice interaction device (so-called AI speaker) that interacts with the user U is used as the sound emission system 20. For example, a portable information processing device such as a mobile phone or a smartphone, or an information processing device such as a personal computer is used as the sound emitting system 20. It is also possible to realize the sound emission system 20 in the form of a toy that simulates the appearance of an animal or the like (for example, a doll such as a stuffed animal) or a robot. For example, transportation facilities such as stations or bus stops, transportation facilities such as railways or buses, commercial facilities such as dealers or restaurants, lodging facilities such as inns or hotels, exhibition facilities such as museums or museums, sightseeing such as historic sites or sights The sound emission system 20 is installed in a facility, athletic facility such as a stadium or gymnasium.

The utterance voice V1 is an utterance voice including a question (question) and a talk, for example. On the other hand, the response voice V2 is a response voice including an answer to the question and an answer to the talk. Note that a voice that utters one or more keywords (for example, words) related to a matter that the user U desires to search may be referred to as a speech voice V1, and a voice that represents a matter related to the keyword as a search result may be referred to as a response voice V2. For example, when the user U utters an utterance voice V1 that asks the location of a restaurant in a commercial facility, “Do you have a restaurant nearby?”, The answer to the utterance voice V1 is “A restaurant ABC is nearby. . ”Is reproduced from the sound emission system 20. As illustrated in FIG. 2, the sound emission system 20 of the first embodiment includes a sound collection device 21 (an example of a reception unit), a sound emission device 22, a storage device 23, a control device 24, and a communication device 25. .

The sound collection device 21 is an input device that collects ambient sounds. The sound collection device 21 of the first embodiment generates data (hereinafter referred to as “input data”) D1 representing the uttered voice V1 uttered by the user U. That is, the sound collection device 21 functions as a reception unit that receives the uttered voice V1 (an example of an input by the user U) pronounced by the user U. Specifically, the sound collection device 21 collects the utterance voice V1 sounded by the user U and generates a signal representing the waveform of the utterance voice V1, and converts the signal from analog to digital. And an A / D converter for generating input data D1.

The control device 24 (an example of a computer) is constituted by a processing circuit such as a CPU (Central Processing Unit), and controls each element of the sound emission system 20 in an integrated manner. The storage device 23 stores a program executed by the control device 24 and various data used by the control device 24. For example, a known recording medium such as a semiconductor recording medium and a magnetic recording medium, or a combination of a plurality of types of recording media is arbitrarily adopted as the storage device 23.

The control device 24 realizes a plurality of functions (communication control unit 243 and sound emission control unit 245) by executing a program stored in the storage device 23 as illustrated in FIG. Note that some functions of the control device 24 may be realized by a dedicated electronic circuit. Further, the function of the control device 24 may be installed in a plurality of devices.

The communication control unit 243 receives and transmits various types of information through the communication device 25. That is, the communication control unit 243 controls the communication device 25 so as to receive and transmit various types of information. First, the communication control unit 243 transmits the input data D1 generated by the sound collection device 21 to the response server 30 via the communication device 25. Upon receiving the input data D1, the response server 30 generates data (hereinafter referred to as “acoustic data”) D2 for causing the sound emission system 20 to emit the response voice V2 corresponding to the utterance voice V1 represented by the input data D1. Secondly, the communication control unit 243 receives the acoustic data D2 generated by the response server 30 from the response server 30 by the communication device 25. The sound emission control unit 245 causes the sound emission device 22 to emit sound according to the acoustic data D2 transmitted from the response server 30.

The communication device 25 is a communication device that communicates with the response server 30 via the communication network under the control of the communication control unit 243. Specifically, the communication device 25 includes a transmission unit 251 and a reception unit 253. The transmission unit 251 transmits input data D1 representing the uttered voice V1 collected by the sound collection device 21 to the response server 30. The receiving unit 253 receives the acoustic data D2 generated by the response server 30. The sound emitting device 22 is an output device that emits various sounds. Specifically, the sound emitting device 22 emits sound according to the acoustic data D2 received by the communication device 25 under the control of the sound emission control unit 245. That is, the response voice V2 represented by the acoustic data D2 is emitted by the sound emission device 22. Therefore, the user U who pronounced the uttered voice V1 can listen to the response voice V2 corresponding to the uttered voice V1.

<Response server 30>
FIG. 3 is a block diagram illustrating the configuration of the response server 30. The response server 30 is a computer system that generates a response to the utterance voice V1 of the user U and related information R related to the response. Specifically, the response server 30 includes a storage device 31, a control device 32, and a communication device 33.

The storage device 31 stores a program executed by the control device 32 and various data used by the control device 32. For example, a known recording medium such as a semiconductor recording medium and a magnetic recording medium, or a combination of a plurality of types of recording media is arbitrarily adopted as the storage device 31. Specifically, the storage device 31 stores a related information table. The related information table is a data table used for specifying the related information R of the response to the speech voice V1. Details of the related information table will be described later.

The control device 32 (an example of a computer) is constituted by a processing circuit such as a CPU (Central Processing Unit), and controls each element of the sound emission system 20 in an integrated manner. As illustrated in FIG. 2, the control device 32 executes a program stored in the storage device 31 to execute a plurality of functions (voice recognition unit 321, response generation unit 322, related information generation unit 323, identification information generation unit). 324, the signal generation unit 325, and the communication control unit 326). Note that some functions of the control device 32 may be realized by a dedicated electronic circuit. Further, the function of the control device 32 may be installed in a plurality of devices.

The voice recognition unit 321 specifies a character string representing the utterance content of the uttered voice V1 (hereinafter referred to as “uttered character string”) by voice recognition on the input data D1 transmitted from the sound emitting system 20. For example, when the user U pronounces the utterance voice V1 that asks the location of the restaurant, the utterance character string “Is the restaurant nearby?” Is specified. For voice recognition with respect to the input data D1, for example, a known technique such as a recognition process using an acoustic model such as HMM (Hidden Markov Model) and a language model indicating linguistic restrictions is arbitrarily adopted.

The response generation unit 322 generates a response to the uttered voice V1. Specifically, the response generation unit 322 generates a character string (hereinafter referred to as “response character string”) representing a response to the utterance character string specified by the voice recognition unit 321. For example, when an utterance character string “is a restaurant nearby?” Is specified, a response character string “the restaurant ABC is nearby” indicating the location of the restaurant ABC is specified. For the generation of the response character string, known techniques such as natural language processing such as morphological analysis for the utterance character string and a dialogue technique using artificial intelligence are arbitrarily employed.

The related information generation unit 323 generates related information R related to the response generated by the response generation unit 322. The related information R is, for example, content for supplementing response details. For example, the content for supplementing the content of a specific word (hereinafter referred to as “response word”) included in the response character string is exemplified as the related information R. The response word is a characteristic word such as a proper noun among words included in the response character string. The response word contained in the response character string “Restaurant ABC is nearby” is “Restaurant ABC”. Various contents such as information (for example, URL of a homepage) describing the matter represented by the response word, information indicating the location of the matter represented by the response word (for example, a map image, a URL of the map, or a character string indicating the location) are related information R As an example. For example, when the matter represented by the response word is a restaurant, the content that informs the restaurant menu or congestion information may be used as the related information R. Note that the related information R is not limited to the above example, and is arbitrarily changed according to the content and type of the response word. For extracting the response word, known natural language processing such as morphological analysis is arbitrarily employed.

The related information table is used to generate the related information R. FIG. 4 is a schematic diagram of a related information table. The related information table is a table in which a plurality of related information R is registered. Specifically, for each of a plurality of response words, related information R corresponding to the response word is registered.

The related information generation unit 323 extracts a response word from the response character string generated by the response generation unit 322, and specifies the related information R corresponding to the response word among the plurality of related information R registered in the related information table. . As understood from the above description, the related information R corresponding to the response word of the response character string generated by the response generation unit 322 is generated. A plurality of related information R may be generated for the response word.

3 generates identification information I for identifying the related information R generated by the related information generating unit 323. The identification information generating unit 324 of FIG. Different identification information I is generated for each of the plurality of related information R registered in the related information table. The identification information I generated in advance for each related information R may be registered in advance in the related information table in association with the related information R.

The signal generation unit 325 generates acoustic data D2 representing the response voice V2 representing the response generated by the response generation unit 322 and the acoustic component of the identification information I corresponding to the related information R generated by the related information generation unit 323. . Specifically, acoustic data D2 representing a mixed sound of the response voice V2 and the acoustic component of the identification information I is generated. FIG. 5 is a block diagram of the signal generation unit 325. As illustrated in FIG. 5, the signal generation unit 325 includes a speech synthesis unit 71, a modulation processing unit 73, and an addition unit 74. The voice synthesis unit 71 generates a voice signal by voice synthesis with respect to the response character string generated by the response generation unit 322. A known speech synthesis technique is arbitrarily employed for generating the speech signal.

The modulation processing unit 73 generates a modulation signal representing the acoustic component of the identification information I generated by the identification information generation unit 324. The modulation signal is generated, for example, by frequency-modulating a carrier wave having a predetermined frequency with the identification information I. Note that the modulation signal may be generated by sequentially executing spread modulation of each information using a spread code and frequency conversion using a carrier wave of a predetermined frequency. The frequency band of the modulated signal is a frequency band that can be emitted by the sound emitting device 22 and collected by the terminal device 50, and the frequency band of the sound that the user U of the terminal device 50 listens to in a normal environment. Is set to a frequency band exceeding (for example, 18 kHz or more and 20 kHz or less). Therefore, the user U can hardly hear the acoustic component of the identification information I. However, the frequency band of the modulation signal is arbitrary, and for example, a modulation signal within an audible band can be generated.

The adding unit 74 adds the audio signal generated by the audio synthesizing unit 71 and the modulation signal generated by the modulation processing unit 73 to generate acoustic data D2.

The communication control unit 326 (illustrated as the first communication control unit) in FIG. That is, the communication control unit 326 controls the communication device 33 so as to receive and transmit various types of information. First, the communication control unit 326 receives the input data D 1 transmitted from the sound emission system 20 by the communication device 33. Secondly, the communication control unit 326 transmits the acoustic data D <b> 2 generated by the signal generation unit 325 to the sound emission system 20 through the communication device 33. Thirdly, the communication control unit 326 includes data (hereinafter referred to as “provided data”) including the related information R generated by the related information generating unit 323 and the identification information I generated by the identification information generating unit 324 regarding the related information R. ) D3 is transmitted to the information providing server 40 by the communication device 33.

The communication device 33 communicates with each of the sound emitting system 20 and the information providing server 40 via the communication network under the control of the communication control unit 326. Specifically, the communication device 33 includes a transmission unit 331 and a reception unit 333. The receiving unit 333 receives the input data D1 transmitted from the sound emission system 20. The transmission unit 331 transmits the acoustic data D2 generated by the signal generation unit 325 to the sound emitting system 20, and transmits the provision data D3 to the information providing server 40.

The sound emission control unit 245 of the sound emission system 20 that has received the sound data D2 causes the sound emission device 22 to emit sound according to the sound data D2. Specifically, by supplying the acoustic data D2 to the sound emitting device 22, the mixed sound represented by the acoustic data D2 is emitted from the sound emitting device 22. That is, the response sound V2 to the utterance voice V1 of the user U and the acoustic component of the identification information I of the related information R related to the response represented by the response voice V2 are emitted from the sound emission device 22.

As understood from the above description, the sound emitting device 22 functions as an acoustic device that reproduces the response voice V2, and transmits the identification information I to the surroundings by acoustic communication using sound waves as air vibration as a transmission medium. It also functions as a machine. That is, the identification information I is transmitted to the surroundings by acoustic communication that emits the sound of the identification information I from the sound emitting device 22 that emits the response voice V2. The identification information I is transmitted every time the response voice V2 is emitted. For example, the identification information I is transmitted together with the sound of the response voice V2 (for example, in parallel with or before the sound of the response voice V2 is emitted).

<Information providing server 40>
FIG. 6 is a block diagram of the information providing server 40. The information providing server 40 is a computer system for transmitting related information R related to the response of the user U to the uttered voice V1 to the terminal device 50. As illustrated in FIG. 6, the information providing server 40 includes a storage device 41, a control device 42, and a communication device 43.

The storage device 41 stores a program executed by the control device 42 and various data used by the control device 42. For example, a known recording medium such as a semiconductor recording medium and a magnetic recording medium, or a combination of a plurality of types of recording media is arbitrarily employed as the storage device 41. Specifically, the storage device 41 stores an information provision table. The information provision table is a data table used for providing the terminal device 50 with the related information R of the response to the speech voice V1. Specifically, the identification information I and the related information R included in the provision data D3 transmitted from the response server 30 are registered in the information provision table in a state where they correspond to each other. Provided data D3 is generated for each utterance voice V1 from the user U.

The control device 42 (an example of a computer) is configured by a processing circuit such as a CPU (Central Processing Unit), for example, and comprehensively controls each element of the sound emission system 20. Specifically, as illustrated in FIG. 2, the control device 42 executes a program stored in the storage device 41 to thereby execute a plurality of functions (a storage control unit 421, a related information specifying unit 423, and a communication control unit 425. ). Note that some functions of the control device 42 may be realized by a dedicated electronic circuit. Further, the function of the control device 42 may be installed in a plurality of devices.

The storage control unit 421 stores the provided data D3 received by the communication device 43 in the storage device 41. Specifically, the storage control unit 421 registers the identification information I and the related information R included in the provision data D3 in association with each other in the information provision table.

The related information specifying unit 423 specifies related information R corresponding to the identification information I in response to an information request from the terminal device 50 that has received the identification information I by acoustic communication by the sound emission system 20. The information request from the terminal device 50 includes identification information I. Specifically, the related information specifying unit 423 displays the related information R corresponding to the identification information I included in the information request from the terminal device 50 among the plurality of related information R registered in the information providing table. Identify from.

The communication control unit 425 (an example of the second communication control unit) receives and transmits various types of information through the communication device 43. That is, the communication control unit 425 controls the communication device 43 so as to receive and transmit various types of information. First, the communication control unit 425 receives the provision data D <b> 3 transmitted from the response server 30 by the communication device 43. Second, the communication control unit 425 responds to an information request from the terminal device 50 that has received the identification information I by acoustic communication by the sound emission system 20, and the related information R corresponding to the identification information I (that is, related information identification). The related information R) specified by the unit 423 is transmitted to the terminal device 50 by the communication device 43.

The communication device 43 communicates with each of the response server 30 and the terminal device 50 via the communication network under the control of the communication control unit 425. Specifically, the communication device 43 includes a transmission unit 431 and a reception unit 433. The receiving unit 433 receives the provision data D3 transmitted from the response server 30. The transmission unit 431 transmits the related information R to the terminal device 50. The response server 30 and the information providing server 40 function as an information processing system that generates a response to the utterance voice V1 of the user U and related information R related to the response.

<Terminal device 50>
FIG. 7 is a block diagram of the terminal device 50. The terminal device 50 is located near the sound emission system 20. The terminal device 50 is a portable information terminal for acquiring, from the information providing server 40, related information R related to a response to the uttered voice V1 uttered by the user U. For example, a mobile phone, a smartphone, a tablet terminal, a personal computer, or the like is used as the terminal device 50.

As illustrated in FIG. 7, the terminal device 50 includes a sound collection device 51, a control device 52, a storage device 53, a communication device 54, and a playback device 55. The sound collection device 51 is an acoustic device (microphone) that collects surrounding sounds. Specifically, the sound collection device 51 collects the sound emitted by the sound emission system 20 according to the acoustic data D2, and generates an acoustic signal Y representing the waveform of the sound. Therefore, the acoustic signal Y generated by sound collection in the vicinity of the sound emission system 20 can include the acoustic component of the identification information I.

As will be understood from the above description, the sound collection device 51 is used for voice communication between the terminal devices 50 or voice recording at the time of moving image shooting, and by acoustic communication using sound waves as air vibration as a transmission medium. It also functions as a receiver that receives the identification information I. Note that an A / D converter that converts the acoustic signal Y generated by the sound pickup device 51 from analog to digital is not shown for convenience. Further, instead of the sound collecting device 51 configured integrally with the terminal device 50, a separate sound collecting device 51 may be connected to the terminal device 50 by wire or wirelessly.

The control device 52 (an example of a computer) is configured by a processing circuit such as a CPU (Central Processing Unit) and controls each element of the terminal device 50 in an integrated manner. The storage device 53 stores a program executed by the control device 52 and various data used by the control device 52. For example, a known recording medium such as a semiconductor recording medium and a magnetic recording medium, or a combination of a plurality of types of recording media can be arbitrarily employed as the storage device 53.

7, the control device 52 realizes a plurality of functions (the information extraction unit 521 and the reproduction control unit 523) by executing a program stored in the storage device 53, as illustrated in FIG. Note that some functions of the control device 52 may be realized by a dedicated electronic circuit. Further, the function of the control device 52 may be mounted on a plurality of devices.

The information extraction unit 521 extracts the identification information I from the acoustic signal Y generated by the sound collection device 51. Specifically, the information extraction unit 521 performs identification by, for example, filtering processing that emphasizes the frequency band including the acoustic component of the identification information I in the acoustic signal Y and demodulation processing corresponding to the modulation processing on the identification information I. Information I is extracted. The identification information I extracted by the information extraction unit 521 is used to acquire related information R corresponding to the identification information I (that is, related information R related to the response represented by the response voice V2 emitted by the sound emitting device 22). .

Since the identification information I can be received only at a position within the range where the response voice V2 corresponding to the identification information I can be collected, the identification information I is also expressed as information indicating the position of the terminal device 50. it can. Therefore, the related information R can be provided only for the terminal devices 50 located around the sound emission system 20.

The communication device 54 communicates with the information providing server 40 via the communication network under the control of the control device 52. Specifically, the communication device 54 transmits the identification information I extracted by the information extraction unit 521 to the information providing server 40. The information providing server 40 acquires related information R corresponding to the identification information I transmitted from the terminal device 50 and transmits it to the terminal device 50. The communication device 54 receives the related information R transmitted from the information providing server 40.

The reproduction control unit 523 causes the reproduction device 55 to reproduce the related information R received by the communication device 54. The playback device 55 is an output device that plays back the related information R. Specifically, the playback device 55 includes a display device that displays an image represented by the related information R. Instead of the playback device 55 configured integrally with the terminal device 50, a separate playback device 55 may be connected to the terminal device 50 by wire or wirelessly. Further, the playback device 55 may include a sound emitting device that emits sound represented by the related information R. That is, the reproduction by the reproduction device 55 includes image display and sound emission.

FIG. 8 is a flowchart of processing of the information providing system 100 as a whole. The process of FIG. 9 is started when the user U pronounces the uttered voice V1. The sound collection device 21 of the sound emission system 20 receives the uttered voice V1 from the user U (Sa1). Specifically, input data D1 representing the uttered voice V1 uttered by the user U is generated by the sound collecting device 21. The communication control unit 243 of the sound emission system 20 transmits the input data D1 generated by the sound collection device 21 to the response server 30 through the communication device 25 (Sa2).

The communication control unit 326 of the response server 30 receives the input data D1 transmitted from the sound emitting system 20 by the communication device 33 (Sa3). The voice recognition unit 321 specifies an utterance character string by voice recognition on the input data D1 received by the communication device 33 (Sa4). The response generation unit 322 generates a response to the uttered voice V1 (Sa5). Specifically, a response character string corresponding to the utterance character string specified by the voice recognition unit 321 is generated. The related information generating unit 323 generates related information R related to the response generated by the response generating unit 322 (Sa6). The identification information generation unit 324 generates identification information I for identifying the related information R generated by the related information generation unit 323 (Sa7). The signal generator 325 generates acoustic data D2 (Sa8). Specifically, acoustic data D2 representing a mixed sound of the response voice V2 and the acoustic component of the identification information I is generated. The communication control unit 326 transmits the provision data D3 to the information provision server 40 through the communication device 33 (Sa9). The provided data D3 includes related information R generated by the related information generating unit 323 and identification information I generated by the identification information generating unit 324 regarding the related information R.

The communication control unit 425 of the information providing server 40 receives the provision data D3 transmitted from the response server 30 by the communication device 43 (Sa10). The storage control unit 421 stores the provided data D3 received by the communication device 43 in the storage device 41 (Sa11). Specifically, the storage control unit 421 stores the related information R and the identification information I included in the provided data D3 in the storage device 41 in association with each other.

The communication control unit 326 of the response server 30 transmits the acoustic data D2 generated by the signal generation unit 325 to the sound emission system 20 through the communication device 33 (Sa12). The communication control unit 243 of the sound emitting system 20 receives the acoustic data D2 transmitted from the response server 30 by the communication device 25 (Sa13). The sound emission control unit 245 causes the sound emission device 22 to emit sound according to the acoustic data D2 (Sa14). The sound emitting device 22 transmits the identification information I to the terminal device 50 by emitting a mixed sound of the response voice V2 and the acoustic component of the identification information I (Sa15). That is, the identification information I is transmitted to the terminal device 50 by acoustic communication using the sound emitting device 22.

The sound collection device 51 of the terminal device 50 collects the sound emitted by the sound emission system 20 according to the acoustic data D2 (that is, the sound including the acoustic component of the identification information I) (Sa16). Specifically, an acoustic signal that represents the waveform of the collected sound is generated. The information extraction unit 521 extracts the identification information I from the acoustic signal generated by the sound collection device 51 (Sa17). The communication device 54 transmits the identification information I extracted by the information extraction unit 521 to the information providing server 40 (Sa18).

The communication control unit 425 of the information providing server 40 receives the identification information I transmitted from the terminal device 50 by the communication device 43 (Sa19). The related information specifying unit 423 specifies related information R corresponding to the identification information I received by the communication device 43 (Sa20). The communication control unit 425 transmits the related information R specified by the related information specifying unit 423 to the terminal device 50 through the communication device 43 (Sa21).

The communication device 54 of the terminal device 50 receives the related information R transmitted from the information providing server 40 (Sa22). The reproduction control unit 523 causes the reproduction device 55 to reproduce the related information R received by the communication device 54 (Sa23). That is, the related information R related to the response represented by the response voice V2 emitted by the sound emitting device 22 is reproduced by the reproducing device 55.

As understood from the above description, in the first embodiment, since the identification information I is transmitted to the terminal device 50 by acoustic communication using the sound emitting device 22 that emits the response sound V2, the response sound V2 represents. The related information R related to the response (for example, more detailed information related to the response) can be acquired by the terminal device 50 using the identification information I. Therefore, it is possible to reduce a load of the user U giving a complicated operation to the terminal device 50 in order to acquire the related information R related to the response voice V2. Further, the identification information I can be transmitted to the terminal device 50 by diverting the sound emitting device 22 for emitting the response voice V2. That is, a transmitter dedicated to the transmission of the identification information I is not necessary.

In the first embodiment, the uttered voice V1 received by the sound emission system 20 is transmitted to the response server 30, and the acoustic data D2 of the response voice V2 representing the response generated by the response server 30 is received by the receiving unit 253. It is not necessary to incorporate an element for generating the response voice V2 in the sound emission system 20. Therefore, the configuration and operation of the sound emission system 20 are simplified. In the first embodiment, since the related information R corresponding to the response word included in the response character string generated by the response generation unit 322 is generated, the related information R corresponding to the entire response character string is specified. The related information R can be easily identified as compared with. Therefore, the processing load on the information providing server 40 can be reduced.

Second Embodiment
A second embodiment of the present disclosure will be described. In the following examples, elements having the same functions as those of the first embodiment are diverted using the same reference numerals used in the description of the first embodiment, and detailed descriptions thereof are appropriately omitted.

In the first embodiment, the identification information I of the related information R is generated by the response server 30. On the other hand, in the second embodiment, the identification information I of the related information R is generated by the sound emission system 20. That is, the identification information generation unit 324 is omitted in the response server 30 of the second embodiment.

The control device 24 of the sound emission system 20 functions as an identification information generation unit in addition to the communication control unit 243 and the sound emission control unit 245. When the sound collection device 21 receives the utterance voice V1 produced by the user U (that is, when the input data D1 is generated), the identification information generation unit generates the identification information I corresponding to the input data D1. Identification information I corresponding to the related information R generated by the response server 30 in accordance with the input data D1 is generated in advance by the identification information generation unit. The communication control unit 243 transmits the input data D1 generated by the sound emitting device 22 and the identification information I generated by the identification information generation unit to the response server 30 through the communication device 25.

The communication control unit 326 of the response server 30 receives the input data D1 and the identification information I transmitted from the sound emitting system 20 by the communication device 33. The voice recognition unit 321 of the response server 30 that has received the input data D1 identifies an utterance character string from the input data D1 as in the first embodiment. The response generation unit 322 generates a response character string for the utterance character string, as in the first embodiment. The related information generation unit 323 generates related information R related to the response represented by the response character string, as in the first embodiment. The signal generator 325 generates acoustic data D2 representing the response voice V2 and the acoustic component of the identification information I transmitted from the sound emission system 20. The acoustic data D2 generated by the signal generation unit 325 is transmitted to the sound emission system 20 under the control of the communication control unit 326, as in the first embodiment. The provided data D3 including the related information R generated by the related information generating unit 323 and the identification information I transmitted from the sound emission system 20 is transmitted to the information providing server 40 under the control of the communication control unit 326. Is done.

The information providing server 40 that has received the provided data D3 stores the provided data D3 in the storage device 41 as in the first embodiment. That is, the identification information I generated by the sound emission system 20 is registered in the storage device 41 in a state corresponding to the related information R generated by the response server 30. The sound emission system 20 that has received the acoustic data D2 sends the response voice V2 and the acoustic component representing the identification information I of the related information R corresponding to the response voice V2 in accordance with the acoustic data D2, as in the first embodiment. Sounds out. The terminal device 50 acquires the related information R from the information providing server 40 as in the first embodiment.

In the second embodiment, the same effect as in the first embodiment is realized. In the second embodiment, since the identification information I is transmitted from the sound emitting system 20 to the response server 30, the response server 30 determines the correspondence between the response voice V 2 and the identification information I without generating the identification information I in the response server 30. 30 can be managed. Therefore, the processing load on the response server 30 can be reduced.

<Modification>
Specific modifications added to each of the above-exemplified aspects will be exemplified below. A plurality of modes arbitrarily selected from the following examples may be appropriately combined as long as they do not contradict each other.

(1) In each of the above-described embodiments, the speech voice V1 is exemplified as the input by the user U. However, the input by the user U is not limited to the speech voice V1. For example, a character string designated by the user U may be input by the user U. For example, a configuration in which the sound emission system 20 includes an operation device (not shown) that receives an instruction from the user U is assumed. The operating device includes, for example, a plurality of operators operated by the user U (for example, a plurality of operators corresponding to kana characters, alphabets, or numbers in Japanese). The user U instructs, for example, a character string including an inquiry (question) and a conversation (hereinafter referred to as “input character string”) to the operating device. Note that the input character string may be one or more keywords (for example, words) related to a matter that the user U desires to search. The controller device accepts an input character string. Specifically, input data D1 representing the input character string is generated. That is, the controller device functions as a reception unit that receives an input character string that the user U has instructed the controller device. Upon receiving the input data D1, the response server 30 generates a response character string and related information R according to the input data D1. That is, the voice recognition unit 321 is omitted.

Further, for example, the user U may select a desired option from among a plurality of options each representing a question and a conversation prepared in advance using the operation device. Input data D1 indicating the question or conversation set in the option selected by the user U is generated. That is, the controller device functions as a reception unit that receives selection of options by the user U. The choice selection corresponds to the input of the user U. As understood from the above description, the input from the user U is information given to the accepting unit according to the intention of the user U, and examples thereof include an utterance voice V1, an input character string, and options. In addition, depending on the type of input by the user U, a device used as a reception unit that receives input from the user U is also changed as appropriate.

(2) In each of the above-described forms, the related information R corresponding to the response word of the response character string is generated. However, if the related information R is information related to the response to the input from the user U, the content is arbitrary. It is. For example, the related information R may be generated in consideration of the entire content of the response character string. The related information generation unit 323 generates the related information R indicating the location of the restaurant ABC, for example, for an utterance character string “Where is the restaurant ABC?”. The response character string itself or a character string obtained by translating the response character string into another language may be used as the related information R. Note that it is not essential to use the related information table for generating the related information R. The generation of the related information R includes both specifying any one of the plurality of related information R registered in the related information table and newly generating the related information R in response to an input from the user U. The method for generating the related information R is appropriately changed according to the content and type of the related information R.

(3) In each of the above-described forms, the response character string is generated by the response generation unit 322 as a response to the speech voice V1, but the response generated by the response generation unit 322 is not limited to the response character string. For example, when the content of the response generated by the response generation unit 322 is fixed, for example, the storage device 23 can store the response voice V2 in advance. The response generation unit 322 specifies the response voice V2 corresponding to the input data D1 from the storage device 23 as a response to the utterance voice V1.

Further, the response generation unit 322 may generate a character string obtained by translating the utterance character string generated by the voice recognition unit 321 into another language as a response to the utterance voice V1. A response voice V2 obtained by translating the speech voice V1 into another language is emitted from the sound emission system 20. According to the above configuration, an automatic translator that translates the speech U1 of the user U into another language is used as the sound emission system 20. In the configuration in which the automatic translator is the sound emission system 20, a character string obtained by translating an utterance character string into another language is used as the related information R. Note that the function of the response server 30 may be installed in an automatic translator.

(4) In each of the above-described embodiments, the sound emission system 20 presents a response to the utterance voice V1 to the user U by emitting the response voice V2, but together with the sound emission of the response voice V2, for example, the sound emission system 20 The response character string and the related information R may be displayed on the display device (for example, a liquid crystal display). Further, a configuration that omits sound emission of the response voice V2 is also employed. In the above configuration, instead of the acoustic data D2 representing the response voice V2 and the acoustic component of the identification information I, the acoustic data D2 representing only the acoustic component of the identification information I is transmitted to the sound emitting system 20, and the sound emitting system 20, identification information I is transmitted to the terminal device 50. Similarly, the display of the response character string may be omitted. *

(5) In each of the above-described embodiments, the acoustic data D2 representing the mixed sound of the response voice V2 and the acoustic component of the identification information I is generated by the response server 30, but the response server 30 uses the response voice V2 and the identification information I. The sound data D2 including the sound components as individual sounds may be generated, and the sound data D2 may be transmitted to the sound emitting system 20. The sound emitting system 20 emits sound according to the sound data D2. A mixed sound of the response voice V2 and the acoustic component of the identification information I may be emitted, or the response voice V2 and the acoustic component of the identification information I may be emitted individually. Further, the relationship between the response voice V2 and the sound component of the identification information I is arbitrary. For example, the response voice V2 and the acoustic component of the identification information I may be emitted in parallel, or the response voice V2 and the acoustic component of the identification information I may be emitted in different periods on the time axis. The sound emission control unit 245 is comprehensive as an element that causes the sound emission device 22 to emit a response voice V2 representing a response to the input received by the reception unit and an acoustic component representing the identification information I of the related information R related to the response. It is expressed in

(6) In each form mentioned above, although the response server 30 produced | generated acoustic data D2, the sound emission system 20 may produce | generate acoustic data D2. The response server 30 generates a response character string and identification information I in the sound emission system 20. The sound emitting system 20 generates acoustic data D2 from the response character string transmitted from the response server 30 and the identification information I, and emits sound according to the acoustic data D2. That is, the signal generation unit 325 can be omitted from the response server 30.

(7) In each of the above forms, the identification information generation unit 324 generates the identification information I every time the related information R is generated. However, the identification information I is registered in advance for the related information R registered in the related information table. You may keep it. When the related information R is generated by the related information generating unit 323, the identification information generating unit 324 specifies the identification information I corresponding to the related information R from the related information table. In the above configuration, each of the plurality of related information R may be registered in advance in the information provision table in association with the identification information I of the related information R. In the above configuration, transmission of the provision data D3 from the response server 30 to the information provision server 40 is omitted.

(8) In each of the above-described embodiments, the sound emission system 20 transmits the acoustic signal representing the utterance voice V1 as the input data D1 to the response server 30, but the utterance character string of the utterance voice V1 is input to the response server 30 as the input data D1. You may send it. That is, the voice recognition unit 321 can be omitted from the response server 30.

(9) In each embodiment described above, the information providing system 100 is configured by the response server 30, the information providing server 40, and the sound emitting system 20, but the configuration of the information providing system 100 is not limited to the above examples. For example, the information providing system 100 may be configured with a single device. Further, the response server 30 and the sound emission system 20 may be realized by a single device, or the response server 30 and the information providing system 100 may be realized by a single device.

(10) In each of the above-described embodiments, the voice interactive device is used as the sound emission system 20. According to the above configuration, for example, information related to a purchased item by the user U can be used as the related information R.

(11) In each of the above-described embodiments, the identification information I is transmitted to the terminal device 50 by acoustic communication using the sound emitting device 22. For example, the sound emitting system 20 may be Bluetooth (registered trademark) or Wi-Fi (registered trademark). The identification information I may be transmitted to the terminal device 50 by short-range wireless communication. That is, the identification information I is transmitted to the terminal device 50 by a communication device different from the sound emitting device 22 that emits the response voice V2.

(12) The functions of the sound emission system 20, the information processing system (the response server 30 and the information providing server 40), and the terminal device 50 according to each of the above-described forms are the same as the cooperation between the control device and the program as illustrated in each form. Realized by work. The programs according to the above-described embodiments can be provided in a form stored in a computer-readable recording medium and installed in the computer. The recording medium is, for example, a non-transitory recording medium, and an optical recording medium (optical disk) such as a CD-ROM is a good example, but a known arbitrary one such as a semiconductor recording medium or a magnetic recording medium This type of recording medium is also included. The non-transitory recording medium includes an arbitrary recording medium excluding a transient propagation signal (transitory, “propagating” signal), and does not exclude a volatile recording medium. In addition, the program may be provided to the computer in the form of distribution via a communication network.

<Appendix>
For example, the following configuration is grasped from the above-exemplified form.

The information providing method according to an example (first aspect) of the present disclosure receives an input from a user, and causes the sound emitting device to emit an acoustic component representing identification information of related information related to a response to the received input. In the above aspect, since the identification information is transmitted to the terminal device by acoustic communication using the sound emitting device, the terminal device displays the related information (for example, more detailed information about the response) related to the response represented by the response voice. Can be obtained using. Therefore, it is possible to reduce a load of the user giving a complicated operation to the terminal device in order to acquire related information related to the response voice.

In an example of the first aspect (second aspect), in the operation of causing the sound emitting device to emit sound, the sound emitting device emits a response voice representing the response and the acoustic component. In the above aspect, the sound emitting device that emits the response sound can be used as a communication device that transmits the identification information of the related information corresponding to the response sound.

In an example of the second mode (third mode), input data representing the accepted input is transmitted to a response server, the response voice representing a response to the input represented by the input data, and identification information of related information regarding the response The sound data representing the sound component representing is received from the response server, and the sound emitting device is caused to emit sound according to the received sound data. In the above aspect, since the received input is transmitted to the response server and the acoustic data of the response voice representing the response generated by the response server is received, it is necessary to incorporate an element for generating the response voice in the sound emission system. There is no. Therefore, the configuration and operation of the information providing method are simplified.

In an example of the third aspect (fourth aspect), the identification information is generated, and the input data and the generated identification information are transmitted to the response server. In the above aspect, the response server can manage the correspondence between the response voice and the identification information without generating the identification information in the response server.

In one example of the first aspect to the fourth aspect (fifth aspect), the input from the user is a voice uttered by the user. In the above aspect, since the related information can be acquired by the user speaking, the related information can be easily acquired by the user without input using the operation element, for example.

An information processing method according to an example (sixth aspect) of the present disclosure generates a response to an input by a user, generates related information regarding the generated response, and represents an acoustic component representing acoustic information representing identification information of the related information In response to an information request from a terminal device that transmits data to a sound emission system that emits sound according to the sound data and receives the identification information through acoustic communication by the sound emission system, Corresponding related information is transmitted to the terminal device. In the above aspect, since the identification information is transmitted to the terminal device by acoustic communication using the sound emitting device, the terminal device displays the related information (for example, more detailed information about the response) related to the response represented by the response voice. Can be obtained using. Therefore, it is possible to reduce a load of the user giving a complicated operation to the terminal device in order to acquire related information related to the response voice.

In an example of the sixth aspect (seventh aspect), in the generation of the related information, related information corresponding to a word included in the response is generated. In the above aspect, the related information can be easily specified as compared with the configuration in which the related information corresponding to the entire response is specified.

A sound emission system according to an example of the present disclosure (eighth aspect) includes a reception unit that receives input from a user, a sound emission device that emits sound, and related information related to a response to the input received by the reception unit. A sound emission control unit that causes the sound emission device to emit an acoustic component representing the identification information. In the above aspect, since the identification information is transmitted to the terminal device by acoustic communication using the sound emitting device, the terminal device displays the related information (for example, more detailed information about the response) related to the response represented by the response voice. Can be obtained using. Therefore, it is possible to reduce a load of the user giving a complicated operation to the terminal device in order to acquire related information related to the response voice.

In an example of the eighth aspect (the ninth aspect), the sound emission control unit causes the sound emitting device to emit a response voice representing the response and the acoustic component. In the above aspect, the sound emitting device that emits the response sound can be used as a communication device that transmits the identification information of the related information corresponding to the response sound.

In an example of the ninth aspect (tenth aspect), a transmission unit that transmits input data representing an input accepted by the reception unit to a response server, the response voice that represents a response to the input represented by the input data, and the response A receiving unit that receives from the response server acoustic data that represents the acoustic component representing the identification information of the related information related to the sound information, and the sound emission control unit is configured to release the sound according to the acoustic data received by the receiving unit. Let the sound device emit sound. In the above aspect, since the input accepted by the accepting unit is transmitted to the response server, and the acoustic data of the response voice representing the response generated by the response server is received by the receiving unit, the element for generating the response voice is released. Does not need to be built into the sound system. Therefore, the configuration and operation of the sound emission system are simplified.

In an example of the tenth aspect (an eleventh aspect), an identification information generation unit that generates the identification information is provided, and the transmission unit receives the input data and the identification information generated by the identification information generation unit as the response. Send to server. In the above aspect, the response server can manage the correspondence between the response voice and the identification information without generating the identification information in the response server.

In one example of the eighth aspect to the eleventh aspect (the twelfth aspect), the input from the user is a voice uttered by the user. In the above aspect, since the related information can be acquired by the user speaking, the related information can be easily acquired by the user without input using the operation element, for example.

An information processing system according to an example of the present disclosure (a thirteenth aspect) includes a response generation unit that generates a response to an input by a user, a related information generation unit that generates related information about the response generated by the response generation unit, A first communication control unit configured to transmit acoustic data representing an acoustic component representing identification information of the related information generated by the related information generating unit to a sound emitting system that emits sound according to the sound data; A second communication control unit that transmits related information corresponding to the identification information to the terminal device in response to an information request from the terminal device that has received the identification information by acoustic communication by the system. In the above aspect, since the identification information is transmitted to the terminal device by acoustic communication using the sound emitting device, the terminal device displays the related information (for example, more detailed information about the response) related to the response represented by the response voice. Can be obtained using. Therefore, it is possible to reduce a load of the user giving a complicated operation to the terminal device in order to acquire related information related to the response voice.

In one example of the thirteenth aspect (fourteenth aspect), the related information generation unit generates related information corresponding to a word included in the response generated by the response generation unit. In the above aspect, the related information can be easily specified as compared with the configuration in which the related information corresponding to the entire response is specified.

DESCRIPTION OF SYMBOLS 100 ... Information provision system, 20 ... Sound emission system, 21 ... Sound collection device, 22 ... Sound emission device, 23 ... Memory | storage device, 24 ... Control apparatus, 243 ... Communication control part, 245 ... Sound emission control part, 25 ... Communication Device: 251 ... Transmission unit, 253 ... Reception unit, 30 ... Response server, 31 ... Storage device, 32 ... Control device, 321 ... Voice recognition unit, 322 ... Response generation unit, 323 ... Related information generation unit, 324 ... Identification information Generation unit, 325 ... signal generation unit, 326 ... communication control unit, 33 ... communication device, 331 ... transmission unit, 333 ... reception unit, 40 ... information providing server, 41 ... storage device, 42 ... control device, 421 ... storage control , 423 ... related information specifying unit, 425 ... communication control unit, 43 ... communication device, 431 ... transmission unit, 433 ... reception unit, 50 ... terminal device, 51 ... sound collecting device, 52 ... control device, 521 ... information extraction Part, 523 ... Raw controller, 53 ... storage device, 54 ... communication device, 55 ... playback apparatus, 71 ... sound synthesis unit, 73 ... modulation processing unit, 74 ... adding unit.

Claims

Accepts input from users,
An information providing method realized by a computer that causes a sound emitting device to emit an acoustic component representing identification information of related information related to a response to the accepted input.
The information providing method according to claim 1, wherein in the operation of causing the sound emitting device to emit sound, the sound emitting device emits a response voice representing the response and the acoustic component.
Sending input data representing the accepted input to a response server;
Receiving from the response server acoustic data representing the response voice representing a response to the input represented by the input data and the acoustic component representing identification information of related information related to the response;
The information providing method according to claim 2, wherein the sound emitting device emits sound according to the received acoustic data.
Generating the identification information;
The information providing method according to claim 3, wherein the input data and the generated identification information are transmitted to the response server.
The information providing method according to claim 1, wherein the input from the user is a voice uttered by the user.
Generate a response to user input,
Generating relevant information about the generated response;
Transmitting acoustic data representing an acoustic component representing identification information of the related information to a sound emitting system that emits sound according to the acoustic data;
An information processing method for transmitting related information corresponding to the identification information to the terminal device in response to an information request from the terminal device that has received the identification information by acoustic communication using the sound emission system.
The information processing method according to claim 6, wherein in the generation of the related information, related information corresponding to a word included in the response is generated.
A reception unit that accepts input from the user;
A sound emitting device that emits sound;
A sound emission system comprising: a sound emission control unit that causes the sound emission device to emit an acoustic component representing identification information of related information related to a response to an input received by the reception unit.
The sound emission system according to claim 8, wherein the sound emission control unit causes the sound emission device to emit a response voice representing the response and the acoustic component.
A transmission unit that transmits input data representing an input accepted by the reception unit to a response server;
A receiver that receives from the response server acoustic data representing the response voice representing a response to an input represented by the input data and the acoustic component representing identification information of related information related to the response;
The sound emission system according to claim 9, wherein the sound emission control unit causes the sound emission device to emit sound according to acoustic data received by the reception unit.
Comprising an identification information generating unit for generating the identification information;
The sound emission system according to claim 10, wherein the transmission unit transmits the input data and the identification information generated by the identification information generation unit to the response server.
The sound emission system according to any one of claims 8 to 11, wherein the input from the user is a voice uttered by the user.
A response generator for generating a response to the input by the user;
A related information generating unit that generates related information related to the response generated by the response generating unit;
A first communication control unit that transmits acoustic data representing acoustic components representing identification information of the related information generated by the related information generating unit to a sound emitting system that emits sound according to the acoustic data;
A second communication control unit that transmits related information corresponding to the identification information to the terminal device in response to an information request from the terminal device that has received the identification information by acoustic communication by the sound emission system. system.
The information processing system according to claim 13, wherein the related information generation unit generates related information corresponding to a word included in the response generated by the response generation unit.