JP2023024713A - server - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technology capable of using a smart speaker as an effective advertising medium, or further improving a smart speaker system.

SOLUTION: A server includes: receiving means for receiving a distribution request from a microphone and a speaker having a communication function via a network; acquisition means for acquiring an audio content without an image in response to the received distribution request; selection means for selecting a voice advertisement without an image from voice advertisement holding means; and transmitting means for transmitting the acquired audio content and the selected audio advertisement together to the speaker via the network.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2023,JPO&INPIT

Description

The present invention relates to a server communicating with a speaker having a microphone.

2. Description of the Related Art Smart speakers that are equipped with a microphone and a communication function and that enable voice operation and information retrieval have begun to spread (see, for example, Non-Patent Document 1).

https://www.is.nri.co.jp/report/short-research/2017/000213.html, retrieved May 9, 2018

Systems that include current smart speakers can receive voice requests from users and process the requests. In this context, it would be desirable to create a more beneficial smart speaker system.

The present invention has been made in view of these problems, and its object is to provide a technology that enables smart speakers to be used as effective advertising media, or to further improve smart speaker systems.

One aspect of the present invention relates to a server. This server includes a receiving means for receiving voice information acquired from a speaker having a microphone and a communication function via the microphone of the speaker via a network, and a delivery request for the received voice information without an image. Acquisition means for acquiring audio content; authentication means for performing user authentication based on received audio information; selection means for selecting audio advertisements without images from audio advertisement holding means; transmitting means for transmitting to the speaker via the network together with the voice advertisement, wherein the selecting means determines the relevance of the acquired voice content and the user's response in the received voice information. selecting a voice advertisement candidate using a first relevance of a plurality of relevances of a relevance to the utterance content and a relevance to the attributes of the account of the authenticated user; Other relevances of the relevance are further used to select a voice advertisement from the selected voice advertisement candidates.

It should be noted that any combination of the above constituent elements, or mutual replacement of the constituent elements and expressions of the present invention with devices, methods, systems, computer programs, recording media storing computer programs, etc., are also included in the present invention. It is effective as an aspect of

ADVANTAGE OF THE INVENTION According to this invention, the technique which can use a smart speaker as an effective advertising medium can be provided, or a smart speaker system can be further improved.

BRIEF DESCRIPTION OF THE DRAWINGS It is a schematic diagram which shows the structure of the voice advertisement distribution system which concerns on 1st Embodiment. 2 is a block diagram showing the functions and configuration of the smart speaker of FIG. 1; FIG. 2 is a hardware configuration diagram of a management server in FIG. 1; FIG. 2 is a block diagram showing the functions and configuration of a management server in FIG. 1; FIG. FIG. 5 is a data structure diagram showing an example of an audio content holding unit in FIG. 4; 5 is a data structure diagram showing an example of a voice advertisement holding unit in FIG. 4; FIG. 5 is a data structure diagram showing an example of a voice information holding unit in FIG. 4; FIG. 5 is a data structure diagram showing an example of a user information holding unit in FIG. 4; FIG. 5 is a data structure diagram showing an example of a session information holding unit in FIG. 4; FIG. FIG. 2 is a flow chart showing a series of processes in the management server of FIG. 1; FIG. 1 is a schematic top view of a user's room; FIG. FIG. 12 is a schematic diagram showing the configuration of a voice operation system according to a third embodiment; FIG. FIG. 12 is a schematic diagram showing the configuration of a voice operation system according to a fourth embodiment; FIG. 14 is a block diagram showing the functions and configuration of the management server of FIG. 13; FIG. 15 is a data structure diagram showing an example of a user information holding unit in FIG. 14; FIG.

Hereinafter, the same or equivalent constituent elements, members, and processes shown in each drawing are denoted by the same reference numerals, and duplication of description will be omitted as appropriate. Also, in each drawing, some members that are not important for explanation are omitted.

(First embodiment)
In the voice advertisement distribution system according to the first embodiment, the user can use the smart speaker to perform the following operations, for example.
・Check the weather forecast ・Listen to the news ・Set an alarm ・Check the schedule ・Do calculations ・Play music ・Control smart home appliances.
The voice advertisement delivery system acquires the user's utterance through the microphone of the smart speaker, and recognizes the utterance by voice so that the user can use the voice content (for example, search results, weather forecasts, news, schedules, calculation results, music, etc.). Understand that you are requesting delivery. The system prepares the requested audio content and delivers it to the smart speaker. Insert into your content.

This voice advertisement is, for example, a voice advertisement tailored to the voice content to be delivered, a voice advertisement based on the content of the conversation so far, or the sound around the smart speaker collected by the smart speaker just before the delivery of the voice content. may be an audio advertisement based on

The length of the voice advertisement may be adjusted to the context of the user's interaction and the surroundings of the smart speaker. As a form of adjustment, for example, the length of the voice advertisement may be adjusted according to the details of the voice content to be distributed, or the important part of the voice advertisement may be extracted.

Regarding the timing of playback of audio advertisements, the advertisement effect is higher when the user is around the smart speaker. It may be determined taking into account that it may be uncomfortable. For example, an audio advertisement may be played only when it is determined that the user is around the smart speaker. Also, audio advertisements may not be played when a user is conversing with another user or speaking into a smart speaker. In the latter case, the output of the voice advertisement may begin or resume when the user stops speaking. Also, voice advertisements may be output in cooperation with other electronic devices such as televisions (hereinafter referred to as TVs). For example, after an advertisement is played on TV, a follow-up report may be output by voice from a smart speaker. In this case, the next TV advertisement may be muted. Alternatively, after playing an audio advertisement on a smart speaker, a related advertisement may be played on the TV.

The voice advertisement distribution system has a function of obtaining a voiceprint from a user's speech obtained through a smart speaker and performing user authentication by voiceprint authentication. In addition, the voice advertisement distribution system cooperates with other services such as web services and SNS, and can associate authenticated users in the voice advertisement distribution system with user accounts in other services. In this case, the voice advertisement distribution system may select, for the authenticated user, voice advertisements associated with the account of the authenticated user. For example, the voice ad serving system may select voice ads based on information collected by smart speakers and account attributes. The voice advertisement delivery system may also update account attributes with information collected by smart speakers.

FIG. 1 is a schematic diagram showing the configuration of a voice advertisement delivery system 2 according to the first embodiment. The voice advertisement distribution system 2 includes a management server 4, a smart speaker 10, and a TV 12. The management server 4, the smart speaker 10, and the TV 12 are communicably connected via a network 6 such as the Internet. Both smart speaker 10 and TV 12 are installed in room 14 of user 8 . The smart speaker 10 is a speaker having a microphone and a communication function, is connected to the network 6 as described above, and is configured to be capable of P2P (Peer to Peer) communication 16 with the TV 12 . Although FIG. 1 shows an example in which the smart speaker 10 and the management server 4 communicate with each other, the number of smart speakers 10 and the number of users 8 are not limited.

The user 8 expresses a voice content delivery request such as "I want to listen to Taro Komura's song", "Tell me today's news", "What is the weather tonight?", "Tell me about Izumo Taisha", etc. A sentence is spoken toward the smart speaker 10 . The microphone of the smart speaker 10 converts the voice uttered by the user 8 into an electrical signal, and the smart speaker 10 transmits the resulting electrical signal as an audio signal to the management server 4 via the network 6 . The management server 4 performs speech recognition processing on the received audio signal to understand what kind of audio content the user wants to be distributed. Management server 4 generates distribution information in which a voice advertisement is attached to the requested audio content, and transmits the distribution information to smart speaker 10 via network 6 . Upon receiving the distribution information, the smart speaker 10 first outputs the voice advertisement and then outputs the voice content.

Note that the smart speaker 10 may or may not have a display, but the content delivered from the management server 4 is not content such as a still image or moving image in which an image and sound are integrated, but is accompanied by an image. audio content (or audio-only content) without Audio advertisements are similarly audio advertisements without images.

FIG. 2 is a block diagram showing the functions and configuration of smart speaker 10 of FIG. Each block shown here can be implemented by hardware such as a computer CPU and other elements and mechanical devices, and is implemented by software such as a computer program. It depicts the function blocks to be used. Therefore, those skilled in the art who have read this specification will understand that these functional blocks can be implemented in various ways by combining hardware and software.

The smart speaker 10 includes a speaker 102 , a microphone 104 , a communication section 106 , an input section 108 and a processing section 110 . The communication unit 106 functions as an interface for communication with the network 6 and also functions as an interface for the P2P communication 16 . The input unit 108 includes physical input mechanisms such as a power button and volume control buttons. The processing unit 110 controls the speaker 102 , the microphone 104 , the communication unit 106 and the input unit 108 to realize various functions of the smart speaker 10 .

In the present embodiment, it is assumed that the microphone 104 converts the user's utterance into a voice signal, the communication unit 106 transmits the voice signal to the management server 4, and the management server 4 performs voice recognition processing on the voice signal. there is However, even if the smart speaker performs at least a part of the voice recognition process, the smart speaker performs the voice content acquisition process and the voice advertisement selection process described later, or the smart speaker is standalone, The technical ideas of the embodiments are applicable. Sending the result of voice recognition performed by the smart speaker to the management server and sending the voice signal from the smart speaker to the management server without modification are both methods of sending voice information corresponding to the user's utterance to the management server. It is said to send.

FIG. 3 is a hardware configuration diagram of the management server 4 of FIG. Management server 4 includes memory 130 , processor 132 , communication interface 134 , display 136 and input interface 138 . These elements are each connected to bus 140 and communicate with each other via bus 140 .

The memory 130 is a storage area for storing data and programs. Data and programs may be stored in memory 130 permanently or temporarily. The processor 132 realizes various functions in the management server 4 by executing programs stored in the memory 130 . The communication interface 134 is an interface for transmitting and receiving data to and from the outside of the management server 4 . For example, communication interface 134 includes an interface for accessing network 6 . The display 136 is a device for displaying various information, such as a liquid crystal display or an organic EL (Electroluminescence) display. The input interface 138 is a device for receiving input from the user. The input interface 138 includes, for example, a mouse, a keyboard, and a touch panel provided on the display 138 .

FIG. 4 is a block diagram showing the functions and configuration of the management server 4 of FIG. Each block shown here can be implemented by hardware such as a computer CPU and other elements and mechanical devices, and is implemented by software such as a computer program. It depicts the function blocks to be used. Therefore, those skilled in the art who have read this specification will understand that these functional blocks can be implemented in various ways by combining hardware and software.

The management server 4 includes a voice content storage unit 402, a voice advertisement storage unit 404, a voice information storage unit 406, a user information storage unit 408, a session information storage unit 410, a voice signal reception unit 412, and a voice recognition unit. 414, a user authentication unit 416, a session management unit 418, a content acquisition unit 420, an advertisement selection unit 422, an advertisement adjustment unit 424, a transmission information generation unit 426, a transmission unit 428, and a timing control unit 430. , and an attribute update unit 432 .

FIG. 5 is a data structure diagram showing an example of the audio content holding unit 402 of FIG. The audio content holding unit 402 associates and holds a content ID that identifies audio content, a keyword that characterizes the audio content, and audio content data. Other metadata such as tags may be used in addition to or instead of keywords.

The data held in the audio content holding unit 402 may be data generated and registered by the management server 4 in advance or in response to a request. A well-known speech synthesis technique may be used to create audio content data. Alternatively, the data held in the audio content holding unit 402 may be data acquired by the management server 4 from another service server in advance or in response to a request.

FIG. 6 is a data structure diagram showing an example of the voice advertisement holding unit 404 of FIG. The voice advertisement holding unit 404 associates and holds an advertisement ID specifying a voice advertisement, a keyword characterizing the voice advertisement, attributes of the voice advertisement, and data of the voice advertisement. Other metadata such as tags may be used in addition to or instead of keywords. The data held in the voice advertisement holding unit 404 may be data received from the advertiser by the entity operating the management server 4 .

FIG. 7 is a data structure diagram showing an example of the voice information holding unit 406 in FIG. The voice information holding unit 406 holds voice information acquired via the microphone 104 of the smart speaker 10 . The voice information includes the content of the user's utterance obtained by voice recognition of the voice signal by the voice recognition unit 414, which will be described later. The voice information holding unit 406 associates and holds a user ID that identifies a user, a session ID of an interactive session between the smart speaker 10 and the user, and utterance content of the user or the system in the interactive session. Note that the voice information holding unit 406 holds an ID unique to the system as a user ID corresponding to the contents of the system's speech.

FIG. 8 is a data structure diagram showing an example of the user information holding unit 408 in FIG. The user information holding unit 408 stores the user ID, the user's voiceprint data, the account ID that identifies the user's account in other services, the attributes of the account, and the NG advertisement ID that identifies the advertisement that the user finds offensive. and are stored in association with each other. The voiceprint data may be obtained when the user first registers with the voice advertisement distribution system 2 .

FIG. 9 is a data structure diagram showing an example of the session information holding unit 410 of FIG. The session information holding unit 410 holds the state of the current interactive session between the smart speaker 10 and the user. The session information holding unit 410 associates and holds the user ID of the user associated with the currently existing or maintained interactive session, the session ID of the interactive session, and the state of the interactive session. The states of the dialog session are "talking" indicating that the user is speaking, "talking" indicating that the user is talking with another user, and "talking" indicating that the user is speaking and the user is not speaking. utterance or "waiting for utterance" waiting for the next utterance by the system. If it is determined that the interactive session has ended, the entry regarding that interactive session is deleted from the session information holding unit 410 . That is, when the session ID of a certain interactive session is registered in the session information holding unit 410 , it is determined that the interactive session is ongoing and the user involved in the interactive session is around the smart speaker 10 .

Returning to FIG. 4 , the audio signal reception unit 412 receives an audio signal representing the content of the user's utterance from the smart speaker 10 via the network 6 . As described above, the audio signal is an electrical signal obtained by converting the user's uttered voice with the microphone 104, and particularly an electrical signal representing the waveform of the voice. The content of the utterance includes a question/response to the smart speaker 10 (or the voice advertisement delivery system 2), a soliloquy, and a conversation with another user.

The voice recognition unit 414 performs predetermined voice recognition processing on the voice signal received by the voice signal receiving unit 412 . A voice recognition unit 414 derives the user's utterance content from the voice signal by voice recognition. The speech recognition processing in the speech recognition unit 414 may be realized using known speech recognition technology using n-grams or hidden Markov models.

User authentication unit 416 extracts or acquires a voiceprint from the audio signal received by audio signal reception unit 412 . A user authentication unit 416 performs user authentication (that is, voiceprint authentication) based on the extracted voiceprint. The user authentication unit 416 refers to the user information holding unit 408 and determines whether or not there is a voiceprint that matches the extracted voiceprint among the voiceprints held in the user information holding unit 408 . If there is a matching voiceprint, user authentication unit 416 identifies the user ID corresponding to the voiceprint, and associates the identified user ID with the utterance content derived by speech recognition unit 414 . In this case, the user who has made an utterance corresponding to the audio signal received by the audio signal receiving unit 412 has been voiceprint-authenticated by the management server 4 . If there is no matching voiceprint, user authenticator 416 produces an output indicating no match or user unknown. The management server 4 may start new user registration according to this output.

The session manager 418 manages interactive sessions between the smart speaker 10 and the user. A session management unit 418 manages the voice information storage unit 406 and the session information storage unit 410 . The session management unit 418 associates the user ID and the utterance content associated by the user authentication unit 416 with a session ID that identifies an interactive session between the smart speaker 10 and the user, and registers them in the voice information holding unit 406 .

Session management unit 418 determines the state of the current interactive session between smart speaker 10 and the user based on the user ID and speech content associated by user authentication unit 416 . The session management unit 418 updates the session information holding unit 410 with the determined state. For example, when the analysis result of the utterance content indicates that the utterance is in the middle of the utterance, the session management unit 418 determines the state of the current dialogue session to be "speaking". When the analysis result of the utterance content indicates that the utterance has ended, the session management unit 418 determines the state of the current dialogue session to be "waiting for utterance." If the analysis result of the speech content indicates the end of the dialogue session (for example, if the speech content is a word indicating the end of the dialogue session such as "see you" or "bye-bye"), the session management unit 418 deletes all entries having session IDs from the session information holding unit 410 . The session management unit 418 may delete from the session information holding unit 410 an interactive session that has remained in the “waiting for speech” state for a predetermined period of time. Here, the state of the dialogue session is determined based on the contents of the utterance, but instead of or in addition to the contents of the utterance, the state of the dialogue session may also be determined from imaging information from a separately provided camera. good. The camera here may be arranged in the smart speaker 10 itself, or a separate camera having a communication function may be used separately, or a TV having a camera function or a computer having a camera function may be used separately. .

Content acquisition section 420 acquires the requested audio content from audio content holding section 402 when the utterance content derived by audio recognition section 414 includes a request for distribution of audio content. For example, when the content of the utterance is a music content distribution request such as “I want to hear some Taro Komura song”, the content acquisition unit 420 acquires the requested music content from the audio content holding unit 402 . Alternatively, the content acquisition unit 420 may access the server of the music distribution service and acquire the requested music content together with the metadata from the server. In this case, the content acquisition unit 420 may register the acquired music content and metadata in the audio content holding unit 402 .

If the utterance content is a request for distribution of information content such as "Tell me today's news" or "What is the weather tonight?" . Alternatively, the content acquisition unit 420 may access the server of the information distribution service and acquire the requested information content in text form together with the metadata from the server. In this case, the content acquisition unit 420 may convert the acquired text-format information content into audio data by using a predetermined speech synthesis process. The content acquisition unit 420 may register the information content and metadata that have become audio data in the audio content holding unit 402 . The speech synthesis process may be implemented using known speech synthesis technology.

If the utterance content is a search result delivery request such as “Tell me about Izumo Taisha”, the content acquisition unit 420 acquires the requested search results from the audio content holding unit 402 . Alternatively, the content acquisition unit 420 may access the server of the search service and acquire the requested search result in text form together with the metadata from the server. In this case, the content acquisition unit 420 may convert the acquired search results in text format into voice data by using a predetermined voice synthesis process. The content acquisition unit 420 may register the search results and metadata that have become audio data in the audio content holding unit 402 .

The advertisement selection unit 422 selects a voice advertisement to be attached to the audio content acquired by the content acquisition unit 420 from the voice advertisement holding unit 404 . The criteria for selection of the voice advertisement in the advertisement selection unit 422 are (1) relevance to the content of the voice content acquired by the content acquisition unit 420, and (2) smart speaker 10 and (3) relevance to attributes of the authenticated user's account, or any combination thereof;

For example, with respect to (1), in response to a search result distribution request of "Tell me about Izumo Taisha", the content acquisition unit 420 acquires audio data of audio content of "Izumo Taisha used to be...". The advertisement selection unit 422 acquires the keyword “Izumo Taisha, god, marriage” corresponding to “Izumo Taisha was old…” acquired by the content acquisition unit 420 from the voice content holding unit 402 . The advertisement selection unit 422 refers to the voice advertisement storage unit 404, and selects the keyword "Izumo Taisha, matchmaking" corresponding to the acquired keyword "Izumo Taisha, God, matchmaking" and selects "Want to go on a trip to Izumo Taisha? Then ABC travel". Select the voice data of the voice advertisement "Please consult with the person." By comparing the keyword of the audio content and the keyword of the audio advertisement in this way, the advertisement selection unit 422 selects the audio advertisement corresponding to the content of the audio content acquired by the content acquisition unit 420 .

For example, regarding (2), between the smart speaker 10 and the user, (user) asks, "Are you ready to take a taxi to the station?"
(Smart speaker 10) "I'll make it in time"
(User) "What's the weather like tonight?"
Suppose that a dialogue is taking place. In response to the information content delivery request "What is the weather tonight?" The advertisement selection unit 422 refers to the voice information storage unit 406 and identifies "Can I take a taxi to the station?" The advertisement selection unit 422 extracts the keyword "station, taxi" from the specified utterance content of "Will a taxi make it to the station?". The advertisement selection unit 422 refers to the voice advertisement holding unit 404, and selects the voice data of the voice advertisement "Sugukuru ZZZ taxi dispatch service" having the keyword "taxi, dispatch" corresponding to the extracted keyword "station, taxi". select. In this way, by referring to the voice information holding unit 406, the advertisement selection unit 422 can select a voice advertisement based on the content of the user's utterance in the current interaction session between the smart speaker 10 and the user.

Note that, in the above example, when the criterion (1) is used instead of (2), the advertisement selection unit 422 corresponds to "Tonight's weather in region C is showery, the temperature is..." acquired by the content acquisition unit 420. The keyword “C region, rain, low temperature” is acquired from the audio content holding unit 402 . The advertisement selection unit 422 refers to the voice advertisement storage unit 404 and selects "CB company's hyper umbrella will not break for 10 years!" ” is selected as the audio data of the voice advertisement. In this way, even if the content of the interaction between the smart speaker 10 and the user is the same, the selected voice advertisement may differ depending on the criteria used.

For example, regarding (3), in response to an information content distribution request of "Tell me about today's news", the content acquisition unit 420 generates voice content of "There was a fire in B city, A prefecture around 6 o'clock this morning." voice data is acquired. At the same time, the user who is the utterer of "Tell me today's news" is authenticated by voiceprint authentication in the user authentication unit 416, and the user ID "B102" of this user is specified. The advertisement selection unit 422 acquires from the user information holding unit 408 the account attributes “child, male, single” corresponding to the specified user ID “B102”. The advertisement selection unit 422 refers to the voice advertisement holding unit 404, and selects a voice saying "If you come to F city, you can ride a steam locomotive." Select audio data for ads. Also, if the attribute of the account corresponding to the specified user ID “B102” is “adult, female, single”, the advertisement selection unit 422 refers to the voice advertisement holding unit 404 and selects the attribute corresponding to the attribute. Select the voice data of the voice advertisement "Do you want to go on a trip to Izumo Taisha? If so, consult with ABC travel agency" having "single, adult". By comparing the attribute of the account of the authenticated user and the attribute of the voice advertisement in this manner, the advertisement selector 422 selects the voice advertisement corresponding to the attribute of the account of the authenticated user.

Alternatively, if the attribute of the account corresponding to the specified user ID “B102” is “adult, male, married”, the advertisement selection unit 422 first selects “Christmas gift, XX precious metal ring” corresponding to the attribute. is recommended", "For fire insurance, leave it to XYZ Fire and Marine Insurance", "ZZZ Taxi Dispatch Service", "Want to go on a trip to Izumo Taisha Shrine? If so, consult with ABC Travel Agency". is selected as a candidate. Further, the advertisement selection unit 422 selects the keyword "A prefecture, B city, fire" corresponding to "At about 6 o'clock this morning, there was a fire in B city, A prefecture, ..." acquired by the content acquisition unit 420, and puts it into the voice content storage unit. 402. Advertisement selection unit 422 selects "XYZ fire and marine insurance for fire insurance" having keywords "fire, fire, insurance" corresponding to the acquired keywords "A prefecture, B city, fire" among the four selected candidates. Select the voice data of the voice advertisement "to". In this way, it is possible to combine criteria (1) and criteria (3) in such a way that candidates are selected based on criteria (3) and narrowed down based on criteria (1).

For example, between the smart speaker 10 and the user (the user), "I want to hear a song by Taro Komura."
(Smart speaker 10) "How about a Christmas song?"
(User) "Okay then."
Suppose that a dialogue is taking place. In response to a music content distribution request such as "I want to listen to some song by Taro Komura", the content acquisition unit 420 acquires audio data of Taro Komura's Christmas song. The management server 4 inquires of the user via the smart speaker 10 whether a Christmas song is acceptable. When the management server 4 receives the user's affirmative response of “Well then, then”, the management server 4 attaches a voice advertisement to the acquired voice data of Taro Komura's Christmas song and transmits the voice data to the smart speaker 10 . Here, the advertisement selection unit 422 selects keywords corresponding to Taro Komura's Christmas song acquired by the content acquisition unit 420: ring” is acquired from the audio content holding unit 402 . The advertisement selection unit 422 refers to the voice advertisement holding unit 404, and selects a keyword corresponding to the acquired keyword "Taro Komura (lyrics and composition), Otsu anime (theme song), Hei movie (insertion song), Christmas song, ring". "Otsu anime, on air from 6:00 pm on Fridays!" A present, a ring”) are selected as candidates. Further, the advertisement selection unit 422 acquires from the user information holding unit 408 the account attributes “adult, male, married” corresponding to the user ID “A101” of the user authenticated by voiceprint authentication. The advertisement selection unit 422 selects a voice advertisement saying "XX precious metal ring is recommended for a Christmas present" having the attribute "adult" corresponding to the acquired attribute "adult, male, married" among the two selected candidates. select the audio data of Further, if the user ID of the user authenticated by voiceprint authentication is "A105", the advertisement selection unit 422 selects the attribute " Select the voice data of the voice advertisement "Anime Otsu, on air from 6:00 pm on Friday!" In this way, it is possible to combine criteria (1) and criteria (3) in such a way that candidates are selected based on criteria (1) and narrowed down based on criteria (3).

There are also combinations of criteria (1) and (2), combinations of criteria (2) and (3), and combinations of the three criteria (1), (2), and (3). It is possible.
Alternatively, in addition to the criteria (1), (2), and (3), voice advertisements may be selected based on sounds collected by the smart speaker 10 around the smart speaker 10 or conversations between users. . For example, when the smart speaker 10 picks up a conversation exchanged between the user and another user such as "I don't have any tissue paper" and "Yes, let's order from an EC site", the advertisement selection unit 422 selects the A keyword "tissue paper" may be extracted from the content of the conversation, and a voice advertisement advertising the extracted "tissue paper" may be selected. Further, for example, if the smart speaker 10 picks up the barking of a dog or cat, the advertisement selection unit 422 identifies the keyword “dog, cat” from the bark, and selects dog food related to the identified “dog, cat”. Or an audio ad advertising cat food.

Advertisement adjustment unit 424 determines whether to adjust the length of the voice advertisement selected by advertisement selection unit 422 . Advertisement adjuster 424, if determined to adjust, extracts a portion (eg, a relatively important portion) from the selected voice advertisement by applying a predetermined extraction algorithm to the voice advertisement. The advertisement adjustment unit 424 determines whether to adjust the length of the audio advertisement based on the content of the audio content acquired by the content acquisition unit 420 and/or the state of the current interaction session between the smart speaker 10 and the user. You may

For example, the advertisement adjusting unit 424 refers to the session information holding unit 410, and determines that adjustment is to be performed when the state of the session corresponding to the selected voice advertisement is "in conversation", and does not adjust if "waiting for speech". can be determined. Alternatively, the advertisement adjustment unit 424 may determine the length of the audio advertisement based on the content of the audio content acquired by the content acquisition unit 420 . For example, the advertisement adjuster 424 may determine the length of the audio advertisement according to the playback time of the audio content. For longer audio content, the audio advertisement may be played multiple times. Also, for example, when the audio content is information content such as news or weather forecast, the advertisement adjustment unit 424 may determine that the adjustment should be made because there is a high probability that the user wants to obtain the desired information as soon as possible.

Techniques for extracting important parts of audio advertisements, such as parts in which people are speaking, parts in which people are speaking loudly, and parts in which the background sound gradually increases, are known, and are used in hard disk recorders and the like. ing. A predetermined extraction algorithm may be constructed using this known technique. Note that the advertisement adjustment unit 424 may adjust the volume of the voice advertisement in addition to or instead of the length of the voice advertisement.

The transmission information generation unit 426 combines the audio content acquired by the content acquisition unit 420 and the audio advertisement selected by the advertisement selection unit 422 to generate one piece of transmission information. When the length of the voice advertisement is adjusted by the advertisement adjustment unit 424, the voice advertisement whose length is adjusted by the advertisement adjustment unit 424 is used instead of the voice advertisement selected by the advertisement selection unit 422. The transmission information generator 426 configures the transmission information such that, when the transmission information is received and played by the smart speaker 10, the audio advertisement is played temporally before the audio content is played. For example, if the transmission information includes a header, audio content, and audio advertisement, the transmission information generation unit 426 may generate the transmission information such that the header, the audio advertisement, and the audio content are arranged in this order.

The transmission unit 428 transmits the transmission information generated by the transmission information generation unit 426 to the smart speaker 10 via the network 6 . Upon receiving the transmission information via the network 6, the smart speaker 10 first reproduces the audio advertisement contained in the transmission information, and then reproduces the audio content contained in the transmission information. Alternatively, the timing control unit 430 (to be described later) may control audio output from the smart speaker 10 via the network 6 . In this case, the timing control unit 430 causes the smart speaker 10 to first output the voice advertisement included in the transmission information and then output the voice content included in the transmission information. In either case, the audio advertisement and audio content are played continuously. That is, there is no other audio between the audio advertisement and the audio content. Specifically, the audio advertisement is played immediately before the audio content.

Alternatively, the audio advertisement may be embedded in the middle of the audio content, or the audio advertisement may be output after the audio content is output.

The timing control unit 430 communicates with the smart speaker 10 via the network 6 and controls the timing of audio output from the smart speaker 10 . The timing control unit 430 refers to the session information holding unit 410 and determines whether or not the user is present around the smart speaker 10 . When the session information holding unit 410 holds the session ID of the interactive session between the smart speaker 10 and the user, the timing control unit 430 determines that the user is present around the smart speaker 10 or detects the presence of the user. do. The timing control unit 430 determines that no user is present around the smart speaker 10 when such a session ID is not held in the session information holding unit 410 .

The timing control unit 430 determines whether the presence of the user around the smart speaker 10 is not detected, or when the state of the interactive session between the smart speaker 10 and the user held in the session information holding unit 410 is "speaking" or " In the case of "conversing", the output of the voice advertisement from the smart speaker 10 is restricted. The timing control unit 430 permits the output of the voice advertisement from the smart speaker 10 when the presence of the user is detected. The timing control unit 430 permits the output of the voice advertisement from the smart speaker 10 when the state of the interactive session is changed to "waiting for speech".

The timing control unit 430 controls the output timing of the voice advertisement so that the output of the TV 12 associated with the smart speaker 10 and the voice advertisement output from the smart speaker 10 are coordinated. For example, the timing control unit 430 causes the smart speaker 10 to start outputting the voice advertisement "This product introduced on TV..." at the timing when the TV 12 finishes playing the advertisement "Continue with the speaker!" , controls the smart speaker 10 . In this case, the timing control section 430 acquires the number of the channel currently being broadcast from the TV 12 via the network 6 . The timing control unit 430 acquires a broadcast schedule in advance from a server of another service. The timing control unit 430 can specify the content of the advertisement to be played on the TV 12, the start timing, and the end timing from the obtained channel number and broadcast schedule. The timing control unit 430 selects audio advertisements related to the identified content from the audio advertisement holding unit 404 and transmits them to the smart speaker 10 (which may or may not accompany the audio content). The timing control unit 430 controls the smart speaker 10 to start outputting the transmitted voice advertisement at the end timing of the advertisement shown on the TV 12 .

The attribute update unit 432 updates the attribute of the user's account with the voice information collected by the smart speaker 10 . For example, if the account ID shown in the user information holding unit 408 in FIG. 8 is that of a search service account, this account ID is given to the user who visited the search service site. Attributes of the user's account are derived from information about what the user is searching for, and are registered as attributes of the user information storage unit 408 in FIG.

On the other hand, the management server 4 can grasp the preferences of the user by analyzing the content of the conversation between the smart speaker 10 and the user and the content of the conversation between the user and other users. The attribute updating unit 432 updates the attributes of the user information holding unit 408 with the preferences grasped through the smart speaker 10 in this way. The attribute update unit 432 may associate the update content with the account ID and provide it to the search service server. As a result, the search service can obtain user preferences that have not been obtained by search services so far, and can use the preferences obtained in this way to optimize the advertisement output of the browser. Note that the user's preferences and attributes obtained through the smart speaker 10 and the preferences and attributes ascertained by the search service may be held so as to be identifiable from each other. As a result, it is possible to cope with the case of selecting a voice advertisement using only one of the preferences and attributes.

Also, when the voice advertisement is output from the smart speaker 10 , the attribute updating unit 432 determines whether or not a direct or indirect expression of disinterest is received from the user via the smart speaker 10 . When receiving, the attribute update unit 432 registers the advertisement ID of the corresponding output voice advertisement in the user information storage unit 408 as an NG advertisement ID in association with the user ID of the user. When selecting a voice advertisement, the advertisement selection unit 422 refers to the user information holding unit 408, and selects the voice advertisement specified by the NG advertisement ID held corresponding to the user ID of the authenticated user from the selection target. except. The advertisement selection unit 422 may exclude the voice advertisement succeeding the voice advertisement identified by the NG advertisement ID from the targets of selection. The advertisement selection unit 422 may exclude voice advertisements that correspond to or have the same attributes or keywords as the attributes or keywords of the voice advertisement specified by the NG advertisement ID from the selection target.

The operation of the management server 4 configured as above will be described.
FIG. 10 is a flow chart showing a series of processes in the management server 4 of FIG. The management server 4 receives an audio signal representing an audio content distribution request from the smart speaker 10 via the network 6 (S302). The management server 4 identifies the requested audio content by performing a speech recognition process on the received audio signal (S304). The management server 4 acquires the requested audio content from the audio content holding unit 402 or the outside (S306). The management server 4 selects a voice advertisement from the voice advertisement holding unit 404 (S308). The management server 4 determines whether or not it is necessary to adjust the length of the selected voice advertisement (S310). If determined to be necessary (YES in S310), the management server 4 adjusts the length of the voice advertisement (S312). The management server 4 combines the audio content acquired in step S306 with the audio advertisement selected in step S308 (if NO in step S310) or the audio advertisement whose length was adjusted in step S312 (if YES in step S310). ), and the transmission information is generated based on (S314). The management server 4 transmits the generated transmission information to the smart speaker 10 via the network 6 (S316). The management server 4 determines whether or not the timing is suitable for outputting the voice advertisement (S318). If the timing is suitable (YES in S318), the management server 4 first causes the smart speaker 10 to output the voice advertisement (S320), and then causes the voice content to be output (S322).

In the above-described embodiments, examples of holding units are hard disks and semiconductor memories. In addition, based on the description of this specification, each part is implemented by a CPU (not shown), an installed application program module, a system program module, a semiconductor memory that temporarily stores the contents of data read from the hard disk, etc. Those skilled in the art who have access to this specification will understand what is possible.

According to the management server 4 according to the present embodiment, the audio advertisement is reproduced in synchronization with the reproduction of the audio content on the smart speaker 10 . As a result, it becomes possible to provide voice advertisements in accordance with the distribution of voice content. Also, in the present embodiment, the audio advertisement is played before the audio content is played. The probability that the user will listen to the audio advertisement in this case is higher than when the audio advertisement is reproduced after the audio content is reproduced. Therefore, more effective advertisement can be provided.

Further, in the management server 4 according to the present embodiment, the voice advertisement is selected based on the content of the voice content, the voice information obtained via the smart speaker 10, and the attribute of the account of the authenticated user. There is a high probability that the audio advertisement selected in this way will meet the user's tastes and desires. Therefore, it is possible to provide voice advertisements that are more appealing to users.

In addition, the management server 4 according to the present embodiment appropriately controls the output timing of the voice advertisement from the smart speaker 10 . Therefore, it is possible to output a voice advertisement that does not interfere with the user's conversation or utterance. Alternatively, it is possible to provide voice advertisements in cooperation with other electronic devices such as the TV 12 .

In the present embodiment, in relation to the fact that the smart speaker 10 can acquire surrounding sounds and conversations between users, the management server 4 determines whether or not child abuse is occurring by understanding the voice context. may The management server 4 may edit voice data regarding automatic abuse and provide it to a predetermined investigative agency. Investigative agencies can listen to the entire audio data.

In this embodiment, a user ID is specified by voiceprint authentication by user authentication unit 416, and attributes corresponding to this user ID are specified by referring to user information holding unit 408. FIG. In this case, the management server 4 may change the mode of outputting the voice content or the voice advertisement according to the attributes of the user. For example, if the user's attribute is a child, the management server 4 may use simple words as much as possible in the voice content or voice advertisement, and may delete or paraphrase swear words. Alternatively, if the user's attribute is an elderly person, the management server 4 may increase the volume or make the pronunciation clearer in the voice content or voice advertisement.

Although the case where the user is authenticated by the user authentication unit 416 has been described in the present embodiment, the present invention is not limited to this, and the user authentication may be omitted. In this case, user attributes are not reflected in the selection of voice advertisements. Here, in the present embodiment, the operation of outputting the voice advertisement in S320 has been described, but in addition to the output of this voice advertisement, the output status can also be stored in the management server 4. FIG. Examples of output status include "target ad played to the end", "target ad stopped halfway", "in addition to playing the target ad, output additional information about the product targeted by the ad", etc. is. “The target advertisement has been played to the end” can be realized by reporting to the management server 4 when the smart speaker 10 outputs the target audio data to the end. In addition, since the management server 4 controls both the stopping and the output of the additional information, it can naturally be managed.

The technical idea according to this embodiment may be represented by the following items.
(Item 1)
a function of receiving a distribution request via a network from a speaker having a microphone and a communication function;
a function of acquiring audio content without images in response to an accepted distribution request;
the ability to select audio advertisements without images from the audio advertisement holding means;
a computer program for causing a server to implement a function of transmitting a combination of acquired audio content and a selected audio advertisement to the speaker via the network.
(Item 2)
receiving a distribution request via a network from a speaker having a microphone and a communication function;
Acquiring audio content without images in response to the received delivery request;
selecting an audio advertisement without an image from an audio advertisement holding means;
transmitting the retrieved audio content and the selected audio advertisement together to the speaker via the network.

(Second embodiment)
In the second embodiment, a plurality of smart speakers are arranged at different positions in a certain real space, and each of them is connected via a management server and network similar to the management server 4 of the first embodiment. Connected.

FIG. 11 is a schematic top view of room 202 of user 204 . Inside this room 202 are a first fixed smart speaker 208, a second fixed smart speaker 210, a third fixed smart speaker 212, a fourth fixed smart speaker 214, and a fifth movable smart speaker 216. , and the TV 206 are arranged. Each smart speaker communicates with the management server through the network. Note that although five smart speakers are shown in FIG. 11, the number of smart speakers is not limited. Each smart speaker may be mounted on a wall, floor, or ceiling of room 202 .

(1) Automatic Determination of Smart Speaker Position The management server records and manages the position of each smart speaker in the room 202 . This position may be registered in the management server 4 by the user 204 . Alternatively, the management server may automatically determine the location of each smart speaker using the microphones and speakers of the five smart speakers.

The management server determines the relative position between the smart speakers by detecting the sound output by one smart speaker by another smart speaker 10 . For example, if the locations of the second smart speaker 210, the third smart speaker 212, and the fourth smart speaker 214 are known and the location of the first smart speaker 208 is determined, the management server may A sound pulse with a predetermined wavelength is output. The management server acquires the time when the sound pulse of the predetermined wavelength was received from each of the second smart speaker 210, the third smart speaker 212, and the fourth smart speaker 214. FIG. The management server calculates the propagation time of the pulse from the acquired time, and calculates the distance from the calculated propagation time and sound velocity. The management server calculates the position of the first smart speaker 208 from each calculated distance and the known positions of the second, third and fourth smart speakers 210 , 212 , 214 .

A fifth smart speaker 216 is, for example, a smart speaker attached to a robot and can move by itself. If the locations of the first, second, third and fourth smart speakers 208, 210, 212, 214 are known, the management server can track the location of the fifth smart speaker 216 through the location calculation process described above. . In addition, when the fifth smart speaker 216 determines the position of another smart speaker based on its own position, the fifth smart speaker 216 may move to a position where it is likely to receive the sound emitted by that smart speaker.

As components of the system shown in FIG. 11, smart speakers and smartphones equipped with both a microphone and speakers are desirable, but even TVs, radios, and other electrical devices that generally have only speakers have speakers, so sound reproduction is not possible. support can be provided. In addition, there are electrical devices with communication functions. This enables speaker output from a plurality of positions. The position where the electrical equipment is arranged may be notified by the user by setting it in the management server, or may be automatically determined by the management server by the above-described position calculation process or radio waves of wireless communication.

(2) Uses of Movable Smart Speakers In audio output, the way the target user hears the sound may change depending on the position of the speaker. Therefore, the management server may perform control to move the fifth smart speaker 216 to a position where sound can be heard more appropriately.

Also, the TV 206 generally does not have a microphone function, and therefore cannot participate in the position calculation process as it is. However, by moving the fifth smart speaker 216 to the location of the TV 206 and taking over the microphone function of the TV 206, the TV 206 can also participate in the location calculation process.

(3) Audio output according to user's location When the location of each smart speaker is known, the closest smart speaker to user 204 can be identified if the location of user 204 is known. When the user 204 utters an audio output request such as "Turn on the TV", the five smart speakers convert the utterance into audio signals and transmit them to the management server. The management server performs voice recognition processing on the voice signal and understands the voice output request of the user 204 . The management server identifies the smart speaker corresponding to the user's 204 location in the room 202 . Specifically, the management server identifies the second smart speaker 210 closest to the user's 204 location. At this time, the management server compares the volume when the microphone of each smart speaker receives the user's speech, and identifies the second smart speaker 210 with the highest volume as the smart speaker closest to the position of the user 204 . Alternatively, if user 204 is using a smart phone, the management server can locate user 204 by obtaining the current location of the smart phone.

The management server transmits audio accompanying the video streamed on the TV 206 to the second smart speaker 210 identified as above. By doing so, the user 204 can receive the audio output of the TV 206 from the second smart speaker 210 closest to the user 204 .

Alternatively, if the speakers of the smart speaker are directional, the management server may control the directivity. For example, if the first, second, third and fourth smart speakers 208 , 210 , 212 , 214 have directional outputs, the management server directs the audio output of each speaker to the location of user 204 . Control each smart speaker. The management server transmits audio that accompanies the video played on the TV 206 to each smart speaker. In this case, each smart speaker outputs audio towards user 204 .

Note that a directional smart speaker may visually indicate to the user the current direction of audio output. For example, an arrow indicating directivity may be displayed on the upper surface of the smart speaker using an LED or the like.

According to this example, for example, when a user who instructs the smart speaker to reproduce content and other users are in the room 202, the sound can be output for the instructed user. Controlling a first smart speaker to face the position of a first user and controlling a second smart speaker to face the position of a second user by assigning a server process for each user, The first smart speaker and the second smart speaker may output audio simultaneously. One smart speaker has a plurality of audio output devices, and the server assigns a server process to each user. You may make it output simultaneously with the voice which faces a user's position.

The technical idea according to this embodiment may be represented by the following items.
(Item 3)
A system comprising a plurality of speakers each having a microphone and communication capability,
A system configured to determine the relative position between speakers by detecting the sound output by one speaker by another speaker.
(Item 4)
A server that communicates with a plurality of speakers, each having a microphone and a communication function, via a network, wherein the plurality of speakers are arranged at different positions in the same physical space,
The server is
means for receiving an audio output request from a user in the physical space via one of the plurality of speakers;
means for identifying a speaker corresponding to the user's position;
means for transmitting audio content to identified speakers.
(Item 5)
A server that communicates with a plurality of speakers, each having a microphone and a communication function, via a network, wherein the plurality of speakers are arranged at different positions in the same physical space,
The server is
means for receiving an audio output request from a user in the physical space via one of the plurality of speakers;
and means for controlling directivity of at least one of the plurality of speakers so that sound is output toward the position of the user.

(Third Embodiment)
FIG. 12 is a schematic diagram showing the configuration of a voice operation system 232 according to the third embodiment. Voice operation system 232 includes management server 234 , smart speaker 240 , TV 242 and smart phone 248 . The management server 234, the smart speaker 240, the TV 242, and the smartphone 248 are communicably connected via a network 236 such as the Internet. Both smart speaker 240 and TV 242 are located in room 244 of user 238 . Smart speaker 240 is configured to enable P2P communication 246 with smart phone 248 .

When operating the TV 242 by voice, the user 238 speaks a sentence representing an operation instruction such as “turn on the TV” to the smart speaker 240 . The microphone of smart speaker 240 converts the voice uttered by user 238 into an electrical signal, and smart speaker 240 transmits the resulting electrical signal as an audio signal to management server 234 via network 236 . The management server 234 understands that the user 238 is requesting to turn on the TV 242 by performing voice recognition processing on the received audio signal. The management server 234 generates an instruction signal for realizing the requested operation, that is, for turning on the TV 242 , and transmits it to the TV 242 via the network 236 . When the TV 242 receives the instruction signal via the network 236, it transitions from the power off state to the power on state.

In this way, control and operation via the smart speaker 10 are basically performed by voice. However, if there are users other than user 238 in room 244, some users 238 may not like voice control. Also, even when only the user 238 is in the room 244, it may be desired to avoid voice control depending on the control content. In that case, the voice operation system 232 can control the system side (management server 234 ) of the smart speaker 240 using text via the smartphone 248 .

In order to enable operation on the smart phone 248, the smart phone 248 downloads and installs an application dedicated to the management server 234. FIG. When the application is launched on smartphone 248, the application acquires the URL of management server 234 from smart speaker 240 via P2P communication 246 or the local network. The application establishes a connection with the management server 234 using the acquired URL. When the connection between the smart phone 248 and the management server 234 is established, the operation content input to the smart phone 248 is transmitted to the management server 234 through the connection. The management server 234 generates and transmits an instruction signal to implement the received operation content.

For example, when management server 234 receives a text string “turn on the TV” from smart phone 248 , it understands that user 238 is requesting that TV 242 be turned on by parsing the received text string. do. The management server 234 generates an instruction signal for realizing the requested operation, that is, for turning on the TV 242 , and transmits it to the TV 242 via the network 236 . When the TV 242 receives the instruction signal via the network 236, it transitions from the power off state to the power on state.

According to the voice operation system 232 according to the present embodiment, the user 238 can switch between voice operation and smartphone 248 operation depending on the situation.

In the present embodiment, a case has been described in which the management server 234 receives an operation instruction from the user 238 via the smart speaker 240 or the smartphone 248. However, the present invention is not limited to this. may accept requests for delivery of audio content from user 238 via smart speaker 240 or smartphone 248 .

The technical idea according to this embodiment may be represented by the following items.
(Item 6)
A server that communicates with a speaker having a microphone and a communication function via a network,
means for processing requests received from a user via a microphone of said speaker;
and means for processing requests received from said user via another electronic device in communication with said speaker.

(Fourth embodiment)
The fourth embodiment relates to layer division in the management server. In this embodiment, the server process (or server) is changed for each speaker. Voiceprint authentication allows the server to recognize who is speaking. The server process (or server) normally used by the target user does the processing.

FIG. 13 is a schematic diagram showing the configuration of a voice operation system 252 according to the fourth embodiment. Voice operation system 252 includes management server 254 , smart speaker 260 and TV 262 . The management server 254, the smart speaker 260, and the TV 262 are communicably connected via a network 256 such as the Internet. A smart speaker 260 and a TV 262 are both installed in a room 264 with three users (a first user 266, a second user 268 and a third user 270).

When operating the TV 262 by voice, the first user 266 speaks to the smart speaker 260 a sentence representing an operation instruction such as “Turn on the TV”. The microphone of smart speaker 260 converts the voice uttered by first user 266 into an electrical signal, and smart speaker 260 transmits the resulting electrical signal as an audio signal to management server 254 via network 256 . The management server 254 performs voiceprint authentication on the received voice signal to identify the first user 266 . The management server 254 selects a server process corresponding to the identified first user 266, and the selected server process processes subsequent requests. When the TV 262 receives an instruction signal over the network 236 from the selected server process of the management server 254, the TV 262 transitions from the power off state to the power on state. In the management server 254 , a server process different from the server process corresponding to the first user 266 is assigned to the speech of the second user 268 and the third user 270 different from the first user 266 .

FIG. 14 is a block diagram showing the functions and configuration of the management server 254 of FIG. 13. As shown in FIG. Each block shown here can be implemented by hardware such as a computer CPU and other elements and mechanical devices, and is implemented by software such as a computer program. It depicts the function blocks to be used. Therefore, those skilled in the art who have read this specification will understand that these functional blocks can be implemented in various ways by combining hardware and software.

The management server 254 includes a user information holding section 272 , an audio signal reception section 274 , a user authentication section 276 and a server process group 278 . Server process group 278 includes a plurality of server processes SP1, SP2, SP3, . . . each assigned to a particular user. In the following, a case where different server processes are used for each user will be described, but in other embodiments, the server itself may be made different for each user. Different servers naturally have different server processes.

FIG. 15 is a data structure diagram showing an example of the user information holding unit 272 of FIG. The user information holding unit 272 holds the user ID, the voiceprint data of the user, and the ID of the server process assigned to the user in association with each other.

Returning to FIG. 14 , audio signal reception unit 274 receives an audio signal representing the utterance content of any one of three users 266 , 268 , 270 from smart speaker 260 via network 256 .

User authentication unit 276 extracts or acquires a voiceprint from the audio signal accepted by audio signal accepting unit 274 . A user authentication unit 276 performs voiceprint authentication based on the extracted voiceprint. The user authentication unit 276 refers to the user information holding unit 272 and determines whether or not there is a voiceprint that matches the extracted voiceprint among the voiceprints held in the user information holding unit 272 . If there is a matching voiceprint, user authentication unit 276 identifies the user ID and server process ID corresponding to that voiceprint. If there is no matching voiceprint, user verifier 276 produces an output indicating no match or user unknown.

When the user authentication unit 276 identifies the server process ID, the server process having the identified server process ID among the server processes included in the server process group 278 is activated. The activated server process performs subsequent processing for the audio signal received by the audio signal receiving unit 274 .

Each server process included in the server process group 278 implements the operation function of the electronic device as described in the third embodiment. In other embodiments, the server process may implement audio content distribution functionality, such as that described in the first embodiment.

For example, if first user 266 is a resident of room 264 , first user 266 's server process is authorized to control TV 262 . If the second user 268 and the third user 270 are visitors to the room 264 of the first user 266 , their server processes are not authorized to control the TV 262 . Therefore, when the second user 268 or the third user 270 voice-operates the TV 262 , the server process of the second user 268 or the third user 270 sends the server process of the first user 266 a request to operate the TV 262 . The server process that has received the investigation request inquires of the first user 266 whether the operation is permissible, and if consent can be obtained from the first user 266, the target operation is executed.

Alternatively, first user 266, the owner of smart speaker 260, may set permissions for second user 268 and third user 270, who are guests. For example, while enabling control of lights via the smart speaker 260, purchasing on an EC site via the smart speaker 260 may be prohibited.

According to the voice operation system 252 according to the present embodiment, by assigning a server process to each user, executable operations, accessible information, authority, and the like can be made different for each user.

In this embodiment, a case has been described in which the management server 254 has a plurality of server processes, the management server 254 receives voice signals, performs voiceprint authentication, and identifies a server process to be used. However, the present invention is not limited to this. For example, if there are multiple servers, the audio signal from the smart speaker 260 may be transmitted to all servers, and voiceprint authentication may be performed by each server. Alternatively, any one user's server or server process, or any one server or server process receives the voice signal, extracts only the target user's voice signal, and transfers it to the target server or server process. may

In the present embodiment, the case where the first user 266 issuing the operation instruction and the TV 262 to be operated are in the same room 264 has been described, but the present invention is not limited to this, and the electronic device to be operated may be remotely operated. . For example, suppose second user 268 is visiting first user 266's room 264 and second user 268 wishes to turn on the air conditioner in his room (which is different from room 264). A second user 268 speaks a sentence representing an operational instruction “turn on the air conditioner in my room” into the smart speaker 260 . The management server 254 understands the request of the second user 268 through voiceprint authentication and speech recognition. The management server 254 forwards the second user's 268 request to another management server that is connected to the smart speaker in the second user's 268 room. At this time, an audio signal is attached as authentication data.

The technical idea according to this embodiment may be represented by the following items.
(Item 7)
A server that communicates with a speaker having a microphone and a communication function via a network,
means for identifying a speaker by analyzing an audio signal acquired through a microphone of said speaker;
means for processing the audio signal using a server process assigned to the identified speaker.

In each of the above-described embodiments, in addition to the smart speaker, the operation in cooperation with a TV or computer connected to the network was also described. can also be displayed on the television or computer. At this time, the management server 4 transmits a URL to be displayed on the TV or computer, and information indicating that the smart speaker or the management server 4 has requested additional information is included in the parameters of this URL. can also be added. As a result, the request destination system side can recognize that the request is made using the management server 4 or the smart speaker. Here, although URL parameters are used as an example of the transmission method, other methods may be used for notification.

The configuration and operation of the system according to the embodiment have been described above. Those skilled in the art will understand that these embodiments are merely examples, and that various modifications can be made to the combination of each component and each process, and that such modifications are within the scope of the present invention. Combinations of embodiments are also possible.

2 voice advertisement distribution system, 4 management server, 6 network, 8 user, 10 smart speaker.

Claims (11)

a receiving means for receiving voice information acquired from a speaker having a microphone and a communication function via a microphone of the speaker via a network;
Acquisition means for acquiring audio content without images in response to a distribution request in received audio information;
authentication means for performing user authentication based on the received voice information;
selection means for selecting an audio advertisement without images from the audio advertisement holding means;
transmitting means for transmitting the acquired audio content and the selected audio advertisement together to the speaker via the network;
The selecting means selects a plurality of relationships among a relationship with the content of the acquired voice content, a relationship with the content of the user's utterance in the received voice information, and a relationship with the attribute of the account of the authenticated user. selecting a candidate voice advertisement using a first one of the relevances of the plurality of relevances, and further using other relevances of the plurality of relevances to select a voice advertisement from the selected candidate voice advertisements. server. The selecting means uses at least the relevance of the acquired audio content and the relevance of the account attributes of the authenticated user to select voice advertisement candidates, and then select the selected voice advertisement. 2. The server of claim 1, wherein the voice advertisement is selected from the candidates for . The selection means selects voice advertisement candidates by using the relevance to attributes of the account of the authenticated user, and further uses the relevance to the obtained voice content to select the selected voice advertisement candidates. 3. The server of claim 1 or 2, wherein the audio advertisement is selected from. Selecting the candidate voice advertisement or the voice advertisement using the relevance to the content of the acquired audio content selects the candidate voice advertisement or the voice advertisement using a keyword related to the content of the acquired audio content 4. A server according to any one of claims 1 to 3, comprising: 2. The selection means according to claim 1, wherein, when using the relevance of the user's utterance content in the received voice information, the selection means uses the relevance of the user's utterance content in the current dialogue session between the speaker and the user. server. 2. The plurality of relevances further includes relevance to sounds around the speaker or content of conversations exchanged between the user and other users acquired via a microphone of the speaker. server described in . Further comprising control means for controlling the timing of audio output from the speaker via the network,
7. The control means limits the output of the voice advertisement from the speaker when the user's presence is not detected or when it is determined that the user's conversation is continuing. server described in . Further comprising control means for controlling the timing of audio output from the speaker via the network,
7. The server according to any one of claims 1 to 6, wherein said control means restricts output of a voice advertisement from said speaker when presence of a user is detected. further comprising updating means for updating attributes of the authenticated user's account using the received voice information;
9. A server according to any one of claims 1 to 8, wherein said selection means uses updated attributes of an authenticated user's account for selecting an audio advertisement. further comprising updating means for updating an attribute of the authenticated user's account using the representation of the user's feedback on the voice advertisement received via the speaker;
9. A server according to any one of claims 1 to 8, wherein said selection means uses updated attributes of an authenticated user's account for selecting an audio advertisement. The selecting means selects voice advertisements associated with the specific voice advertisement when an expression of feedback from the user to the voice advertisement indicating that the user is not interested in the specific voice advertisement is received through the speaker. 9. A server according to any one of claims 1 to 8, excluding from.

Images