WO2018087967A1 - 情報処理装置および情報処理方法 - Google Patents
情報処理装置および情報処理方法 Download PDFInfo
- Publication number
- WO2018087967A1 WO2018087967A1 PCT/JP2017/028471 JP2017028471W WO2018087967A1 WO 2018087967 A1 WO2018087967 A1 WO 2018087967A1 JP 2017028471 W JP2017028471 W JP 2017028471W WO 2018087967 A1 WO2018087967 A1 WO 2018087967A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user
- application service
- information
- specific
- voice
- Prior art date
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 50
- 238000003672 processing method Methods 0.000 title claims abstract description 7
- 238000004891 communication Methods 0.000 claims abstract description 38
- 230000004044 response Effects 0.000 description 96
- 238000012545 processing Methods 0.000 description 74
- 238000000034 method Methods 0.000 description 35
- 230000008569 process Effects 0.000 description 34
- 238000004458 analytical method Methods 0.000 description 28
- 238000010586 diagram Methods 0.000 description 20
- 235000015278 beef Nutrition 0.000 description 11
- 230000000694 effects Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 239000000284 extract Substances 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 208000019901 Anxiety disease Diseases 0.000 description 3
- 230000036506 anxiety Effects 0.000 description 3
- 235000013372 meat Nutrition 0.000 description 3
- 235000013405 beer Nutrition 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000001151 other effect Effects 0.000 description 2
- OHVLMTFVQDZYHP-UHFFFAOYSA-N 1-(2,4,6,7-tetrahydrotriazolo[4,5-c]pyridin-5-yl)-2-[4-[2-[[3-(trifluoromethoxy)phenyl]methylamino]pyrimidin-5-yl]piperazin-1-yl]ethanone Chemical compound N1N=NC=2CN(CCC=21)C(CN1CCN(CC1)C=1C=NC(=NC=1)NCC1=CC(=CC=C1)OC(F)(F)F)=O OHVLMTFVQDZYHP-UHFFFAOYSA-N 0.000 description 1
- WZFUQSJFWNHZHM-UHFFFAOYSA-N 2-[4-[2-(2,3-dihydro-1H-inden-2-ylamino)pyrimidin-5-yl]piperazin-1-yl]-1-(2,4,6,7-tetrahydrotriazolo[4,5-c]pyridin-5-yl)ethanone Chemical compound C1C(CC2=CC=CC=C12)NC1=NC=C(C=N1)N1CCN(CC1)CC(=O)N1CC2=C(CC1)NN=N2 WZFUQSJFWNHZHM-UHFFFAOYSA-N 0.000 description 1
- IHCCLXNEEPMSIO-UHFFFAOYSA-N 2-[4-[2-(2,3-dihydro-1H-inden-2-ylamino)pyrimidin-5-yl]piperidin-1-yl]-1-(2,4,6,7-tetrahydrotriazolo[4,5-c]pyridin-5-yl)ethanone Chemical compound C1C(CC2=CC=CC=C12)NC1=NC=C(C=N1)C1CCN(CC1)CC(=O)N1CC2=C(CC1)NN=N2 IHCCLXNEEPMSIO-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/10—Speech classification or search using distance or distortion measures between unknown speech and reference templates
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/08—Use of distortion metrics or a particular distance between probe pattern and reference templates
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
- H04R1/32—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only
- H04R1/40—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only by combining a number of identical transducers
- H04R1/406—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only by combining a number of identical transducers microphones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
- H04R3/005—Circuits for transducers, loudspeakers or microphones for combining the signals of two or more microphones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
Definitions
- This disclosure relates to an information processing apparatus and an information processing method.
- Patent Document 1 based on voice feature data generated by analyzing singing voice of karaoke, personal information registered in advance from a customer database is extracted to identify a customer, A communication karaoke system that outputs an assigned message is disclosed.
- Patent Document 2 discloses a communication karaoke system that reads a customer ID from an ID card and outputs a message for the customer based on the analysis result of the content of the corresponding customer-specific record.
- Patent Document 3 customer information is read from a customer recording medium such as a point card, the customer visit rate is calculated from the number of customer visits and the number of business days of the amusement hall, and regular customers and emergency customers are accurately identified.
- a customer management device that can be used for a sales strategy of an amusement hall is disclosed.
- the present disclosure proposes an information processing apparatus and an information processing method capable of collecting a user's uttered voice and recognizing a specific user based on the number of utterances of the user within a predetermined period.
- a communication unit capable of receiving audio information related to sound collected by a plurality of discretely arranged microphones, and a specification of the plurality of microphones received via the communication unit
- the user identified based on the voice information related to the voice collected by the microphone is determined to be a specific user who has made at least a prescribed number of utterances in a certain period, and through the communication unit,
- An information processing apparatus comprising: a control unit configured to control a speaker corresponding to a specific microphone to transmit audio information to be transmitted to the specific user.
- a specific microphone of the plurality of microphones received by the processor via a communication unit capable of receiving sound information related to sound collected by the plurality of discrete microphones. Determining that the user identified based on the voice information related to the voice collected by the user is a specific user who has spoken at least a prescribed number of times in a certain period, and through the communication unit, Proposed is an information processing method including: controlling a speaker corresponding to a specific microphone to transmit audio information to be transmitted to the specific user.
- FIG. 1 is a diagram illustrating an overview of an information processing system according to an embodiment of the present disclosure.
- the information processing system according to the present embodiment collects a user's uttered voice by the terminal device 1 having voice input and output functions, and is determined to be a specific user that satisfies a predetermined condition A predetermined response voice is output to the user.
- the voice of the user who asked “Is there usual?” In the store is collected by the voice input unit 12 (microphone) of the terminal device 1 installed in the store, and the voice of the user is collected. Analyzing the voiceprint of the information to identify the user, whether or not the user is a regular customer (for example, the user identified based on voiceprint analysis is voiced for a predetermined number of days within a predetermined period at the store Whether or not it has been recognized). Then, if the user satisfies the determination condition, it is determined that the user is a regular customer, and a special response for the regular customer (for example, “special steak meat limited sale” etc.) as shown in FIG. 1 from the audio output unit 13 (speaker).
- a special response for the regular customer for example, “special steak meat limited sale” etc.
- FIG. 2 is a diagram illustrating an example of the overall configuration of the information processing system according to the present embodiment.
- the information processing system includes a plurality of terminal devices 1 (here, three terminal devices 1a to 1c are shown as an example) arranged in various places, and a server 2 Including. It is assumed that a large number of terminal devices 1 are installed in various places in the city such as a shopping street, a department store, a restaurant, an apparel shop, and a game center.
- the form of the terminal device 1 is not particularly limited, and may be provided in a stuffed toy, a game machine, a store robot, a local character costume, or the like.
- the server 2 is connected to a plurality of terminal devices 1 via the network 3 and transmits / receives data to / from each other.
- the server 2 performs voiceprint analysis on the utterance voice information received from the plurality of terminal devices 1, performs user identification (individual identification), and whether or not the user is a premium user who satisfies a predetermined condition. Make a decision.
- response voice data for the premium user is acquired and transmitted to the terminal device 1.
- Response voice data for premium users is acquired from the corresponding predetermined application service server 4 (4a to 4c).
- the application service server 4 is a server corresponding to an application service applied to each terminal device 1, and information on the determination conditions of premium users in the service and the ID (terminal ID) of the terminal device 1 to which the service is applied Is held.
- the application service server 4 In response to a request from the server 2, the application service server 4 generates response voice data (customer information, etc.) for premium users and transmits it to the server 2.
- FIG. 3 is a block diagram illustrating an example of the configuration of the terminal device 1 according to the present embodiment. As illustrated in FIG. 3, the terminal device 1 includes a control unit 10, a communication unit 11, a voice input unit 12, a voice output unit 13, and a storage unit 14.
- the control unit 10 functions as an arithmetic processing device and a control device, and controls the overall operation in the terminal device 1 according to various programs.
- the control unit 10 is realized by an electronic circuit such as a CPU (Central Processing Unit) or a microprocessor, for example.
- the control unit 10 may include a ROM (Read Only Memory) that stores programs to be used, calculation parameters, and the like, and a RAM (Random Access Memory) that temporarily stores parameters that change as appropriate.
- control unit 10 controls to continuously transmit the voice information collected by the voice input unit 12 (specifically, user's utterance voice information) from the communication unit 11 to the server 2.
- voice information collected by the voice input unit 12 specifically, user's utterance voice information
- the audio information transmitted to the server 2 may be raw audio data, or may be audio data processed by encoding, feature amount extraction, or the like.
- control unit 10 controls to reproduce the audio information received from the server 2 (specifically, response audio data for premium users) from the audio output unit 13. Thereby, information for premium users can be presented.
- control unit 10 may have a function of a voice agent that automatically responds to the user's utterance.
- the response pattern to the user utterance may be stored in the storage unit 14 or acquired from the server 2.
- the audio input unit 12 is realized by a microphone, a microphone amplifier unit that amplifies the audio signal obtained by the microphone, and an A / D converter that digitally converts the audio signal, and outputs the audio signal to the control unit 10. .
- the audio output unit 13 has a speaker for reproducing an audio signal and an amplifier circuit for the speaker.
- the communication unit 11 is connected to the network 3 by wire or wireless, and transmits / receives data to / from the server 2 on the network.
- the communication unit 11 is, for example, by a wired / wireless LAN (Local Area Network), Wi-Fi (registered trademark), a mobile communication network (LTE (Long Term Evolution), 3G (third generation mobile communication system)) or the like. Connect to network 3 for communication.
- the storage unit 14 is realized by a ROM (Read Only Memory) that stores programs and calculation parameters used for the processing of the control unit 10, and a RAM (Random Access Memory) that temporarily stores parameters that change as appropriate.
- ROM Read Only Memory
- RAM Random Access Memory
- the configuration of the terminal device 1 according to the present embodiment has been specifically described above.
- the configuration of the terminal device 1 is not limited to the example illustrated in FIG.
- at least one of the voice input unit 12 and the voice output unit 13 may be separate from the terminal device 1.
- FIG. 4 is a block diagram illustrating an example of the configuration of the server 2 according to the present embodiment.
- the server 2 (information processing apparatus) includes a control unit 20, a network communication unit 21, an application service server I / F (interface) 22, and a storage unit 23.
- the control unit 20 functions as an arithmetic processing device and a control device, and controls the overall operation in the server 2 according to various programs.
- the control unit 20 is realized by an electronic circuit such as a CPU (Central Processing Unit) and a microprocessor, for example.
- the control unit 20 may include a ROM (Read Only Memory) that stores programs to be used, calculation parameters, and the like, and a RAM (Random Access Memory) that temporarily stores parameters that change as appropriate.
- control unit 20 includes an application service management unit 20a, a user information management unit 20b, a voiceprint analysis unit 20c, a voice recognition unit 20d, a user identification unit 20e, and a premium user determination unit 20f. , And the response voice data acquisition unit 20g.
- the application service management unit 20a manages information related to application services (for example, reading and writing data) using the application service management table, the application service keyword list, and the application service terminal list stored in the storage unit 23. Information about the application service is acquired from each application service server 4 via the application service server I / F 22.
- FIG. 5 shows an example of an application service management table according to the present embodiment.
- the application service management table stores an application service ID in association with an application name and a premium user determination condition.
- the application service ID is identification information of the application service.
- the application name is the name of the application service.
- the premium user determination condition is a determination condition of a premium user targeted by the application service, and includes, for example, the number of visits to the store (the number of utterance days) within a predetermined period, the number of utterances of a predetermined keyword, and the like. Also, there may be a plurality of premium user determination conditions. For example, in the example shown in FIG.
- a premium user who sells beef jerky as a person who has ordered beef jerky 10 or more times a month as “ABC shopping district customer campaign” with application service ID: app0001 The person who ordered steak meat five times or more in one month can be determined as a premium user who will be selling steak meat.
- FIG. 6 shows an example of the application service keyword list.
- the application service keyword list is a list of keywords associated with the application service ID. Specifically, it is a list of keywords used in premium user determination. Note that the number of keywords associated with each application service ID is not limited to one, and may be plural. Further, a keyword of a subordinate concept of a certain keyword may be further linked.
- FIG. 7 shows an example of the application service terminal list.
- the application service terminal list is a list of terminal devices associated with the application service ID. For example, in the example shown in FIG. 7, IDs of terminal devices to which the application service ID: app0001 is applied are registered: dev0001, dev0002,.
- the user information management unit 20b manages information about the user by the user management table stored in the storage unit 23.
- the user-related information includes a user ID and voiceprint analysis result (voiceprint data) allocated for each user on the system side, a keyword history spoken by the user, and a history specifying the user.
- voiceprint data voiceprint data allocated for each user on the system side
- keyword history spoken by the user a keyword history spoken by the user
- history specifying the user a history specifying the user.
- FIG. 8 is a diagram showing an example of a user management table according to the present embodiment.
- the user management table includes a user ID allocated for each user, voice print data, and an area of “application service data” that can be freely used for each application service.
- application service data By storing the application service data in association with each user ID, cooperation with a function provided uniquely by each application can be realized.
- FIG. 9 is a diagram showing an example of the user keyword history.
- the date (registration date) when the user issued a predetermined keyword and the corresponding application service ID are stored in association with the user ID. This makes it possible to determine whether or not the user has issued a predetermined keyword within a predetermined period.
- FIG. 10 is a diagram showing an example of the user identification history.
- the ID of a terminal device that identifies the user and the specific date (registration date) are stored in association with the user ID. Thereby, for example, it is possible to determine the number of times the user has visited a shopping street or a shopping center.
- the voiceprint analysis unit 20c performs voiceprint analysis on the voice information of the user utterance received from the terminal device 1 by the network communication unit 21, and acquires voiceprint data (ie, voiceprint analysis result).
- voiceprint analysis algorithm is not particularly limited.
- the voiceprint data varies depending on the person, and personal identification can be performed.
- the voice recognition unit 20d converts voice information of the user utterance into text, performs morphological analysis, and performs keyword extraction, semantic understanding, attribute evaluation, and the like.
- the attribute evaluation is estimation of a speaker's gender, age, and the like.
- the user identification unit 20e identifies the user based on the voiceprint analysis result by the voiceprint analysis unit 20c. Specifically, the user specifying unit 20e uses the user management table stored in the storage unit 23 to compare the voice print data associated with each user ID with the voice print analysis result, and which user's voice is. To identify.
- the premium user determination unit 20f refers to the premium user determination condition stored in the storage unit 23, and determines whether or not the user specified by the user specifying unit 20e is a premium user.
- the premium user determination unit 20f refers to user information (user keyword history or user identification history) stored in the storage unit 23, and designates a user who has spoken more than a prescribed number of times at least for a certain period as a premium user ( It is determined that it is an example of a specific user. Further, the premium user determination condition is set for each application service as described with reference to FIG. For this reason, the premium user determination unit 20f determines a premium user using the application service determination condition applied to the terminal device 1 that picks up the user uttered voice.
- the response voice data acquisition unit 20g acquires response voice data for the user utterance. Specifically, for example, the response voice data acquisition unit 20g transmits, to the application service server 4, a determination condition satisfied by the user, a terminal device ID that has collected the user's uttered voice, and the like, and a response for a premium user Request and obtain audio data.
- the response voice data acquired by the response voice data acquisition unit 20g is transmitted to the terminal device 1 (a device including a speaker corresponding to the microphone that picks up the speech voice of the premium user) via the network communication unit 21.
- the network communication unit 21 is connected to the network 3 by wire or wireless, and transmits / receives data to / from each terminal device 1 via the network 3.
- the network communication unit 21 is connected to the network 3 by, for example, a wired / wireless LAN (Local Area Network) or Wi-Fi (Wireless Fidelity, registered trademark).
- the application service server I / F 22 transmits and receives data to and from the application service server 4. Communication with the application service server I / F 22 may be via a dedicated line or via the network 3.
- the storage unit 23 is realized by a ROM that stores programs and calculation parameters used for the processing of the control unit 20, and a RAM that temporarily stores parameters that change as appropriate.
- the storage unit 23 according to the present embodiment stores the above-described application service management table, application service keyword list, application service terminal list, user management table, user keyword history, and user identification history.
- the configuration of the server 2 according to the present embodiment has been specifically described above.
- FIG. 11 is a sequence diagram showing application service registration processing according to this embodiment.
- the application service server 4 transmits to the server 2 the application service ID and name information allocated to itself (step S103).
- the application service management unit 20a of the server 2 registers the received application service ID and name information in the application service management table stored in the storage unit 23 (step S106).
- the application service server 4 transmits the ID of the terminal device to which the application service provided by itself is applied to the server 2 (step S109).
- the application service management unit 20a of the server 2 registers the received ID of the terminal device in the application service terminal list stored in the storage unit 23 in association with the application service ID (step S112).
- the application service server 4 transmits a list of keywords targeted for speech recognition to the server 2 (step S115).
- the application service management unit 20a of the server 2 assigns a unique ID to each keyword included in the received keyword list, associates the ID and the keyword with the application service ID, and stores them in the storage unit 23.
- the application service keyword list is registered (step S118).
- the application service server 4 transmits the premium user determination conditions to the server 2 (step S121).
- the application service management unit 20a of the server 2 associates the received determination condition with the application service ID and registers it in the application service management table stored in the storage unit 23 (step S124).
- the application service registration process described above is appropriately performed with the server 2 for each application service.
- FIGS. 12 and 13 are sequence diagrams illustrating response processing of the information processing system according to the present embodiment.
- the terminal device 1 collects a user uttered voice by the voice input unit 12 (step S203).
- the terminal device 1 is provided, for example, in a store or at the entrance of a store, and continuously collects a user's conversation or whispering.
- the terminal device 1 transmits the ID of the terminal device 1 and the collected voice information to the server 2 (step S206).
- the server 2 analyzes the received voice information by the voiceprint analysis unit 20c (step S209).
- the server 2 collates the result of the voice print analysis with the user management table by the user specifying unit 20e (step S212). As described with reference to FIG. 8, since the voice print data associated with the user ID is stored in the user management table, the user can be identified by comparing the voice print analysis result with the voice print data. It becomes.
- the user information management unit 20b registers the result of voiceprint analysis in the user management table as voiceprint data of the new user (step S218).
- the user information management unit 20b records the date and time when the user is recognized and the ID of the received terminal device in the user identification history (step S221). “Recognized user” means that there is a corresponding user in step S215 or a new user is registered in step S218.
- the server 2 recognizes the voice information of the user utterance received from the terminal device 1 by the voice recognition unit 20d and extracts a keyword from the utterance content (step S224). Specifically, the speech recognition unit 20d converts the speech information into text and morphological analysis, and extracts keywords from the utterance text (in this case, widely extracts words).
- the server 2 compares the received ID of the terminal device 1 with the application service terminal list (see FIG. 7) by the application service management unit 20 a and applies it to the terminal device 1.
- Application service ID is extracted (step S227).
- the voice recognition unit 20d acquires a keyword list (see FIG. 6) registered in the extracted application service ID (step S230).
- the speech recognition unit 20d determines whether or not the keyword extracted from the speech information of the user utterance by speech recognition is included in the keyword list (step S233).
- the user information management unit 20b records the keyword in the user keyword history (see FIG. 9) (step S236).
- the premium user determination unit 20f performs a premium user determination process (step S239). Specifically, the premium user determination unit 20f determines whether or not the user who has spoken is a premium user according to the premium user determination condition set in the application service management table.
- the premium user determination condition varies depending on the application service to be applied. Specific examples of the premium user determination condition will be described later using a plurality of examples.
- step S242 when the premium user determination unit 20f determines that the user is not a premium user (step S242 / No), the server 2 notifies the terminal device 1 that the user is not a premium user (step S245).
- the terminal device 1 When the server 2 determines that the user is not a premium user, the terminal device 1 does not respond to the user (step S248). Note that the terminal device 1 may perform a general automatic response by a voice agent, such as “I welcome”, without performing a response for a premium user based on the application service.
- the server 2 matches the application service server 4 indicated by the application service ID to be applied (for example, the matched determination condition, The user ID of the premium user and the terminal device ID are transmitted) (step S251).
- the application service server 4 generates response voice data for premium users according to the information received from the server 2 (step S254).
- the response voice data for premium users may be stored in the application service server 4 in advance or may be generated by a predetermined algorithm. A specific example of the generated response voice data will be described later using a plurality of embodiments.
- the application service server 4 transmits the generated response voice data for the premium user to the server 2 (step S257).
- the server 2 transmits the response voice data received from the application service server 4 to the terminal device 1 (step S260).
- the terminal device 1 outputs the response voice data received from the server 2 by voice from the voice output unit 13 (step S263).
- a special response for example, provision of campaign information for regular customers, etc.
- First Example> In the first embodiment, when a user specified by voiceprint analysis has made some utterance at a high frequency in the past (that is, visited frequently), the user is determined to be a premium user.
- the application service used in this embodiment is “Application service ID: app0002, application name: DD Mall store thanks event registered in the application service management table shown in FIG. Corresponds to “when you say something”.
- FIG. 14 is a diagram for explaining the outline of this embodiment.
- a user who visits in the vicinity of terminal devices 1-1a to 1-1c may be singular installed in a large number in “DD mall”. If the user speaks for a predetermined number of days (for example, 5 days) within a predetermined period (for example, within one week), it can be estimated that the user has visited the DD mall at a high frequency, and therefore the user is determined to be a premium user.
- each of the terminal devices 1-1a to 1-1d is a group of terminal devices installed in the DD mall, and when at least one of the terminal devices 1-1 recognizes utterance, the user identification is performed. Is called.
- the present embodiment is not limited to this, and there may be one terminal device 1-1 installed in the DD mall.
- FIG. 15 is a flowchart showing premium user determination processing according to the first embodiment.
- the premium user determination unit 20f of the server 2 refers to the user identification history (see FIG. 10) and the application service terminal list stored in the storage unit 23, and sets the application service ID to be applied.
- the user's utterance frequency for the terminal device to which the terminal belongs is acquired (step S303). Specifically, for example, the premium user determination unit 20f extracts terminal devices 1-1a to 1-1c belonging to the same application service ID as the application service ID applied to the terminal device 1-1d from the application service terminal list. To do.
- the premium user determination unit 20f compares the user identification history with the date and time (speech frequency) when the user was identified by the terminal devices 1-1a to 1-1d (that is, the user's utterance was recognized by voiceprint analysis). get.
- the premium user determination unit 20f determines whether or not the user has made any utterance for five days or more in the past week according to the premium user determination condition of the application service ID: app0002 registered in the application service management table. (Step S306).
- step S306 determines that the user is a premium user (step S309).
- step S312 determines that the user is not a premium user (step S312).
- a user who has made a certain utterance for a predetermined number of days or more within a predetermined period without specifying a keyword that is, a user estimated to have visited the store for a predetermined number of days within a predetermined period
- a keyword that is, a user estimated to have visited the store for a predetermined number of days within a predetermined period
- FIG. 16 is a flowchart showing response voice data generation processing according to the first embodiment.
- the application service server 4 generates predetermined response voice data such as “Thank you for your use each time” based on the matched determination condition received from the server 2 (step S320).
- the application service server 4 has response voice data or a response voice data generation algorithm corresponding to the determination condition, for example, and can generate response voice data based on the “matched determination condition” received from the server 2. is there.
- the response voice data generation process according to the first embodiment has been specifically described above.
- the response voice data generated by the application service server 4 is transmitted from the application service server 4 to the terminal device 1-1 via the server 2 as shown in steps S257 to S263 in FIG. 1 is output as audio.
- Second Embodiment> when a user specified by voiceprint analysis has uttered a predetermined keyword at a high frequency in the past, it is determined that the user is a premium user.
- the application service used in this embodiment is “Application service ID: app0001, application name: ABC shopping district customer campaign, registered in the month:“ Beef ”registered in the application service management table shown in FIG. Corresponds to "Jerky” ordered 10 times (speaking "Beef Jerky”).
- FIG. 17 is a diagram for explaining the outline of this embodiment.
- a user who has visited near the terminal devices 1-2a to 1-2c may be singular installed in a large number in “ABC shopping street” If the user utters the predetermined keyword “beef jerky” for a predetermined number of times (for example, 10 times) within a predetermined period (for example, one month), it can be estimated that the user purchases the beef jerky at a high frequency. It is determined that the user is a premium user.
- each of the terminal devices 1-2a to 1-2d is a group of terminal devices installed in the ABC shopping street, and when the utterance is recognized by at least one of the terminal devices 1-2, the user identification is performed. Done.
- the present embodiment is not limited to this, and one terminal device 1-2 may be provided.
- FIG. 18 is a flowchart showing premium user determination processing according to the second embodiment.
- the premium user determination unit 20 f of the server 2 refers to the user keyword history (see FIG. 9) stored in the storage unit 23 and utters a predetermined keyword “beef jerky” by the user.
- the frequency is acquired (step S403).
- the premium user determination unit 20f extracts, from the application service keyword list, a predetermined keyword that is used as a determination condition for a premium user that is a target of an application service applied to the terminal device 1-2d.
- the premium user determination unit 20f obtains the date and time (speech frequency) when the user utters a predetermined keyword in comparison with the user keyword history.
- the premium user determination unit 20f determines whether the user has uttered “beef jerky” at least 10 times in the past month according to the premium user determination condition of the application service ID: app0001 registered in the application service management table. Is determined (step S406).
- step S406 determines that the user is a premium user (step S409).
- step S409 / No the premium user determination unit 20f determines that the user is not a premium user (step S412).
- a user who utters a predetermined keyword a predetermined number of times within a predetermined period (for example, when the terminal device 1-2 is installed near a cash register, the predetermined keyword is input a predetermined number of times within a predetermined period. It is determined that the user who is presumed to have ordered the product is a premium user.
- FIG. 19 is a flowchart showing response voice data generation processing according to the second embodiment.
- the application service server 4 generates predetermined response voice data such as “Beef Jerky Special Sale!” Based on the matched determination condition received from the server 2 (step S420).
- the application service server 4 has response voice data or a response voice data generation algorithm corresponding to the determination condition, for example, and can generate response voice data based on the “matched determination condition” received from the server 2. is there.
- the response voice data generation process according to the second embodiment has been specifically described above.
- the response voice data generated by the application service server 4 is transmitted from the application service server 4 to the terminal device 1-2 via the server 2 as shown in steps S257 to S263 in FIG. 2 is output as audio.
- FIG. 20 is a diagram for explaining an application example of the present embodiment.
- a user who passes in front of a fortune teller may “depress”, “worry”, “ When a predetermined keyword indicating anxiety such as “anxiety” is frequently uttered (for example, when a word indicating anxiety is spoken five times or more per week), response voice data recommending fortune-telling to the user You may make it output from the terminal device 1-2.
- a user specified by voiceprint analysis is a premium user when he / she utters something at a high frequency in the past, has a specific user attribute, and utters a predetermined keyword. judge.
- the user attributes are a user's sex, age, and the like estimated by voice recognition of the user's speech voice data.
- the application service used in the present embodiment is “Application service ID: app0003, application name: EE Shopping Center Male Premium User Benefit, Judgment condition: 5 days within one week, registered in the application service management table shown in FIG. Corresponds to “Visit to the store (speak something in the store), adult male, and a specific keyword“ hot ””.
- FIG. 21 is a diagram for explaining the outline of this embodiment.
- a customer visits a store near the terminal devices 1-3a to 1-3c (may be singular) installed in many “EE shopping centers”.
- the user speaks for a predetermined date (for example, 5 days) or more within a predetermined period (for example, one week), and the attribute of the user is “adult male” and, as shown in the lower part of FIG.
- a predetermined date for example, 5 days
- a predetermined period for example, one week
- each of the terminal devices 1-3a to 1-3d is a terminal device group installed in the EE shopping center, and at least one of the terminal devices 1-3 recognizes the utterance and performs user identification. .
- the present embodiment is not limited to this, and one terminal device 1-3 may be provided.
- FIG. 22 is a flowchart showing premium user determination processing according to the third embodiment.
- the server 2 estimates the user attributes (gender, age, etc.) by voice recognition of the utterance voice information (step S503).
- the control unit 20 of the server 2 sets the gender and age (age) as user attributes based on the user's way of speaking, tone, wording of endings, voice color, voice pitch, voice characteristics, or voiceprint. presume.
- the premium user determination unit 20f refers to the user identification history (see FIG. 10) and the application service terminal list stored in the storage unit 23, and the user utterance frequency with respect to the terminal device belonging to the application service ID to be applied Is acquired (step S506). Specifically, for example, the premium user determination unit 20f extracts terminal devices 1-3a to 1-3c belonging to the same application service ID as the application service ID applied to the terminal device 1-3d from the application service terminal list. To do. Next, the premium user determination unit 20f compares the user identification history with the date and time (speech frequency) when the user was identified by the terminal devices 1-3a to 1-3d (that is, the user's utterance was recognized by voiceprint analysis). get.
- the premium user determination unit 20f determines whether or not the user has made any utterance for five days or more in the past week according to the premium user determination condition of the application service ID: app0003 registered in the application service management table (step S20). In step S509, it is determined whether the attribute is “adult male” (step S512) or whether a predetermined keyword “hot” is uttered (step S515).
- step S515 the premium user determination unit 20f determines that the user is a premium user (step S518).
- step S509 / No, step S512 / No, or step S515 / No the premium user determining unit 20f determines that the user is not a premium user (step S519).
- the premium user determination process according to the third embodiment has been specifically described above.
- a user who has made a certain utterance for a predetermined number of days or more within a predetermined period without specifying a keyword that is, a user who is estimated to have visited the store for a predetermined number of days within a predetermined period
- a specific keyword serving as a trigger is uttered, it is determined that the user is a premium user.
- FIG. 23 is a flowchart showing response voice data generation processing according to the third embodiment.
- the application service server 4 generates predetermined response voice data such as “Happy hour from 4 o'clock! Beer is half price!” Based on the matched determination condition received from the server 2 (step S520). ).
- the application service server 4 has response voice data or a response voice data generation algorithm corresponding to the determination condition, for example, and can generate response voice data based on the “matched determination condition” received from the server 2. is there.
- the response voice data generation process according to the third embodiment has been specifically described above.
- the response voice data generated by the application service server 4 is transmitted from the application service server 4 to the terminal device 1-3 via the server 2 as shown in steps S257 to S263 in FIG. 3 is output as audio.
- the place where the terminal device 1-3 is installed is not limited to a store, but may be a game arcade such as a game center, for example.
- a game arcade such as a game center
- the case where the terminal device 1-3 is installed in the game center will be described with reference to FIGS.
- FIG. 24 is a diagram for explaining the outline of application example 1 of the present embodiment.
- a terminal device 1-3a is installed around the game machine 5, and an adult male user often passes in front of the game machine 5 (for example, 10 days or more within one month).
- stress relief such as ⁇ I'm messy '', ⁇ I'm irritated '', ⁇ I want to blow it up '' in conversations with my accompanying people or in my own words etc.
- it can be estimated that the game is in an optimum state for recommending a game, and it is determined that the user is a premium user.
- response voice data recommending that stress is released by the game machine 5 hitting the sandbag is output from the terminal device 1-3a.
- the play history (score) of the game machine 5 if the average score of the user so far (an example of user information) exceeds the highest score of all players of the day today, It is possible to make a response that recommends the game, including a message such as “You can be the top today.”
- FIG. 25 is a flowchart showing premium user determination processing according to Application Example 1.
- the server 2 estimates the user's attributes (gender, age, etc.) by voice recognition of the utterance voice information (step S603).
- the control unit 20 of the server 2 estimates gender and age (age) as user attributes from the user's speech, tone, voice color, voice pitch, voice characteristics, voice print, and the like.
- the premium user determination unit 20f refers to the user identification history (see FIG. 10) and the application service terminal list (see FIG. 7) stored in the storage unit 23, and belongs to the application service ID to be applied.
- the utterance frequency of the user is acquired (step S606).
- the premium user determination unit 20f includes a terminal device belonging to the same application service ID as the application service ID applied to the terminal device 1-3a (for example, a plurality of devices installed around a game machine or a game center). Terminal device) is extracted from the application service terminal list.
- the premium user determination unit 20f compares the user identification history with the terminal device 1-3a or the terminal device belonging to the application service ID (that is, the date and time when the user's utterance was recognized by voiceprint analysis). (Speech frequency) is acquired.
- the premium user determination unit 20f determines a premium user according to the premium user determination condition of the application service registered in the application service management table (steps S609 to S615). Specifically, for example, whether or not the user has made any utterance for 10 days or more in the past month (step S609), whether the attribute is “adult male” (step S612), a predetermined keyword “munching”, It is determined whether or not a word requiring stress release such as “I want to make a mistake” is spoken (step S615). Note that each determination condition is an example, and the present application example is not limited to this.
- step S609 / Yes, step S612 / Yes, step S615 / Yes the premium user determination unit 20f determines that the user is a premium user (step S618).
- step S609 / No, step S612 / No, or step S615 / No the premium user determining unit 20f determines that the user is not a premium user (step S619).
- the premium user determination process according to the application example 1 has been specifically described.
- a user who has made a certain utterance for a predetermined number of days within a predetermined period without specifying a keyword that is, a user who is estimated to have visited for a predetermined number of days within a predetermined period
- a keyword that is, a user who is estimated to have visited for a predetermined number of days within a predetermined period
- FIG. 26 is a flowchart showing response voice data generation processing according to this application example.
- response sound data is generated in consideration of the game play history.
- the play history of each user is accumulated in “application service data” of a user management table (see FIG. 8) stored in the storage unit 23 of the server 2, for example.
- the application service server 4 transmits the user ID of the user determined to be a premium user and the application service ID to the server 2 (step S620).
- the application service server 4 receives the application data of the user from the server 2 (step S623), and records the play history of the user in the game machine 5 associated with the application service recorded in the application data. Obtain (step S626).
- the application service server 4 determines whether or not the average score of the user is higher than today's high score (step S632).
- step S632 when it is determined that the number exceeds (step S632 / Yes), the application service server 4 determines, for example, “Would you like to go around once? Predetermined response voice data such as “I can be the top today!” Is generated (step S635).
- step S632 determines, for example, “Will you go around once? Predetermined response voice data such as “Let's do it!” Is generated (step S638).
- the response voice data generated by the application service server 4 is transmitted from the application service server 4 to the terminal device 1-3a via the server 2 as shown in steps S257 to S263 in FIG. Audio is output from 3a.
- FIG. 27 is a sequence diagram illustrating a management process of play results of the game machine 5 according to the application example 1.
- step S643 when the game machine 5 starts playing the game (step S643), the game machine 5 notifies the application service server 4 of the start of play via the network (step S646).
- the application service server 4 starts the game within a certain time after the premium user is determined by the server 2 (step S649 / Yes). It is determined that the user is playing a game (step S652).
- the user ID of the premium user determined by the server 2 is also transmitted to the application service server 4, so that the application service server 4 determines that the premium user has been determined by the server 2 and the user ID of the premium user. Can be recognized.
- the application service server 4 transmits the received play result to the server 2 together with the user ID of the premium user and its own application service ID (Ste S658).
- the server 2 updates the application data associated with the corresponding user and application service in the user management table (see FIG. 8) (step S661). That is, the server 2 registers the play result of the premium user in the game as application data in the user management table.
- the application service server 4 can also receive a play result of a normal user who is not determined to be a premium user from the game machine 5 and record it as a play history. Specifically, when a play result is transmitted from the game machine 5 when the premium user is not determined, the application service server 4 accumulates the play result as a play result of an unspecified user (player). In addition, the application service server 4 transmits the play result of the unspecified user to the server 2 together with its own application service ID. The server 2 registers the received play result of the unspecified user in association with the corresponding application service in the application service management table (see FIG. 5), for example. Thereby, for example, the score of the player of the day in the game machine 5 can be grasped.
- response voice data can be generated by referring to a play history (for example, a score) in the game machine 5 in conjunction with the game machine 5.
- a play history for example, a score
- FIG. 28 is a diagram for explaining the outline of the application example 2.
- an adult male user who frequently visits the batting center (for example, 3 days or more per week) Is determined to be a premium user. If it is determined that the user is a premium user, response voice data recommending the use of the batting center is output from the terminal device 1-3b as shown in the lower part of FIG.
- FIG. 29 is a flowchart showing a premium user determination process according to Application Example 2.
- the server 2 estimates the user attributes (gender, age, etc.) by voice recognition of the speech voice information (step S703).
- the control unit 20 of the server 2 estimates gender and age (age) as user attributes from the user's speech, tone, voice color, voice pitch, voice characteristics, voice print, and the like.
- the premium user determination unit 20f refers to the user identification history (see FIG. 10) and the application service terminal list (see FIG. 7) stored in the storage unit 23, and belongs to the application service ID to be applied.
- the user's utterance frequency is acquired (step S706).
- the premium user determination unit 20f for example, the terminal device belonging to the same application service ID as the application service ID applied to the terminal device 1-3b (for example, a plurality of terminal devices installed in the batting center). Are extracted from the application service terminal list.
- the premium user determination unit 20f compares the user identification history with the terminal device 1-3b or the terminal device belonging to the application service ID (that is, the date and time when the user's utterance was recognized by voiceprint analysis). (Speech frequency) is acquired.
- the premium user determination unit 20f determines a premium user according to the premium user determination condition of the application service registered in the application service management table (steps S709 to S715). Specifically, for example, whether or not the user has made any utterance for three days or more in the past week (step S709), whether the attribute is “adult male” (step S712), a predetermined keyword ( It is determined whether a team name, a player name, etc.) are spoken (step S715).
- each determination condition is an example, and the present application example is not limited to this.
- step S709 / Yes, step S712 / Yes, step S715 / Yes the premium user determination unit 20f determines that the user is a fan of a specific team and sets the user attribute It adds (step S718) and determines with the said user being a premium user (step S721).
- the user attributes are accumulated in, for example, a user management table (see FIG. 8) stored in the storage unit 23 of the server 2.
- step S709 / No, step S712 / No, or step S715 / No the premium user determination unit 20f determines that the user is not a premium user (step S724).
- the premium user determination process according to the application example 2 has been specifically described.
- a user who has made a certain utterance for a predetermined number of days within a predetermined period without specifying a keyword that is, a user who is estimated to have visited for a predetermined number of days within a predetermined period
- FIG. 30 is a flowchart showing response voice data generation processing according to this application example.
- response voice data is generated in consideration of which team (baseball team) the user is a fan of. Which team is a fan of each user is accumulated in, for example, a user management table (see FIG. 8) stored in the storage unit 23 of the server 2 as an example of attribute information.
- the application service server 4 acquires which team is a fan based on the attributes of the premium user (step S730). Specifically, for example, the application service server 4 transmits the user ID of the premium user to the server 2 to request the attribute information of the user, and acquires information on which team the fan is.
- the application service server 4 acquires the previous day's professional baseball win / loss data from a predetermined server (not shown) on the network (step S733).
- step S736 / Yes when the user is a G team (an example of a team) fan (step S736 / Yes), the application service server 4 refers to the previous day's professional baseball win / loss data to confirm whether the G team has won ( Step S739).
- the application service server 4 may, for example, say “G team won last night. Response voice data such as “Your big brother! You can hit it for half the price today!” (Step S742).
- step S739 / No the application service server 4 generates response voice data such as “It was a shame last night. Wouldn't you like to revenge?” (Step S745). .
- the application service server 4 refers to the previous day's professional baseball win / loss data to check whether the H team has won. (Step S751).
- the application service server 4 may, for example, say “H team won last night. Response voice data such as “Old brother! Today is limited to customers and you can hit it at half price!” Is generated (step S754).
- step S751 the application service server 4 sends response voice data such as “It was a shame last night. Generate (step S757).
- step S760 the user generates response voice data in accordance with the winning or losing of the specific team of the fans.
- the response voice data generated by the application service server 4 is transmitted from the application service server 4 to the terminal device 1-3b via the server 2 as shown in steps S257 to S263 in FIG. Audio is output from 3b.
- the terminal device 1-3b provided with response voice data recommending batting in the batting center after referring to the game contents of the team. Can be output from.
- the present embodiment since the user is specified by voice processing, there is an advantage that the processing load is relatively small.
- voice collection has an effect that fewer users have resistance compared to imaging by a camera, and a microphone has less directivity than a camera, so that it is easy to acquire peripheral voice information.
- the present embodiment is not limited to audio processing alone, and user determination may be performed by using a camera in an auxiliary manner, such as when user determination is difficult only by audio processing such as voiceprint analysis.
- a computer program for causing the terminal device 1 or the server 2 to exhibit the functions of the terminal device 1 or the server 2 on hardware such as the CPU, ROM, and RAM incorporated in the terminal device 1 or the server 2 described above.
- a computer-readable storage medium storing the computer program is also provided.
- positive users such as regular customers are determined based on the utterance voice.
- the present embodiment is not limited to this, and the suspicious person is based on the utterance voice using the system. It is also possible to determine negative users such as unfavorable customers. If it is determined that the user is a negative user, the server 2 may generate response voice data corresponding to security and output the response voice data from the terminal device 1.
- a communication unit capable of receiving audio information related to audio collected by a plurality of discretely arranged microphones; At least a specified number of utterances in a certain period at least for a user identified based on audio information related to audio collected by a specific microphone among the plurality of microphones received via the communication unit It is determined that it is the specific user who went, A control unit that controls the speaker corresponding to the specific microphone to transmit audio information to be transmitted to the specific user via the communication unit;
- An information processing apparatus comprising: (2) The controller is When it is determined that a user identified based on audio information related to audio collected by a specific microphone is a specific user defined in application service units, The information processing apparatus according to (1), wherein the audio information to be transmitted to the specific user is controlled to be transmitted to the speaker corresponding to the specific microphone via the communication unit.
- the controller is According to the keyword extracted as a result of recognizing the voice information related to the voice collected by the specific microphone and the keyword specified in the application service unit, the user identified based on the voice information is assigned to the application service unit.
- the information processing apparatus according to (2) wherein the information processing apparatus determines that the user is a specific user defined in (2).
- the controller is The user identified based on the voice information is determined to be a specific user defined for each application service according to the attribute of the user specified based on the voice information related to the voice collected by the specific microphone.
- the controller is Audio information corresponding to the user information is transmitted to the speaker corresponding to the specific microphone via the communication unit according to the user information specified based on the audio information related to the sound collected by the specific microphone.
- the information processing apparatus according to any one of (2) to (4), wherein the information processing apparatus is controlled so as to perform.
- the control unit analyzes a voice print of the collected voice to identify a user.
- the control unit performs the determination of the specific user by using a determination condition defined by an application service applied to a speaker corresponding to a specific microphone that picks up the sound, (2) to (7) The information processing apparatus according to any one of the above.
- Processor Audio information related to audio collected by a specific microphone among the plurality of microphones, received via a communication unit capable of receiving audio information related to audio collected by a plurality of discretely arranged microphones Determining that the user identified based on is a specific user who has made at least a prescribed number of utterances in a certain period; Controlling to transmit audio information to be transmitted to the specific user to the speaker corresponding to the specific microphone via the communication unit; Including an information processing method.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Otolaryngology (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Telephonic Communication Services (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
1.本開示の一実施形態による情報処理システムの概要
2.構成
2-1.端末装置1の構成
2-2.サーバ2の構成
3.動作処理
3-1.登録処理
3-2.応答処理
4.実施例
4-1.第1の実施例
4-2.第2の実施例
4-3.第3の実施例
(4-3-1.応用例1)
(4-3-2.応用例2)
5.まとめ
図1は、本開示の一実施形態による情報処理システムの概要について説明する図である。図1に示すように、本実施形態による情報処理システムは、音声の入力および出力機能を有する端末装置1によりユーザの発話音声を収音し、所定の条件を満たす特定ユーザであると判定されたユーザに対して、所定の応答音声を出力する。
<2-1.端末装置1の構成>
図3は、本実施形態による端末装置1の構成の一例を示すブロック図である。図3に示すように、端末装置1は、制御部10、通信部11、音声入力部12、音声出力部13、および記憶部14を有する。
図4は、本実施形態によるサーバ2の構成の一例を示すブロック図である。図4に示すように、サーバ2(情報処理装置)は、制御部20、ネットワーク通信部21、アプリケーションサービスサーバI/F(インタフェース)22、および記憶部23を有する。
制御部20は、演算処理装置および制御装置として機能し、各種プログラムに従ってサーバ2内の動作全般を制御する。制御部20は、例えばCPU(Central Processing Unit)、マイクロプロセッサ等の電子回路によって実現される。また、制御部20は、使用するプログラムや演算パラメータ等を記憶するROM(Read Only Memory)、及び適宜変化するパラメータ等を一時記憶するRAM(Random Access Memory)を含んでいてもよい。
ネットワーク通信部21は、有線または無線によりネットワーク3と接続し、ネットワーク3を介して各端末装置1とデータの送受信を行う。ネットワーク通信部21は、例えば有線/無線LAN(Local Area Network)、またはWi-Fi(Wireless Fidelity、登録商標)等によりネットワーク3と通信接続する。
アプリケーションサービスサーバI/F22は、アプリケーションサービスサーバ4とデータの送受信を行う。アプリケーションサービスサーバI/F22との通信は、専用回線を介してでもよいし、ネットワーク3を介してであってもよい。
記憶部23は、制御部20の処理に用いられるプログラムや演算パラメータ等を記憶するROM、および適宜変化するパラメータ等を一時記憶するRAMにより実現される。例えば本実施形態による記憶部23は、上述したアプリケーションサービス管理テーブル、アプリケーションサービスキーワードリスト、アプリケーションサービス端末リスト、ユーザ管理テーブル、ユーザキーワード履歴、およびユーザ特定履歴を記憶する。
続いて、本実施形態による情報処理システムの動作処理について図面を用いて具体的に説明する。
まず、図11を参照してアプリケーションサービスの登録処理について説明する。図11は、本実施形態によるアプリケーションサービスの登録処理を示すシーケンス図である。
続いて、プレミアムユーザを判定して所定のアプリケーションサービスに基づく応答を行う動作処理について図12および図13を参照して説明する。図12および図13は、本実施形態による情報処理システムの応答処理を示すシーケンス図である。
<4-1.第1の実施例>
第1の実施例では、声紋解析により特定したユーザが、店舗において過去に高い頻度で何らかの発声を行っていた(すなわち、高い頻度で来店した)場合に、プレミアムユーザであると判定する。なお、本実施例で用いるアプリケーションサービスは、図5に示すアプリケーションサービス管理テーブルに登録された「アプリケーションサービスID:app0002、アプリケーション名:DDモール来店感謝イベント、判定条件:1週間内に5日来店(何かを発声)した場合」に相当する。
続いて、第1の実施例による動作処理について説明する。本実施例による基本的な動作処理は、主に図12および図13を参照して説明した動作処理と同様であるため、ここでは本実施例特有の処理となるプレミアムユーザ判定処理(図13に示すステップS239)および応答音声データ生成処理(図13に示すステップS254)について図15および図16を参照して順次説明する。
図15は、第1の実施例によるプレミアムユーザの判定処理を示すフローチャートである。図15に示すように、まず、サーバ2のプレミアムユーザ判定部20fは、記憶部23に記憶されているユーザ特定履歴(図10参照)およびアプリケーションサービス端末リストを参照し、適用するアプリケーションサービスIDに属している端末装置に対するユーザの発声頻度を取得する(ステップS303)。具体的には、例えばプレミアムユーザ判定部20fは、端末装置1-1dに適用されるアプリケーションサービスIDと同じアプリケーションサービスIDに属している端末装置1-1a~1-1cをアプリケーションサービス端末リストから抽出する。次いで、プレミアムユーザ判定部20fは、ユーザ特定履歴と照らし合わせ、端末装置1-1a~1-1dでユーザが特定された(すなわち声紋解析によりユーザの発話が認識された)日時(発声頻度)を取得する。
図16は、第1の実施例による応答音声データの生成処理を示すフローチャートである。図16に示すように、アプリケーションサービスサーバ4は、サーバ2から受信した、合致した判定条件に基づいて、例えば「毎度ご利用ありがとうございます」といった所定の応答音声データを生成する(ステップS320)。アプリケーションサービスサーバ4は、例えば判定条件に応じた応答音声データ若しくは応答音声データの生成アルゴリズムを保有し、サーバ2から受信した「合致した判定条件」に基づいて応答音声データを生成することが可能である。
第2の実施例では、声紋解析により特定したユーザが、店舗で過去に高い頻度で所定のキーワードを発声していた場合に、プレミアムユーザであると判定する。なお、本実施例で用いるアプリケーションサービスは、図5に示すアプリケーションサービス管理テーブルに登録された「アプリケーションサービスID:app0001、アプリケーション名:ABC商店街お得意様キャンペーン、判定条件:1ヶ月内に『ビーフジャーキー』を10回注文(『ビーフジャーキー』と発声)」に相当する。
続いて、第2の実施例による動作処理について説明する。本実施例による基本的な動作処理は、主に図12および図13を参照して説明した動作処理と同様であるため、ここでは本実施例特有の処理となるプレミアムユーザ判定処理(図13に示すステップS239)および応答音声データ生成処理(図13に示すステップS254)について図18および図19を参照して順次説明する。
図18は、第2の実施例によるプレミアムユーザの判定処理を示すフローチャートである。図18に示すように、まず、サーバ2のプレミアムユーザ判定部20fは、記憶部23に記憶されているユーザキーワード履歴(図9参照)を参照し、所定のキーワード「ビーフジャーキー」のユーザによる発声頻度を取得する(ステップS403)。具体的には、例えばプレミアムユーザ判定部20fは、端末装置1-2dに適用されるアプリケーションサービスの対象となるプレミアムユーザの判定条件に用いられる所定のキーワードを、アプリケーションサービスキーワードリストから抽出する。次いで、プレミアムユーザ判定部20fは、ユーザキーワード履歴と照らし合わせ、ユーザが所定のキーワードを発声した日時(発声頻度)を取得する。
図19は、第2の実施例による応答音声データの生成処理を示すフローチャートである。図19に示すように、アプリケーションサービスサーバ4は、サーバ2から受信した、合致した判定条件に基づいて、例えば「ビーフジャーキーの特売だよ!」といった所定の応答音声データを生成する(ステップS420)。アプリケーションサービスサーバ4は、例えば判定条件に応じた応答音声データ若しくは応答音声データの生成アルゴリズムを保有し、サーバ2から受信した「合致した判定条件」に基づいて応答音声データを生成することが可能である。
第3の実施例では、声紋解析により特定したユーザが、店舗で過去に高い頻度で何らかの発声を行い、かつ特定のユーザ属性を持ち、かつ所定のキーワードを発声した場合に、プレミアムユーザであると判定する。ユーザ属性とは、ユーザの発話音声データの音声認識により推定されるユーザの性別や年齢等である。なお、本実施例で用いるアプリケーションサービスは、図5に示すアプリケーションサービス管理テーブルに登録された「アプリケーションサービスID:app0003、アプリケーション名:EEショッピングセンター男性プレミアムユーザ特典、判定条件:1週間内に5日来店(店内で何かを発声)、かつ成人男性、かつ特定のキーワード『暑い』を発声した場合」に相当する。
続いて、第3の実施例による動作処理について説明する。本実施例による基本的な動作処理は、主に図12および図13を参照して説明した動作処理と同様であるため、ここでは本実施例特有の処理となるプレミアムユーザ判定処理(図13に示すステップS239)および応答音声データ生成処理(図13に示すステップS254)について図22および図23を参照して順次説明する。
図22は、第3の実施例によるプレミアムユーザの判定処理を示すフローチャートである。図22に示すように、まず、サーバ2は、発話音声情報の音声認識により、ユーザの属性(性別、年代等)を推定する(ステップS503)。具体的には、例えばサーバ2の制御部20は、ユーザの話し方、口調、語尾の言い回し、声色、声の高さ、声の特徴、または声紋等から、ユーザ属性として性別や年代(年齢)を推定する。
図23は、第3の実施例による応答音声データの生成処理を示すフローチャートである。図23に示すように、アプリケーションサービスサーバ4は、サーバ2から受信した合致した判定条件に基づいて、例えば「4時からハッピーアワー!ビールが半額!」といった所定の応答音声データを生成する(ステップS520)。アプリケーションサービスサーバ4は、例えば判定条件に応じた応答音声データ若しくは応答音声データの生成アルゴリズムを保有し、サーバ2から受信した「合致した判定条件」に基づいて応答音声データを生成することが可能である。
なお、端末装置1-3が設置される場所は店舗に限定されず、例えばゲームセンター等の遊技場であってもよい。ここで、端末装置1-3がゲームセンターに設置されている場合について図24~図27を参照して説明する。
次に、本応用例の動作処理について説明する。本実施例による基本的な動作処理は、主に図12および図13を参照して説明した動作処理と同様であるため、ここでは本実施例特有の処理となるプレミアムユーザ判定処理(図13に示すステップS239)および応答音声データ生成処理(図13に示すステップS254)について図25および図26を参照して順次説明する。
図25は、応用例1によるプレミアムユーザの判定処理を示すフローチャートである。図25に示すように、まず、サーバ2は、発話音声情報の音声認識により、ユーザの属性(性別、年代等)を推定する(ステップS603)。具体的には、例えばサーバ2の制御部20は、ユーザの話し方、口調、声色、声の高さ、声の特徴、または声紋等から、ユーザ属性として性別や年代(年齢)を推定する。
図26は、本応用例による応答音声データの生成処理を示すフローチャートである。本応用例では、ゲームのプレイ履歴も考慮して応答音声データを生成する。各ユーザのプレイ履歴は、例えばサーバ2の記憶部23に記憶されたユーザ管理テーブル(図8参照)の「アプリケーションサービスデータ」に蓄積されている。
次に、ゲーム機5のプレイ結果の管理処理について、図27を参照して説明する。図27は、応用例1によるゲーム機5のプレイ結果の管理処理を示すシーケンス図である。
また、端末装置1-3が設置される場所は、上述した例に限定されず、例えばバッティングセンターであってもよい。図28は、応用例2の概要について説明する図である。
次に、本応用例の動作処理について説明する。本実施例による基本的な動作処理は、主に図12および図13を参照して説明した動作処理と同様であるため、ここでは本実施例特有の処理となるプレミアムユーザ判定処理(図13に示すステップS239)および応答音声データ生成処理(図13に示すステップS254)について図29および図30を参照して順次説明する。
図29は、応用例2によるプレミアムユーザの判定処理を示すフローチャートである。図29に示すように、まず、サーバ2は、発話音声情報の音声認識により、ユーザの属性(性別、年代等)を推定する(ステップS703)。具体的には、例えばサーバ2の制御部20は、ユーザの話し方、口調、声色、声の高さ、声の特徴、または声紋等から、ユーザ属性として性別や年代(年齢)を推定する。
図30は、本応用例による応答音声データの生成処理を示すフローチャートである。本応用例では、ユーザがどの球団(野球チーム)のファンであるかも考慮して応答音声データを生成する。各ユーザがどの球団のファンであるかは、属性情報の一例として、例えばサーバ2の記憶部23に記憶されたユーザ管理テーブル(図8参照)に蓄積される。
上述したように、本開示の実施形態による情報処理システムでは、ユーザの発話音声を収音し、所定期間内のユーザの発話回数に基づいて特定ユーザを認識することが可能となる。
(1)
離散的に配される複数のマイクロホンにより収音された音声に関する音声情報を受信可能な通信部と、
前記通信部を介して受信された、前記複数のマイクロホンのうちの特定のマイクロホンにより収音された音声に関する音声情報に基づき識別されたユーザを、少なくとも、一定の期間に規定の回数以上の発話を行った特定ユーザであると判別し、
前記通信部を介して、前記特定のマイクロホンに対応するスピーカに対して、前記特定ユーザに送信すべき音声情報を送信するように制御する制御部と、
を備える、情報処理装置。
(2)
前記制御部は、
特定のマイクロホンにより収音された音声に関する音声情報に基づき識別されたユーザを、アプリケーションサービス単位で規定されている特定ユーザであると判定するとき、
前記通信部を介して、前記特定のマイクロホンに対応するスピーカに対して、前記特定ユーザに送信すべき音声情報を送信するように制御する、前記(1)に記載の情報処理装置。
(3)
前記制御部は、
特定のマイクロホンにより収音された音声に関する音声情報を認識した結果抽出されたキーワードと、アプリケーションサービス単位で規定されているキーワードとに応じて、当該音声情報に基づき識別されたユーザを、アプリケーションサービス単位で規定されている特定ユーザであると判定する、前記(2)に記載の情報処理装置。
(4)
前記制御部は、
特定のマイクロホンにより収音された音声に関する音声情報に基づき特定されたユーザの属性に応じて、当該音声情報に基づき識別されたユーザを、アプリケーションサービス単位で規定されている特定ユーザであると判定する、前記(2)に記載の情報処理装置。
(5)
前記制御部は、
特定のマイクロホンにより収音された音声に関する音声情報に基づき特定されたユーザ情報に応じて、前記通信部を介して前記特定のマイクロホンに対応するスピーカに対し、前記ユーザ情報に応じた音声情報を送信するように制御する、前記(2)~(4)のいずれか1項に記載の情報処理装置。
(6)
前記ユーザ情報は、ユーザ属性、連動するゲーム機のプレイ履歴、またはユーザの嗜好情報である、前記(5)に記載の情報処理装置。
(7)
前記制御部は、前記収音された音声の声紋を解析してユーザの識別を行う、前記(1)~(6)のいずれか1項に記載の情報処理装置。
(8)
前記制御部は、前記音声を収音した特定のマイクロホンに対応するスピーカに適用されるアプリケーションサービスで規定された判定条件を用いて、前記特定ユーザの判定を行う、前記(2)~(7)のいずれか1項に記載の情報処理装置。
(9)
プロセッサが、
離散的に配される複数のマイクロホンにより収音された音声に関する音声情報を受信可能な通信部を介して受信された、前記複数のマイクロホンのうちの特定のマイクロホンにより収音された音声に関する音声情報に基づき識別されたユーザを、少なくとも、一定の期間に規定の回数以上の発話を行った特定ユーザであると判別することと、
前記通信部を介して、前記特定のマイクロホンに対応するスピーカに対して、前記特定ユーザに送信すべき音声情報を送信するように制御することと、
を含む、情報処理方法。
2 サーバ
3 ネットワーク
4 アプリケーションサービスサーバ
5 ゲーム機
10 制御部
11 通信部
12 音声入力部
13 音声出力部
14 記憶部
20 制御部
20a アプリケーションサービス管理部
20b ユーザ情報管理部
20c 声紋解析部
20d 音声認識部
20e ユーザ特定部
20f プレミアムユーザ判定部
20g 応答音声データ取得部
21 ネットワーク通信部
22 アプリケーションサービスサーバI/F
23 記憶部
Claims (9)
- 離散的に配される複数のマイクロホンにより収音された音声に関する音声情報を受信可能な通信部と、
前記通信部を介して受信された、前記複数のマイクロホンのうちの特定のマイクロホンにより収音された音声に関する音声情報に基づき識別されたユーザを、少なくとも、一定の期間に規定の回数以上の発話を行った特定ユーザであると判別し、
前記通信部を介して、前記特定のマイクロホンに対応するスピーカに対して、前記特定ユーザに送信すべき音声情報を送信するように制御する制御部と、
を備える、情報処理装置。 - 前記制御部は、
特定のマイクロホンにより収音された音声に関する音声情報に基づき識別されたユーザを、アプリケーションサービス単位で規定されている特定ユーザであると判定するとき、
前記通信部を介して、前記特定のマイクロホンに対応するスピーカに対して、前記特定ユーザに送信すべき音声情報を送信するように制御する、請求項1に記載の情報処理装置。 - 前記制御部は、
特定のマイクロホンにより収音された音声に関する音声情報を認識した結果抽出されたキーワードと、アプリケーションサービス単位で規定されているキーワードとに応じて、当該音声情報に基づき識別されたユーザを、アプリケーションサービス単位で規定されている特定ユーザであると判定する、請求項2に記載の情報処理装置。 - 前記制御部は、
特定のマイクロホンにより収音された音声に関する音声情報に基づき特定されたユーザの属性に応じて、当該音声情報に基づき識別されたユーザを、アプリケーションサービス単位で規定されている特定ユーザであると判定する、請求項2に記載の情報処理装置。 - 前記制御部は、
特定のマイクロホンにより収音された音声に関する音声情報に基づき特定されたユーザ情報に応じて、前記通信部を介して前記特定のマイクロホンに対応するスピーカに対し、前記ユーザ情報に応じた音声情報を送信するように制御する、請求項2に記載の情報処理装置。 - 前記ユーザ情報は、ユーザ属性、連動するゲーム機のプレイ履歴、またはユーザの嗜好情報である、請求項5に記載の情報処理装置。
- 前記制御部は、前記収音された音声の声紋を解析してユーザの識別を行う、請求項1に記載の情報処理装置。
- 前記制御部は、前記音声を収音した特定のマイクロホンに対応するスピーカに適用されるアプリケーションサービスで規定された判定条件を用いて、前記特定ユーザの判定を行う、請求項2に記載の情報処理装置。
- プロセッサが、
離散的に配される複数のマイクロホンにより収音された音声に関する音声情報を受信可能な通信部を介して受信された、前記複数のマイクロホンのうちの特定のマイクロホンにより収音された音声に関する音声情報に基づき識別されたユーザを、少なくとも、一定の期間に規定の回数以上の発話を行った特定ユーザであると判別することと、
前記通信部を介して、前記特定のマイクロホンに対応するスピーカに対して、前記特定ユーザに送信すべき音声情報を送信するように制御することと、
を含む、情報処理方法。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201780067884.4A CN109906466B (zh) | 2016-11-08 | 2017-08-04 | 信息处理设备和信息处理方法 |
KR1020197011717A KR20190084033A (ko) | 2016-11-08 | 2017-08-04 | 정보 처리 장치 및 정보 처리 방법 |
EP17870181.9A EP3540677A4 (en) | 2016-11-08 | 2017-08-04 | INFORMATION PROCESSING DEVICE AND INFORMATION PROCESSING METHOD |
JP2018550028A JP7092035B2 (ja) | 2016-11-08 | 2017-08-04 | 情報処理装置および情報処理方法 |
US16/330,131 US11289099B2 (en) | 2016-11-08 | 2017-08-04 | Information processing device and information processing method for determining a user type based on performed speech |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2016218130 | 2016-11-08 | ||
JP2016-218130 | 2016-11-08 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018087967A1 true WO2018087967A1 (ja) | 2018-05-17 |
Family
ID=62109758
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2017/028471 WO2018087967A1 (ja) | 2016-11-08 | 2017-08-04 | 情報処理装置および情報処理方法 |
Country Status (6)
Country | Link |
---|---|
US (1) | US11289099B2 (ja) |
EP (1) | EP3540677A4 (ja) |
JP (1) | JP7092035B2 (ja) |
KR (1) | KR20190084033A (ja) |
CN (1) | CN109906466B (ja) |
WO (1) | WO2018087967A1 (ja) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10777203B1 (en) * | 2018-03-23 | 2020-09-15 | Amazon Technologies, Inc. | Speech interface device with caching component |
US11152006B2 (en) * | 2018-05-07 | 2021-10-19 | Microsoft Technology Licensing, Llc | Voice identification enrollment |
CN110111796B (zh) * | 2019-06-24 | 2021-09-17 | 秒针信息技术有限公司 | 识别身份的方法及装置 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001300099A (ja) | 2000-04-26 | 2001-10-30 | Ace Denken:Kk | 顧客管理装置 |
JP2004046233A (ja) | 2003-09-04 | 2004-02-12 | Daiichikosho Co Ltd | 通信カラオケ再生端末 |
JP2009145755A (ja) * | 2007-12-17 | 2009-07-02 | Toyota Motor Corp | 音声認識装置 |
JP2010156825A (ja) * | 2008-12-26 | 2010-07-15 | Fujitsu Ten Ltd | 音声出力装置 |
JP2011043715A (ja) | 2009-08-21 | 2011-03-03 | Daiichikosho Co Ltd | 歌声の特徴に基づいて顧客を特定して顧客の個人情報に基づくメッセージを出力する通信カラオケシステム |
JP2013164642A (ja) * | 2012-02-09 | 2013-08-22 | Nikon Corp | 検索手段制御装置、検索結果出力装置及びプログラム |
JP2014013494A (ja) * | 2012-07-04 | 2014-01-23 | Nikon Corp | 表示制御装置、表示システム、表示装置、端末装置、表示制御方法及びプログラム |
JP3190554U (ja) * | 2014-02-25 | 2014-05-15 | 泰三 玉置 | 車内会話装置 |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050043994A1 (en) * | 1996-09-04 | 2005-02-24 | Walker Jay S. | Method for allowing a customer to obtain a discounted price for a transaction and terminal for performing the method |
US6058364A (en) * | 1997-11-20 | 2000-05-02 | At&T Corp. | Speech recognition of customer identifiers using adjusted probabilities based on customer attribute parameters |
US6785647B2 (en) * | 2001-04-20 | 2004-08-31 | William R. Hutchison | Speech recognition system with network accessible speech processing resources |
US20070156470A1 (en) * | 2005-06-24 | 2007-07-05 | Granucci Nicole J | Automatically Calculating A Discount Using A Reservation System |
WO2008111190A1 (ja) | 2007-03-14 | 2008-09-18 | Pioneer Corporation | 音響モデル登録装置、話者認識装置、音響モデル登録方法及び音響モデル登録処理プログラム |
US20090157472A1 (en) * | 2007-12-14 | 2009-06-18 | Kimberly-Clark Worldwide, Inc. | Personalized Retail Information Delivery Systems and Methods |
US8412604B1 (en) * | 2009-09-03 | 2013-04-02 | Visa International Service Association | Financial account segmentation system |
US20120072290A1 (en) * | 2010-09-20 | 2012-03-22 | International Business Machines Corporation | Machine generated dynamic promotion system |
US20130006633A1 (en) * | 2011-07-01 | 2013-01-03 | Qualcomm Incorporated | Learning speech models for mobile device users |
JP5810946B2 (ja) | 2012-01-31 | 2015-11-11 | 富士通株式会社 | 特定通話検出装置、特定通話検出方法及び特定通話検出用コンピュータプログラム |
JP6314837B2 (ja) * | 2013-01-15 | 2018-04-25 | ソニー株式会社 | 記憶制御装置、再生制御装置および記録媒体 |
US20150324881A1 (en) | 2014-05-09 | 2015-11-12 | Myworld, Inc. | Commerce System and Method of Providing Intelligent Personal Agents for Identifying Intent to Buy |
US9691379B1 (en) * | 2014-06-26 | 2017-06-27 | Amazon Technologies, Inc. | Selecting from multiple content sources |
CN105448292B (zh) * | 2014-08-19 | 2019-03-12 | 北京羽扇智信息科技有限公司 | 一种基于场景的实时语音识别系统和方法 |
US9653075B1 (en) * | 2015-11-06 | 2017-05-16 | Google Inc. | Voice commands across devices |
JP6559079B2 (ja) | 2016-02-12 | 2019-08-14 | シャープ株式会社 | 対話型家電システム、および発話者との対話に基づいてメッセージを出力するためにコンピュータが実行する方法 |
US9898250B1 (en) * | 2016-02-12 | 2018-02-20 | Amazon Technologies, Inc. | Controlling distributed audio outputs to enable voice output |
CN105868360A (zh) * | 2016-03-29 | 2016-08-17 | 乐视控股(北京)有限公司 | 基于语音识别的内容推荐方法及装置 |
-
2017
- 2017-08-04 EP EP17870181.9A patent/EP3540677A4/en not_active Ceased
- 2017-08-04 JP JP2018550028A patent/JP7092035B2/ja active Active
- 2017-08-04 CN CN201780067884.4A patent/CN109906466B/zh active Active
- 2017-08-04 KR KR1020197011717A patent/KR20190084033A/ko active IP Right Grant
- 2017-08-04 WO PCT/JP2017/028471 patent/WO2018087967A1/ja unknown
- 2017-08-04 US US16/330,131 patent/US11289099B2/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001300099A (ja) | 2000-04-26 | 2001-10-30 | Ace Denken:Kk | 顧客管理装置 |
JP2004046233A (ja) | 2003-09-04 | 2004-02-12 | Daiichikosho Co Ltd | 通信カラオケ再生端末 |
JP2009145755A (ja) * | 2007-12-17 | 2009-07-02 | Toyota Motor Corp | 音声認識装置 |
JP2010156825A (ja) * | 2008-12-26 | 2010-07-15 | Fujitsu Ten Ltd | 音声出力装置 |
JP2011043715A (ja) | 2009-08-21 | 2011-03-03 | Daiichikosho Co Ltd | 歌声の特徴に基づいて顧客を特定して顧客の個人情報に基づくメッセージを出力する通信カラオケシステム |
JP2013164642A (ja) * | 2012-02-09 | 2013-08-22 | Nikon Corp | 検索手段制御装置、検索結果出力装置及びプログラム |
JP2014013494A (ja) * | 2012-07-04 | 2014-01-23 | Nikon Corp | 表示制御装置、表示システム、表示装置、端末装置、表示制御方法及びプログラム |
JP3190554U (ja) * | 2014-02-25 | 2014-05-15 | 泰三 玉置 | 車内会話装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3540677A4 |
Also Published As
Publication number | Publication date |
---|---|
JP7092035B2 (ja) | 2022-06-28 |
EP3540677A4 (en) | 2019-10-16 |
EP3540677A1 (en) | 2019-09-18 |
KR20190084033A (ko) | 2019-07-15 |
US11289099B2 (en) | 2022-03-29 |
US20190214023A1 (en) | 2019-07-11 |
CN109906466B (zh) | 2023-05-05 |
CN109906466A (zh) | 2019-06-18 |
JPWO2018087967A1 (ja) | 2019-09-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5855290B2 (ja) | 接客評価装置、接客評価システム及び接客評価方法 | |
TW201905895A (zh) | 聲音識別特徵的優化、動態註冊方法、客戶端和伺服器 | |
WO2018087967A1 (ja) | 情報処理装置および情報処理方法 | |
CN109145145A (zh) | 一种数据更新方法、客户端及电子设备 | |
JP2020080156A (ja) | プログラムおよび情報処理方法 | |
JP5477153B2 (ja) | 接客データ記録装置、接客データ記録方法およびプログラム | |
JP2011221891A (ja) | キーワード記録装置、接客支援装置、キーワード記録方法およびプログラム | |
CN110480656B (zh) | 一种陪护机器人、陪护机器人控制方法及装置 | |
JP5702422B2 (ja) | 情報処理装置、情報処理方法及び情報処理プログラム | |
JP6183841B2 (ja) | Ngワードの兆候を把握するコールセンタ用語管理システム及びその方法 | |
CN108320757A (zh) | 配送信息提示方法、装置、智能音箱及存储介质 | |
CN112262432A (zh) | 语音处理装置、语音处理方法以及记录介质 | |
JP2011065304A (ja) | 接客業務用サーバ、並びに、当該サーバを用いる接客システム及び接客業務の予測終了時間算出方法 | |
JP6347938B2 (ja) | 発話内重要語抽出装置とその装置を用いた発話内重要語抽出システムと、それらの方法とプログラム | |
JP7371749B2 (ja) | 情報処理装置、情報処理システム、情報処理方法及びプログラム | |
US20220036381A1 (en) | Data disclosure device, data disclosure method, and program | |
WO2022091940A1 (ja) | 情報処理装置、情報処理方法、及びプログラム | |
JP2022001967A (ja) | 音響イベント認識装置 | |
JP7244910B2 (ja) | 情報伝達システムおよびプログラム | |
CN112381989A (zh) | 排序方法、装置、系统和电子设备 | |
JP5749213B2 (ja) | 音声データ分析装置、音声データ分析方法および音声データ分析プログラム | |
JP2009245291A (ja) | 特典管理システム、特典管理方法及び特典管理プログラム | |
KR101748411B1 (ko) | 집단지성을 이용한 꿈 해몽 방법 및 장치 | |
CN113348502A (zh) | 语音识别方法、装置、存储介质及电子设备 | |
WO2022201339A1 (ja) | 価格管理システム、価格管理方法、及び、記録媒体 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17870181 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2018550028 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 20197011717 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2017870181 Country of ref document: EP Effective date: 20190611 |