WO2014141676A1 - 情報通信端末、対話提供方法 - Google Patents
情報通信端末、対話提供方法 Download PDFInfo
- Publication number
- WO2014141676A1 WO2014141676A1 PCT/JP2014/001333 JP2014001333W WO2014141676A1 WO 2014141676 A1 WO2014141676 A1 WO 2014141676A1 JP 2014001333 W JP2014001333 W JP 2014001333W WO 2014141676 A1 WO2014141676 A1 WO 2014141676A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- unit
- communication
- dialogue
- presentation
- Prior art date
Links
- 238000004891 communication Methods 0.000 title claims abstract description 485
- 238000000034 method Methods 0.000 title claims description 30
- 238000012545 processing Methods 0.000 claims abstract description 105
- 230000003993 interaction Effects 0.000 claims description 38
- 230000006866 deterioration Effects 0.000 claims description 23
- 230000004044 response Effects 0.000 claims description 21
- 230000008859 change Effects 0.000 claims description 20
- 230000015556 catabolic process Effects 0.000 abstract 1
- 238000006731 degradation reaction Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 18
- 238000004590 computer program Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 230000002452 interceptive effect Effects 0.000 description 7
- 230000015572 biosynthetic process Effects 0.000 description 6
- 238000003786 synthesis reaction Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 5
- 230000001174 ascending effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000004065 semiconductor Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000005401 electroluminescence Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3605—Destination input or retrieval
- G01C21/3608—Destination input or retrieval using speech input, e.g. using speech recognition
-
- 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
Definitions
- the present invention relates to an information communication terminal, and more particularly to an information communication terminal etc. that interacts with a user.
- an information communication terminal capable of interacting with a user.
- Such an information communication terminal communicates with a server managed by a service provider, acquires a response to the user's speech from the server, and presents the user with the response (for example, see Patent Document 1).
- the present invention provides an information communication terminal or the like that can respond to the user's speech while the communication is disconnected even if the communication is disconnected during the interaction.
- An information communication terminal is an information communication terminal that interacts with a user according to an interaction scenario indicating a presentation order of a plurality of presentation information stored in a server, and the user's input in the interaction ,
- a communication unit for acquiring from the server presentation information according to the user's input according to the dialog scenario each time the input receiver receives an input from the user, and the information in the dialog
- a dialog processing unit that presents presentation information acquired by the communication unit to the user as a response to the user of the communication terminal; and a communication state determination unit that determines a communication state between the communication unit and the server; If the communication state determination unit makes a first determination indicating deterioration of the communication state during the interaction, the dialog processing unit performs the first determination Than said presentation information presented to the user to acquire the presentation candidate information which is presented information after the presentation order in the dialog scenario to at least one said communication unit to come.
- FIG. 1 is a block diagram showing the configuration of the voice dialogue system according to the first embodiment.
- FIG. 2 is a diagram for explaining a dialogue scenario.
- FIG. 3 is a diagram showing a data structure of the dialogue scenario.
- FIG. 4 is a flowchart showing voice dialogue processing of the voice dialogue system according to the first embodiment.
- FIG. 5 is a schematic diagram for explaining the voice interaction process when the communication state is good.
- FIG. 6 is a diagram for explaining voice dialogue processing in the case where the communication state deteriorates during the dialogue.
- FIG. 7 is a diagram for explaining the presentation candidate information.
- FIG. 8 is a diagram for explaining presentation candidate information selected according to the frequency of use.
- FIG. 9 is a diagram for explaining the determination method of the communication state of the communication state determination unit.
- FIG. 10 is a block diagram showing an information communication terminal of the minimum configuration.
- FIG. 11 is a diagram showing an application example of the information communication terminal.
- the information communication terminal can not respond to the user's speech until the communication between the information communication terminal and the server is restored. That is, while communication between the information communication terminal and the server is disconnected, there is a problem that the user may feel confused.
- Patent Document 2 discloses a technique for determining whether the information communication terminal performs the translation process or the server using the information indicating the communication state.
- an information communication terminal concerning one mode of the present invention is an information communication terminal which interacts with a user according to a dialogue scenario which shows a presentation order of a plurality of presentation information memorized by a server.
- the presentation information corresponding to the user's input is acquired from the server according to the dialog scenario Determining a communication state between a communication unit, a dialog processing unit that presents to the user presentation information acquired by the communication unit as a response to the user of the information communication terminal in the dialog, a communication unit, and the server And the communication processing unit makes a first judgment indicating the deterioration of the communication state in the middle of the dialogue. If the at least one said to acquire the communication unit presentation candidate information which is presented information after the presentation order in the dialog scenario than presentation information presented to the user when the first judgment is.
- the dialogue can be continued using the presentation candidate information even when the communication becomes impossible thereafter. That is, it is possible to reduce confusion that the user feels while the communication between the server and the information communication terminal is disconnected.
- the communication state determination unit determines the communication state Is determined to be in a state in which communication is not possible
- the interactive processing unit presents the user with the presentation candidate information acquired by the communication unit, corresponding to the first input, to the user
- the communication unit acquires presentation information corresponding to the first input from the server
- the dialogue processing unit determines the communication unit. Presentation information according to the first input acquired by the user may be presented to the user.
- the interaction processing unit sequentially generates a predetermined number of the presentation candidate information in the order of presentation information used in the first determination and the presentation order being closer. May be selected, and the selected presentation candidate information may be acquired by the communication unit.
- the server when the server stores history information indicating the use frequency of each of the plurality of pieces of presentation information stored in the server, and the communication state determination unit makes the first determination in the middle of the dialogue, the server The dialogue processing unit may select a predetermined number of the presentation candidate information in order from the one with the highest frequency of use based on the history information, and acquire the selected presentation candidate information to the communication unit.
- the dialogue processing unit selects a predetermined number of pieces of the presentation candidate information in the ascending order of data size, and selects the presentation candidate selected Information may be acquired by the communication unit.
- the information communication terminal further includes a position acquisition unit that acquires position information indicating the current position of the information communication terminal, and the server uses the frequency of use of the plurality of presentation information stored in the server.
- the dialogue processing unit determines the history information classified by area A predetermined number of pieces of the presentation candidate information may be selected in order from the one with the highest frequency of use in the area to which the position indicated by the position information belongs, and the communication unit may acquire the selected presentation candidate information.
- the information communication terminal includes a speed acquisition unit which is mounted on a moving body and further acquires a moving speed of the moving body as a moving speed of the information communication terminal, and the communication state determination unit
- the dialogue processing unit may acquire a large number of the presentation candidate information to the communication unit as the moving speed is lower.
- the dialogue processing unit further includes a storage unit in which the presentation candidate information acquired by the communication unit is stored, and the communication state determination unit makes the first determination in the middle of the dialogue.
- the free space of the unit is larger, a large number of pieces of the presentation candidate information may be acquired by the communication unit.
- the presentation candidate information can be efficiently acquired according to the free space of the storage unit, and the possibility of interruption of the voice dialogue can be further reduced.
- the communication state determination unit may perform the first determination when a BER (Bit Error Rate) of a signal in the communication between the communication unit and the server becomes larger than a first threshold.
- BER Bit Error Rate
- the communication state determination unit may perform the first determination when the BER changes by a time change amount smaller than a predetermined time change amount and becomes larger than the first threshold.
- communication state information in which a position acquisition unit for acquiring position information indicating the current position of the information communication terminal, a position of the information communication terminal, and the communication state at the position are stored.
- a storage unit may be provided, and the communication state determination unit may perform the first determination based on the position information and the communication state information.
- the communication state information is the communication state in which the position indicated by the position information acquired by the position acquisition unit in the past is associated with the determination result of the communication state of the communication state determination unit at the position. It may be a history.
- the communication processing unit may further include an audio output unit that outputs a sound
- the dialogue processing unit may present the user with the presentation information acquired by the communication unit by causing the audio output unit to output a sound.
- a display unit for displaying a video may be provided, and the dialogue processing unit may present the user with the presentation information acquired by the communication unit by displaying the video on the display unit.
- the input reception unit includes a voice acquisition unit that acquires the voice of the user as an input of the user, and a voice recognition unit that recognizes the voice of the user acquired by the voice acquisition unit, and the communication unit
- the display information may be acquired from the server according to the recognition result of the voice of the user according to the dialogue scenario each time the voice recognition unit recognizes the voice of the user.
- the information acquisition request is received every time the information acquisition request is received from the information communication terminal operated by the user according to the dialogue scenario indicating the presentation order of the plurality of presentation information.
- a method for providing server interaction which transmits corresponding presentation information to the information communication terminal, and receives the information acquisition request including communication deterioration information indicating that the communication state between the server and the information communication terminal has deteriorated.
- at least one piece of presentation candidate information which is presentation information after the presentation order in the dialogue scenario after the presentation information already sent to the information communication terminal, is sent to the information communication terminal.
- Embodiment 1 Hereinafter, the voice dialogue system according to the first embodiment will be described.
- FIG. 1 is a block diagram showing the configuration of the voice dialogue system according to the first embodiment.
- the voice dialogue system 10 includes an information communication terminal 100, a server 200, and a wireless communication line 300 connecting the information communication terminal 100 and the server 200.
- the information communication terminal 100 is a car navigation device mounted on a mobile body (vehicle), and performs voice dialogue to recognize and respond to the voice of the user 20.
- the information communication terminal 100 may be an on-vehicle device fixedly mounted on a vehicle, or may be a communication terminal that can be taken out of the vehicle.
- the speech dialogue is executed according to a prepared dialogue scenario.
- a dialogue scenario about restaurant search will be described.
- the user 20 requests the information communication terminal 100 to search for a restaurant by voice (utterance).
- the information communication terminal 100 acquires and recognizes the voice of the user 20.
- the server 200 acquires presentation information (a question to the user 20) stored in advance in the dialogue scenario database 202 provided in the server 200, and "type of cooking?" Corresponding to the acquired presentation information Output the voice.
- one speech dialogue is executed based on one dialogue scenario, and one speech dialogue is described as being constituted by a plurality of dialogue units.
- a dialogue unit is a unit of dialogue including at least presentation information.
- the information communication terminal 100 similarly acquires the dialogue unit corresponding to the response of the user 20, and outputs the speech corresponding to the acquired dialogue unit.
- the information communication terminal 100 asks the user 20 an area for searching a restaurant, a meal budget, and the like according to the dialogue scenario, and the user 20 sequentially responds to these questions. Finally, the restaurant selected based on the response of the user 20 is presented to the user 20 as a search result, and the voice dialogue ends.
- the information communication terminal 100 constituting the voice dialogue system 10 includes an input reception unit 101a (a voice acquisition unit 101 and a speech recognition unit 102), a communication unit 103, a dialogue processing unit 104, and a communication state determination unit 106. .
- the information communication terminal 100 includes a position acquisition unit 105, a storage unit 108, a speed acquisition unit 109, an audio output unit 110, and an audio synthesis unit 111.
- the voice acquisition unit 101 obtains the voice of the user 20 in the voice dialogue, and generates a digital voice signal.
- the voice acquisition unit 101 is configured of, for example, a microphone and an A / D converter.
- the speech recognition unit 102 recognizes the digital speech signal generated by the speech acquisition unit 101.
- the voice recognition unit 102 recognizes the voice of the user 20 by the existing voice recognition technology, and generates voice data in text format.
- the generated voice data is transmitted to the communication unit 103 via the dialogue processing unit 104.
- the communication unit 103 transmits the voice data generated by the voice recognition unit 102 to the server 200 through the wireless communication line 300, and acquires presentation information corresponding to the voice data from the server 200 according to the dialogue scenario. That is, the communication unit 103 acquires presentation information corresponding to the recognition result from the server 200 each time the speech recognition unit 102 recognizes speech.
- the communication unit 103 is a wireless module capable of wireless communication using a line such as 3G, 4G, Wi-Fi (registered trademark), Zigbee (registered trademark), or the like.
- the dialogue processing unit 104 controls the information communication terminal 100 in voice dialogue.
- the dialogue processing unit 104 outputs the speech data corresponding to the speech unit acquired by the communication unit 103 to the speech synthesis unit, and the speech data output from the dialogue processing unit 104 is converted into a digital speech signal by the speech synthesis unit 111.
- the audio output unit 110 then outputs the That is, the dialog processing unit 104 presents the user 20 with the presentation information (dialogue unit) acquired by the communication unit 103 as a response to the user 20 of the information communication terminal 100 in the dialog.
- the dialogue processing unit 104 caches the presentation candidate information and continues the voice dialogue. Details of the voice dialogue (voice dialogue processing) will be described later.
- the dialogue processing unit 104 may be configured only by hardware, or may be realized by combining hardware and software.
- the dialogue processing unit 104 can also be realized by a processor, a microcomputer or the like.
- Position acquisition unit 105 acquires position information indicating the current position of information communication terminal 100.
- the position acquisition unit 105 is a GPS (Global Positioning System) module, but may be any module capable of acquiring position information of the information communication terminal 100.
- the communication state determination unit 106 determines the communication state between the communication unit 103 and the server 200. Specifically, the communication state determination unit 106 monitors a bit error rate (BER) of a signal received by the communication unit 103. When the BER is larger than the first threshold, the communication state determination unit 106 determines that the communication state is deteriorated. The communication state determination unit 106 further determines that the communication state can not be communicated when the BER is larger than a second threshold which is a threshold larger than the first threshold. The communication state determination unit 106 determines that the communication state is a communicable state when the BER is equal to or less than a predetermined first threshold.
- BER bit error rate
- the communication state determination unit 106 may determine the communication state based on the radio wave intensity of the communication unit 103 (wireless module) or may determine the communication state based on the communication speed of the communication unit 103. Further, the communication state determination unit 106 may determine the communication state based on communication state information described later.
- the storage unit 108 stores presentation candidate information and communication state information.
- the presentation candidate information is presentation information acquired in advance in a state in which the communication state has deteriorated in order to present the user 20 in a state in which the interaction processing unit 104 can not communicate. For example, when the communication state determination unit 106 makes a first determination indicating deterioration of the communication state in the middle of the first voice dialogue performed according to the first dialogue scenario, the presentation candidate information is based on the first dialogue scenario. This is presentation information that may be presented to the user 20 after the first determination, which is determined. In other words, the presentation candidate information is presentation information that follows the presentation order in the dialogue scenario from the presentation information presented to the user when the first determination is made.
- the presentation information which may be presented to the user 20 after the first judgment is In one voice dialogue, meaning the presentation information which may be presented to the user 20 before the first speech dialogue ends after the first determination. That is, the presentation information used for the voice dialogue based on the dialogue scenario different from the first dialogue scenario performed after the first determination is not included.
- middle of the first voice dialogue means both in the middle of presenting the presentation information by the dialogue processing unit 104 and in the middle of the response of the user 20. That is, in the first embodiment, the middle of the first voice dialogue means that the dialogue scenario is being executed.
- the communication state information is information in which the position of the information communication terminal 100 is associated with the communication state at the position.
- the communication state information stores the communication state of the communication unit 103 and the position information acquired by the position acquisition unit 105 in real time, for example, when the mobile unit on which the information communication terminal 100 is mounted is traveling. It can be realized by That is, in this case, the communication state information is a history of communication states in which the position indicated by the position information acquired by the position acquiring unit 105 in the past is associated with the determination result of the communication state of the communication state determining unit 106 at the position. It is.
- the waiting time calculation unit 107 can estimate the timing at which the communication state deteriorates by comparing the current position information acquired by the position acquisition unit 105 with the communication state information. it can.
- the communication state information may be, for example, map information of a communication state provided by a service provider providing a wireless communication service, in which the communication state is associated with the position information.
- the communication state information may be information such as a building in map information provided in the car navigation device. In this case, a position where the radio wave condition is bad, such as in a tunnel or near a high-rise building, is treated as a position where the communication state between the communication unit 103 and the server 200 is deteriorated.
- the storage unit 108 is, for example, a semiconductor memory or an HDD (Hard Disc Drive).
- the information communication terminal 100 includes the storage unit 108.
- the storage unit 108 may be provided separately from the information communication terminal 100. That is, the storage unit 108 may be realized as a USB memory or an external HDD. That is, the storage unit 108 is not an essential component.
- the presentation candidate information and the communication state information are stored in one storage unit 108, but the presentation candidate information and the communication state information may be stored in separate storage units.
- the speed acquisition unit 109 acquires the moving speed (speed and moving direction) of the information communication terminal 100 ( ⁇ user 20, moving object).
- the velocity of the moving object is acquired from the moving object through CAN (Controller Area Network).
- the velocity can also be calculated using the change (displacement) of the position information of the position acquisition unit 105. That is, the speed acquisition unit 109 is not an essential component. That is, the method of acquiring the velocity of the velocity acquiring unit 109 of the information communication terminal 100 is not limited to the method of acquiring the velocity of the moving object, and any method may be used.
- the voice synthesis unit 111 converts voice data into a digital voice signal and outputs the digital voice signal to the voice output unit 110.
- the audio output unit 110 outputs a digital audio signal as a sound.
- information communication terminal 100 is realized as a car navigation device, it is used as reproduction sound (music, radio broadcast, navigation sound, etc.) reproduced by information communication terminal 100 and information to be presented to user 20. It synthesizes the digital audio signal output from the audio synthesis unit 111 and outputs it as a sound.
- the wireless communication line 300 constituting the voice dialogue system 10 is, for example, a line such as 3G, 4G, Wi-Fi (registered trademark), Zigbee (registered trademark) or the like.
- the wireless communication line 300 is typically a line provided by a service provider (a telecommunications carrier) that provides a wireless communication service.
- a service provider a telecommunications carrier
- the information communication terminal 100 and the wireless communication line 300 are directly connected in FIG. 1, the information communication terminal 100 may be connected to the wireless communication line 300 via a relay device such as a smartphone or a wireless router. Good.
- the server 200 constituting the voice dialogue system 10 includes a server communication unit 203, a server dialogue processing unit 204, and a dialogue scenario database 202.
- the server communication unit 203 receives the voice data transmitted by the communication unit 103, and transmits the dialogue unit corresponding to the voice data to the communication unit 103.
- the server communication unit 203 is, for example, a wireless module.
- the server dialogue processing unit 204 selects a dialogue unit corresponding to the voice data received by the server communication unit 203 from the dialogue scenario database 202, and transmits the selected dialogue unit to the communication unit 103 via the server communication unit 203.
- the server interaction processing unit 204 can be realized by a processor, a microcomputer, or the like.
- the dialogue scenario database 202 is a storage unit in which dialogue scenarios consisting of a plurality of dialogue units are stored.
- the dialogue scenario database 202 is a semiconductor memory, a hard disc drive (HDD), or the like.
- FIG. 2 is a diagram for explaining a dialogue scenario.
- FIG. 3 is a diagram showing a data structure of the dialogue scenario.
- the dialogue scenario in the first embodiment is a tree-like list of the procedure (order) of the questioning of the information communication terminal 100, and one unit of dialogue is herein defined as a dialogue unit. Do.
- the dialogue scenario includes the dialogue unit ID, the presentation information (message) that the information communication terminal 100 presents to the user 20, and the user 20's response assumed for the message It is information having a data structure in which branch information (next dialogue unit ID) corresponding thereto is associated.
- the dialogue scenario may have any configuration as long as it indicates the presentation order of presentation information.
- the dialogue scenario may be information that does not include presentation information and indicates only the order of the presentation information, and is information stored in the storage unit 108 of the information communication terminal 100.
- the present embodiment is different in that acquisition of presentation candidate information is performed triggered by the determination indicating the deterioration of the communication state of the communication state determination unit 106. That is, the voice dialogue process of the voice dialogue system 10 is characterized in that the presentation candidate information is acquired (cached) regardless of the situation of the voice dialogue when the communication state is deteriorated during the voice dialogue.
- Caching of the presentation candidate information is performed only when the communication state deteriorates during the voice dialogue. This makes it possible to reduce the area in the storage unit 108 where the presentation candidate information is stored. As in the first embodiment, in the car navigation apparatus and the like, the capacity of the storage unit 108 is limited to a certain extent, so it is useful to cache the presentation candidate information only when the communication state deteriorates during voice interaction. .
- FIG. 4 is a flowchart showing the voice interaction process of the voice interaction system 10.
- the dialogue processing unit 104 determines whether or not a voice dialogue is currently in progress (S101). If voice communication is in progress (Yes in S101), the communication state determination unit 106 determines the deterioration of the communication state between the communication unit 103 and the server 200 (S102). When the communication state between the communication unit 103 and the server 200 is not deteriorated (No in S102) and when the voice dialogue is not in progress (No in S101), it is determined whether the voice dialogue is currently in progress (S101) Return to).
- the dialogue processing unit 104 causes the communication unit 103 to acquire at least one piece of presentation candidate information.
- the dialogue processing unit 104 selects a predetermined number of pieces of presentation candidate information in order from the closest presentation order, and causes the communication unit 103 to acquire the pieces of presentation candidate information.
- the communication unit 103 acquires the presentation candidate information selected by the dialogue processing unit 104 (S103).
- the acquired presentation candidate information is stored in the storage unit 108.
- the communication unit 103 After the communication unit 103 acquires the presentation candidate information, when the speech recognition unit 102 completes the speech recognition of the user 20, which is a response from the user 20 in the dialogue (S104), the communication state judgment unit 106 again performs the process.
- the communication state is determined (S105).
- the communication unit 103 dialogue processing unit 1014 acquires presentation information corresponding to the speech recognition result of the user 20 from the server 200 according to the dialogue scenario.
- the dialogue processing unit 104 presents the acquired presentation information to the user 20 (S107).
- step S105 when communication is not possible (Yes in S105), the dialogue processing unit 104 presents presentation candidate information according to the recognition result of the voice of the user 20 out of the presentation candidate information acquired in step S103. Are selected and presented to the user 20 (S108).
- acquiring presentation information may be described as "acquiring a dialogue unit”.
- FIG. 5 is a schematic diagram for explaining the voice interaction process when the communication state is good.
- the communication state of the communication state determination unit 106 is represented by 1-BER. That is, in the graph of 1-BER in FIG. 5, the upper side of the vertical axis indicates small BER and good communication state, and the lower side of the vertical axis indicates large BER and bad communication state.
- FIG. 5 (a) shows the type of information presented during speech dialogue
- FIG. 5 (b) shows the execution period of each dialogue unit.
- (c) of FIG. 5 shows the period when the communication part 103 is communicating.
- the communication state is good during the period shown by the graph.
- no caching of the interaction unit takes place during the time indicated by the graph.
- the dialogue processing unit 104 causes the communication unit 103 to acquire a dialogue unit (presentation information) from the server 200 each time the user 20 responds, and presents the presentation information included in the dialogue unit.
- the voice interactive process proceeds with the server 200 holding the execution right.
- the communication unit 103 transmits the dialogue unit in periods 301, 302, 303, and 304 at the start of execution of each dialogue unit. It is acquired from the server 200. Further, in the periods 311, 312, 313, and 314 at the end of execution of each dialogue unit, the response (voice data) of the user 20 is transmitted to the server 200.
- FIG. 6 is a figure for demonstrating the audio
- the first threshold 400 a and the second threshold 400 are illustrated in the graph representing the communication state in FIG. 6.
- periods T1 and T5 are periods in which 1-BER is larger than the first threshold 400a, that is, BER is equal to or smaller than the first threshold 400a. Therefore, the periods T1 and T5 are periods in which the communication state determination unit 106 determines that the communication state is good (the communication state is possible).
- the periods T 2 and T 4 are periods in which 1 ⁇ BER is equal to or less than the first threshold 400 a and larger than the second threshold 400. That is, the periods T2 and T4 are periods in which the BER is larger than the first threshold 400a and equal to or smaller than the second threshold 400. Therefore, the periods T2 and T4 are periods in which the communication state determination unit 106 determines that the communication state is deteriorated but the communication itself is possible.
- the period T 3 is a period during which 1-BER is equal to or less than the second threshold 400, that is, BER is larger than the second threshold 400. Therefore, the period T3 is a period during which the communication state determination unit 106 determines that communication can not be performed.
- the dialogue processing unit 104 causes the communication unit 103 to acquire a dialogue unit from the server 200, and presents this. Specifically, as shown in (b) and (c) of FIG. 6, the communication unit 103 acquires the dialog unit from the server 200 in the period 305 at the start of execution of each dialog unit.
- the dialogue processing unit 104 causes the communication unit 103 to acquire the dialogue unit (presentation candidate information) in the period 321 immediately after the timing t1.
- the dialogue processing unit 104 causes the communication unit 103 to acquire the dialogue unit from the server 200 and presents this.
- the dialog processing unit 104 reproduces the message "Please wait for a while".
- the communication processing unit 104 may present the dialogue unit cached as the presentation candidate information in a period in which the communication itself is deteriorated but the communication itself is possible as in the period T2.
- the dialogue unit executed (started) in the period T3 is the dialogue unit cached as the presentation candidate information in the period 321.
- the voice interaction process proceeds with the information communication terminal 100 holding the execution right.
- the dialogue processing unit 104 reproduces a message indicating that the voice dialogue can not be continued, such as “Please wait for a while”.
- the reproduction of such a message is performed, for example, when an incommunicable time is extended for a long time.
- the dialog processing unit 104 (the communication unit 103) performs a period after the end of the execution of the dialog unit which was being executed at timing t4 when the BER becomes equal to or less than the first threshold 400a.
- the ID of the interaction unit to be executed next is sent to the server 200. In other words, in the period 322, the right to execute the voice interaction process is transferred from the information communication terminal 100 to the server 200.
- the communication unit 103 acquires the dialogue unit from the server 200, and the dialogue processing unit 104 presents the presentation information included in the acquired dialogue unit to the user 20. Then, in the period 316 at the end of execution of the dialogue unit, the response of the user 20 is transmitted to the server 200.
- the voice dialogue is performed using the presentation candidate information included in the cached dialogue unit. You can continue.
- FIG. 7 is a diagram for explaining the presentation candidate information.
- the dialogue unit 380 shown in FIG. 7 is a dialogue unit being executed when the communication state determination unit 106 determines that the communication state is deteriorated.
- dialog units that may be executed for the response of the user 20 after the above determination, ie, dialog units including presentation candidate information, are dialog units 391 to 397 in FIG.
- the dialogue processing unit 104 selects a predetermined number of dialogue units (presentation candidate information) from the dialogue units 391 to 397 in descending order of presentation order from the dialogue unit 380 and selects the selected dialogue units. Are acquired by the communication unit 103.
- the dialogue units closest to the presentation order to the dialogue unit 380 are dialogue units 391-393, and the dialogue units next closest to the presentation order are dialogue units 394 and 395.
- the dialogue units whose presentation order is closest to these next dialogue units 380 are dialogue units 396 and 397.
- dialogue processing unit 104 when the number of dialogue units selected by dialogue processing unit 104 is five, dialogue units 391 to 395 surrounded by a broken line in FIG. 7 are selected.
- the selection method of a dialog unit is not limited to said method.
- the dialogue processing unit 104 may select a predetermined number of dialogue units (presentation candidate information) in ascending order of data size, and cause the communication unit 103 to acquire the selected dialogue units.
- the number of interactive units that can be cached is limited because storage resources are limited.
- the dialogue processing unit 104 can store more dialogue units in the storage unit 108 by selecting the dialogue units in ascending order of data size. This can increase the number of interaction units to be cached. Therefore, there is an advantage that interruption of voice dialogue does not easily occur in a period in which communication can not be performed.
- the interruption of the voice dialogue means that the dialogue unit corresponding to the response of the user 20 can not be presented to the user 20 because the dialogue unit is not stored in the storage unit 108.
- the dialogue processing unit 104 may select a predetermined number of dialogue units (presentation candidate information) in order from the one with the highest frequency of use, and cause the communication unit 103 to acquire the selected dialogue units.
- FIG. 8 is a diagram for explaining presentation candidate information selected according to the frequency of use.
- the dialogue unit 380 is a dialogue unit being executed, and the dialogue units including presentation candidate information are dialogue units 391 to 397.
- history information in which the ID of the dialogue unit and the number of times the dialogue unit has been acquired by the communication unit 103 in the past is associated as the information indicating the use frequency. It is stored in the dialogue scenario database 202 of the server 200.
- the dialogue units belonging to the most frequently used class are dialogue units 393, 394 and 396.
- the dialogue units belonging to the next most frequently used class are dialogue units 392 and 397.
- the dialogue units belonging to the least frequently used class are dialogue units 391 and 395.
- dialogue processing unit 104 when the number of dialogue units selected by dialogue processing unit 104 is three, dialogue units 393, 394 and 396 surrounded by a broken line in FIG. 8 are selected.
- the history information may be information representing the individual usage frequency of the user 20, and the history information is information including the number of times acquired by other users or other information communication terminals, etc. It may be information indicating general use frequency of a plurality of users performed in the voice dialogue using 200.
- the dialogue processing unit 104 selects a predetermined number of dialogue units (presentation candidate information) in order from the one with the highest frequency of use in the area to which the position indicated by the position acquisition unit 105 belongs.
- the unit may be acquired by the communication unit 103.
- regional history information indicating the use frequency of the plurality of pieces of presentation information stored in the server 200 for each region where the presentation information is used is stored in the server 200.
- the dialogue processing unit 104 caches the dialogue unit (presentation candidate information) based on the history information classified by area and the position information acquired by the position acquisition unit 105.
- the dialogue processing unit 104 is highly likely to be required to present information for this, and such presentation information is cached as presentation candidate information based on the regional history information.
- the dialogue processing unit 104 can further reduce the possibility of interruption of the voice dialogue.
- the frequency of use in the regional history information is the frequency of use of presentation information including other users different from the user 20, and is generally used by a plurality of users in a voice dialogue performed using the server 200. Means frequency.
- the use frequency in the regional history information may be an individual use frequency of the user 20.
- the above history information and the history information classified by region may be stored in the information communication terminal 100, or a storage device separate from the server 200, and the information communication terminal 100 can be connected by wire or wirelessly. May be stored in the storage device.
- a dialog unit (presentation candidate information) to be selected may be determined by combining the use frequency, data size, and the like. For example, for each of the presentation candidate information, the interactive processing unit 104 sets a first evaluation value that increases as the use frequency of the presentation candidate information increases, and a second evaluation value that increases as the data amount of the presentation candidate information decreases. An evaluation value may be calculated, and a predetermined number of pieces of presentation candidate information may be selected in descending order of the sum of the first evaluation value and the second evaluation value.
- information communication terminal 100 is realized as a car navigation device mounted on a mobile as described above.
- the dialogue processing unit 104 may change the number of pieces of presentation candidate information to be selected according to the speed of the moving object.
- the dialogue processing unit 104 may cause the communication unit 103 to acquire more presentation candidate information as the moving speed of the mobile object is slower.
- the dialogue processing unit 104 should cache a large amount of candidate presentation information and prepare for the user's response.
- the moving speed of the mobile object is high, it is estimated that the time until the communication unit 103 returns from the non-communicable state to the communicable state is short. Therefore, the number of pieces of presentation candidate information cached by the dialogue processing unit 104 may be smaller than in the case where the moving speed of the moving object is slow. Therefore, with the configuration as described above, the dialogue processing unit 104 can efficiently obtain the presentation candidate information, and can further reduce the possibility of interruption of the voice dialogue.
- the dialog processing unit 104 may cause the communication unit 103 to acquire more presentation candidate information as the free space of the storage unit 108 is larger.
- the dialogue processing unit 104 can efficiently obtain the presentation candidate information according to the free space of the storage unit 108, and can further reduce the possibility of interruption of the voice dialogue.
- the voice interaction system 10 (the information communication terminal 100) according to the first embodiment, by caching the presentation candidate information when the communication state is deteriorated, the communication can not be performed thereafter. You can continue the dialogue even if you Therefore, interruption of dialogue can reduce stress and confusion felt by the user.
- the dialogue processing unit 104 causes the communication unit 103 to acquire a predetermined number of pieces of presentation candidate information when the communication state determination unit 106 determines the deterioration of the communication state during the voice dialogue.
- the dialogue processing unit 104 may be acquired by at least one communication unit 103.
- the communication state determination unit 106 changes the BER by a time change amount smaller than a predetermined time change amount and becomes larger than the first threshold 400a, the communication between the communication unit 103 and the server 200 is deteriorated. It may be determined that Similarly, when communication state determination unit 106 changes BER by a time change amount smaller than a predetermined time change amount and becomes larger than second threshold 400, communication between communication unit 103 and server 200 is not performed. It may be determined that it is possible.
- the time change amount is the absolute value of the slope of the time change of BER.
- FIG. 9 is a diagram for explaining the determination method of the communication state of the communication state determination unit 106.
- the vertical axis represents 1-BER.
- the BER When the BER rises rapidly and exceeds the first threshold 400a, the deterioration of the communication state is likely to be temporary. In such a case, the BER is changed by a time change amount smaller than a predetermined time change amount so that the communication state determination unit 106 does not determine that the communication between the communication unit 103 and the server 200 is deteriorated. It may be determined that the communication is in a deteriorated state only when the value becomes larger than the first threshold 400a.
- the 1-BER drops sharply and becomes equal to or less than the first threshold 400a. That is, the BER rapidly increases and exceeds the first threshold 400a, and the BER changes by a time change amount equal to or more than a predetermined time change amount and becomes larger than the first threshold 400a. Therefore, the communication state determination unit 106 determines that the period 402 a is in a state in which communication between the communication unit 103 and the server 200 is possible. That is, the communication state determination unit 106 does not determine that the communication between the communication unit 103 and the server 200 is deteriorated in the period 402 a.
- the 1-BER gradually decreases and becomes equal to or less than the first threshold 400a. That is, the BER rises gradually and exceeds the first threshold 400a, and the BER changes with a time change amount smaller than a predetermined time change amount and becomes larger than the first threshold 400a. Therefore, the communication state determination unit 106 determines that the period 403 a is in a state in which communication between the communication unit 103 and the server 200 is deteriorated (a period 403 is a state in which communication is not possible).
- the communication state determination unit 106 can not communicate with the communication state determination unit 106 depending on whether the BER changes by a time change amount equal to or larger than a predetermined time change amount and becomes larger than the second threshold 400. It may be determined whether it is or not. Specifically, in FIG. 9, communication state determination unit 106 determines that period 402 is in a state in which communication between communication unit 103 and server 200 is possible, and period 403 corresponds to communication unit 103 and server 200. It determines that communication is impossible.
- the communication state determination unit 106 can also determine the communication state in advance using the communication state information. That is, “when the first determination indicating the deterioration of the communication state is made” of the communication state determination unit 106 includes determining the current or future communication state. Further, “when the first determination indicating the deterioration of the communication state is made” includes the case where the communication state determination unit 106 specifies the first timing in advance.
- the communication state determination unit 106 determines the deterioration of the communication state using the communication state information
- the information communication terminal 100 is controlled from the current position and the moving speed of the information communication terminal 100 until the communication state is deteriorated.
- the time may be estimated, and the presentation candidate information may be acquired by the communication unit 103 when the time until the communication state deteriorates becomes equal to or less than a predetermined threshold.
- the information communication terminal 100 is not the minimum configuration.
- FIG. 10 is a block diagram showing an information communication terminal of the minimum configuration.
- the information communication terminal 100a having the minimum configuration includes an input receiving unit 101a, a communication unit 103, a dialog processing unit 104, and a communication state determination unit 106.
- the dialogue processing unit and the simplified dialogue processing unit present information by voice, but the method of presenting information to the user is not limited to such a method.
- the information communication terminal further includes a display unit for displaying an image
- the dialogue processing unit presents information to the user by displaying the image on the display unit
- the simple dialogue processing unit displays the image on the display unit.
- the display may present the user with predetermined first information.
- the display unit in this case is, for example, a liquid crystal display, a plasma display, or an organic EL (Electro Luminescence) display.
- a head up display (HUD: Head Up Display) using a windshield of a vehicle may be used as a display unit.
- the information presented by the interaction processing unit and the simplified interaction processing unit may be only still images. That is, the dialogue between the user and the information communication terminal may not be a voice dialogue. Further, the information presented by the dialogue processing unit and the simple dialogue processing unit may be a moving image obtained by combining sound and video.
- the input to a user's information communication terminal may not be a voice. That is, the information communication terminal may be provided with an input receiving unit, and may perform interactive processing based on the user's input.
- the input receiving unit in this case may be the voice acquisition unit and the voice recognition unit described in the first embodiment, or a device such as a touch panel that receives a user's touch operation, a hardware switch, or the like that receives a user's input. I hope there is.
- the information communication terminal is realized as a car navigation device as shown in FIG. 11, but the information communication terminal may be realized as a smartphone or a tablet terminal.
- the present invention may be realized as a server 200 that provides presentation information (dialogue unit). That is, part or all of the functions of the interaction processing unit 104 may be realized as the functions of the server 200 (server interaction processing unit 204).
- the server 200 sends presentation information corresponding to the information acquisition request to the information communication terminal 100 each time the information acquisition request is received from the information communication terminal 100 operated by the user 20 according to the interaction scenario. Send.
- the presentation information is transmitted according to the received information acquisition request and interaction scenario.
- the dialog processing unit 104 of the information communication terminal 100 transmits an information acquisition request including communication deterioration information to the server 200 (the communication unit 103). It transmits to the server communication unit 203).
- the communication deterioration information is information indicating that the communication state between the server 200 and the information communication terminal 100 is deteriorated.
- the server 200 When the server 200 receives the information acquisition request including the communication deterioration information, the server 200 at least one information candidate communication that is the presentation information whose presentation order in the dialogue scenario is later than the presentation information transmitted to the information communication terminal 100. It transmits to the terminal 100.
- the server 200 can select presentation candidate information triggered by communication deterioration information. That is, the selection method of the presentation candidate information of the above-mentioned information communication terminal 100 is applicable also to server 200.
- the server 200 determines in order from the presentation information that is close to the presentation information transmitted to the communication unit 103 immediately before receiving the information acquisition request including communication deterioration information. A number of pieces of presentation candidate information may be selected, and the selected presentation candidate information may be transmitted to the communication unit 103.
- history information indicating the use frequency of each of the plurality of pieces of presentation information stored in the server 200 is stored in the server 200, and when the server 200 receives an information acquisition request including communication deterioration information, the history Based on the information, a predetermined number of presentation candidate information may be selected in descending order of usage frequency, and the selected presentation candidate information may be transmitted to the communication unit 103.
- the information communication terminal 100 since the information communication terminal 100 only needs to transmit the information acquisition request and the communication deterioration information when the server 200 selects the presentation candidate information, the processing on the information communication terminal 100 side can be simplified. There is.
- the server 200 may determine the communication state. That is, when the server 200 determines that the communication state is deteriorated, the presentation candidate information may be selected and transmitted to the communication unit 103. This has the advantage that the processing on the side of the information communication terminal 100 can be further simplified.
- Each of the above-described devices can be specifically realized by a computer system including a microprocessor, a ROM, a RAM, a hard disk unit, a display unit, a keyboard, a mouse and the like.
- a computer program is stored in the RAM or the hard disk unit.
- Each device achieves its function by the microprocessor operating according to the computer program.
- the computer program is configured by combining a plurality of instruction codes indicating instructions to the computer in order to achieve a predetermined function.
- the system LSI is a super-multifunctional LSI manufactured by integrating a plurality of components on one chip, and more specifically, a computer system including a microprocessor, a ROM, a RAM, and the like. .
- a computer program is stored in the ROM.
- the system LSI achieves its functions as the microprocessor loads a computer program from the ROM to the RAM and operates according to the loaded computer program.
- a part or all of the components constituting each of the above-described devices may be configured from an IC card or a single module which can be detached from each device.
- the IC card or module is a computer system including a microprocessor, a ROM, a RAM, and the like.
- the IC card or module may include the above-described ultra-multifunctional LSI.
- the IC card or module achieves its function by the microprocessor operating according to the computer program. This IC card or this module may have tamper resistance.
- the present invention may be realized by the method shown above. Also, these methods may be realized by a computer program realized by a computer, or may be realized by a digital signal consisting of a computer program.
- the present invention is a computer program or a recording medium capable of reading digital signals from a computer, such as a flexible disk, a hard disk, a CD-ROM, an MO, a DVD, a DVD-ROM, a DVD-RAM, a BD (Blu-ray (registered trademark) Disc), semiconductor memory, etc. may be realized. Also, it may be realized by digital signals recorded in these recording media.
- a computer such as a flexible disk, a hard disk, a CD-ROM, an MO, a DVD, a DVD-ROM, a DVD-RAM, a BD (Blu-ray (registered trademark) Disc), semiconductor memory, etc.
- the present invention may transmit a computer program or a digital signal via a telecommunication line, a wireless or wired communication line, a network typified by the Internet, data broadcasting, and the like.
- the present invention is a computer system comprising a microprocessor and a memory, the memory storing a computer program, and the microprocessor may operate according to the computer program.
- the present invention is useful as an information communication terminal used in a car navigation device.
- DESCRIPTION OF SYMBOLS 10 voice dialogue system 20 user 100, 100a information communication terminal 101 voice acquisition part 101a input reception part 102 voice recognition part 103 communication part 104 dialogue processing part 105 position acquisition part 106 communication state determination part 108 storage part 109 speed acquisition part 110 voice output Unit 111 Speech synthesis unit 200 Server 202 Dialogue scenario database 203 Server communication unit 204 Server dialogue processing unit 300 Wireless communication line 301 to 305, 311 to 316, 321, 322, 401, 402, 402a, 403a, 403, 404a Period 380, 391 to 397 dialogue unit 400 second threshold 400 a first threshold
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Acoustics & Sound (AREA)
- Artificial Intelligence (AREA)
- Automation & Control Theory (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
- Navigation (AREA)
Abstract
Description
背景技術で説明したように、ユーザと対話を行うことができる情報通信端末が知られている。
以下、実施の形態1に係る音声対話システムについて説明する。
本発明は、上記の実施の形態1に限定されない。以下のような場合も本発明に含まれる。
20 ユーザ
100、100a 情報通信端末
101 音声取得部
101a 入力受付部
102 音声認識部
103 通信部
104 対話処理部
105 位置取得部
106 通信状態判定部
108 記憶部
109 速度取得部
110 音声出力部
111 音声合成部
200 サーバ
202 対話シナリオデータベース
203 サーバ通信部
204 サーバ対話処理部
300 無線通信回線
301~305、311~316、321、322、401a、402、402a、403a、403、404a 期間
380、391~397 対話ユニット
400 第2閾値
400a 第1閾値
Claims (16)
- サーバに記憶された複数の提示情報の提示順序を示す対話シナリオにしたがって、ユーザと対話を行う情報通信端末であって、
前記対話における前記ユーザの入力を受け付ける入力受付部と、
前記入力受付部が前記ユーザの入力を受け付けるごとに、前記対話シナリオにしたがって当該ユーザの入力に応じた提示情報を前記サーバから取得する通信部と、
前記対話における前記情報通信端末の前記ユーザへの応答として、前記通信部が取得した提示情報を前記ユーザに提示する対話処理部と、
前記通信部と前記サーバとの通信状態を判定する通信状態判定部とを備え、
前記対話処理部は、前記対話の途中に前記通信状態判定部が前記通信状態の悪化を示す第1判定をした場合、前記第1判定がされたときに前記ユーザに提示されている提示情報よりも前記対話シナリオにおける提示順序が後の提示情報である提示候補情報を少なくとも1つ前記通信部に取得させる
情報通信端末。 - 前記対話の途中において、前記通信部が前記提示候補情報を取得した後に前記入力受付部が前記ユーザの第1の入力を受け付けたときに、
(1)前記通信状態判定部が前記通信状態が通信不可能な状態であると判定した場合、前記対話処理部は、前記第1の入力に対応する、前記通信部が取得した前記提示候補情報を前記ユーザに提示し、
(2)前記通信状態判定部が前記通信状態が通信可能な状態であると判定した場合、前記通信部は、前記サーバから前記第1の入力に応じた提示情報を取得し、前記対話処理部は、前記通信部が取得した、前記第1の入力に応じた提示情報を前記ユーザに提示する
請求項1に記載の情報通信端末。 - 前記対話の途中に前記通信状態判定部が前記第1判定をした場合、前記対話処理部は、前記第1判定時に用いる提示情報と提示順序が近いものから順に所定数の前記提示候補情報を選択し、選択した前記提示候補情報を前記通信部に取得させる
請求項1または2に記載の情報通信端末。 - 前記サーバには、当該サーバに記憶された前記複数の提示情報それぞれの使用頻度を示す履歴情報が記憶され、
前記対話の途中に前記通信状態判定部が前記第1判定をした場合、前記対話処理部は、前記履歴情報に基づいて使用頻度の高いものから順に所定数の前記提示候補情報を選択し、選択した前記提示候補情報を前記通信部に取得させる
請求項1または2に記載の情報通信端末。 - 前記対話の途中に前記通信状態判定部が前記第1判定をした場合、前記対話処理部は、データサイズの小さいものから順に所定数の前記提示候補情報を選択し、選択した前記提示候補情報を前記通信部に取得させる
請求項1または2に記載の情報通信端末。 - 前記情報通信端末は、さらに、前記情報通信端末の現在の位置を示す位置情報を取得する位置取得部を備え、
前記サーバには、当該サーバに記憶された前記複数の提示情報の使用頻度を当該提示情報が使用された地域ごとに示す地域別履歴情報が記憶され、
前記対話の途中に前記通信状態判定部が前記第1判定をした場合、前記対話処理部は、前記地域別履歴情報に基づいて、前記位置情報が示す位置が属する地域における使用頻度の高いものから順に所定数の前記提示候補情報を選択し、選択した前記提示候補情報を前記通信部に取得させる
請求項1または2に記載の情報通信端末。 - 前記情報通信端末は、移動体に搭載され、さらに、当該移動体の移動速度を前記情報通信端末の移動速度として取得する速度取得部を備え、
前記対話の途中に前記通信状態判定部が前記第1判定をした場合、前記対話処理部は、前記移動速度が遅いほど、数多くの前記提示候補情報を前記通信部に取得させる
請求項1~6のいずれか1項に記載の情報通信端末。 - さらに、前記通信部が取得した前記提示候補情報が記憶される記憶部を備え、
前記対話の途中に前記通信状態判定部が前記第1判定をした場合、前記対話処理部は、前記記憶部の空き容量が大きいほど、数多くの前記提示候補情報を前記通信部に取得させる
請求項1~7のいずれか1項に記載の情報通信端末。 - 前記通信状態判定部は、前記通信部と前記サーバとの通信における信号のBER(Bit Error Rate)が第1閾値よりも大きくなった場合に、前記第1判定を行う
請求項1~8のいずれか1項に記載の情報通信端末。 - 前記通信状態判定部は、前記BERが所定の時間変化量よりも小さい時間変化量で変化して前記第1閾値よりも大きくなった場合に、前記第1判定を行う
請求項9に記載の情報通信端末。 - さらに、
前記情報通信端末の現在の位置を示す位置情報を取得する位置取得部と、
前記情報通信端末の位置と、当該位置における前記通信状態とを対応付けた通信状態情報が記憶される記憶部を備え、
前記通信状態判定部は、前記位置情報と、前記通信状態情報とに基づいて前記第1判定を行う
請求項1~8のいずれか1項に記載の情報通信端末。 - 前記通信状態情報は、過去における、前記位置取得部が取得した前記位置情報が示す位置と、当該位置における前記通信状態判定部の前記通信状態の判定結果とを対応付けた前記通信状態の履歴である
請求項11に記載の情報通信端末。 - さらに、音を出力する音声出力部を備え、
前記対話処理部は、前記音声出力部に音を出力させることによって前記通信部が取得した提示情報を前記ユーザに提示する
請求項1~12のいずれか1項に記載の情報通信端末。 - さらに、映像を表示する表示部を備え、
前記対話処理部は、前記表示部に映像を表示させることによって前記通信部が取得した提示情報を前記ユーザに提示する
請求項1~12のいずれか1項に記載の情報通信端末。 - 前記入力受付部は、
前記ユーザの音声を前記ユーザの入力として取得する音声取得部と、
前記音声取得部が取得した前記ユーザの音声を認識する音声認識部とを有し、
前記通信部は、前記音声認識部が前記ユーザの音声を認識するごとに、前記対話シナリオにしたがって前記ユーザの音声の認識結果に応じた提示情報を前記サーバから取得する
請求項1~14のいずれか1項に記載の情報通信端末。 - 複数の提示情報の提示順序を示す対話シナリオにしたがって、ユーザが操作する情報通信端末から情報取得要求を受信するごとに、前記情報取得要求に応じた提示情報を前記情報通信端末に送信する、サーバの対話提供方法であって、
前記サーバと前記情報通信端末との通信状態が悪化したことを示す通信悪化情報を含む前記情報取得要求を受信したときに、前記情報通信端末に送信済みの提示情報よりも前記対話シナリオにおける提示順序が後の提示情報である提示候補情報を少なくとも1つ前記情報通信端末に送信する
対話提供方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/767,739 US9405504B2 (en) | 2013-03-12 | 2014-03-10 | Information communication terminal and dialogue presentation method |
JP2015505283A JP6284104B2 (ja) | 2013-03-12 | 2014-03-10 | 情報通信端末、対話提供方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013049735 | 2013-03-12 | ||
JP2013-049735 | 2013-03-12 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014141676A1 true WO2014141676A1 (ja) | 2014-09-18 |
Family
ID=51536355
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/001333 WO2014141676A1 (ja) | 2013-03-12 | 2014-03-10 | 情報通信端末、対話提供方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US9405504B2 (ja) |
JP (1) | JP6284104B2 (ja) |
WO (1) | WO2014141676A1 (ja) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106055547A (zh) * | 2015-04-02 | 2016-10-26 | 松下知识产权经营株式会社 | 对话方法、记录介质以及对话系统 |
JP2016206249A (ja) * | 2015-04-15 | 2016-12-08 | シャープ株式会社 | 対話装置、対話システム、及び対話装置の制御方法 |
JP2017083713A (ja) * | 2015-10-29 | 2017-05-18 | シャープ株式会社 | 対話装置、対話機器、対話装置の制御方法、制御プログラム、および記録媒体 |
JP2019120903A (ja) * | 2018-01-11 | 2019-07-22 | トヨタ自動車株式会社 | 音声出力システム、音声出力方法、及びプログラム |
JP2020160135A (ja) * | 2019-03-25 | 2020-10-01 | 本田技研工業株式会社 | エージェント装置、エージェント装置の制御方法、およびプログラム |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102014002543A1 (de) * | 2014-02-22 | 2015-08-27 | Audi Ag | Verfahren zur Erfassung wenigstens zweier zu erfassender Informationen mit zu verknüpfendem Informationsgehalt durch eine Sprachdialogeinrichtung, Sprachdialogeinrichtung und Kraftfahrzeug |
EP3828883A4 (en) * | 2018-07-24 | 2022-05-04 | Faurecia Clarion Electronics Co., Ltd. | INFORMATION COLLECTION DEVICE AND CONTROL METHOD |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001209571A (ja) * | 2000-01-26 | 2001-08-03 | Sharp Corp | 情報取得装置および情報取得方法、ならびに情報取得プログラムを記録したコンピュータ読み取り可能な記録媒体 |
JP2003167895A (ja) * | 2001-11-30 | 2003-06-13 | Denso Corp | 情報検索システム、サーバおよび車載端末 |
JP2009124219A (ja) * | 2007-11-12 | 2009-06-04 | Casio Hitachi Mobile Communications Co Ltd | 通信装置、および、プログラム |
JP2009153078A (ja) * | 2007-12-21 | 2009-07-09 | Sony Ericsson Mobilecommunications Japan Inc | 情報通信端末、情報通信システム、情報通信端末の制御方法及び制御プログラム |
WO2012011490A1 (ja) * | 2010-07-20 | 2012-01-26 | シャープ株式会社 | コンテンツ取得装置、コンテンツ送信装置、コンテンツ送受信システム、データ構造、制御方法、制御プログラム、及び記録媒体 |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2002079896A2 (en) * | 2001-03-30 | 2002-10-10 | British Telecommunications Public Limited Company | Multi-modal interface |
US7287227B2 (en) * | 2001-06-29 | 2007-10-23 | Ve Enterprises Llc | System and method for editing web pages in a client/server architecture |
AU2002951244A0 (en) * | 2002-09-06 | 2002-09-19 | Telstra New Wave Pty Ltd | A development system for a dialog system |
JP4451166B2 (ja) | 2004-03-08 | 2010-04-14 | 三菱電機株式会社 | 音声対話システム |
JP2006099296A (ja) | 2004-09-29 | 2006-04-13 | Nec Corp | 翻訳システム、翻訳通信システム、機械翻訳方法、および、プログラム |
US7853453B2 (en) * | 2005-06-30 | 2010-12-14 | Microsoft Corporation | Analyzing dialog between a user and an interactive application |
US8117303B2 (en) * | 2007-06-29 | 2012-02-14 | Nokia Corporation | Systems, methods, devices, and computer program products for downloading content for offline browsing |
JP2009053866A (ja) * | 2007-08-24 | 2009-03-12 | Ntt Docomo Inc | データ転送装置およびデータ転送システム |
JP2009237786A (ja) * | 2008-03-26 | 2009-10-15 | Brother Ind Ltd | 情報提示装置及びコンピュータプログラム、並びに情報提示方法 |
JP5768346B2 (ja) * | 2010-08-26 | 2015-08-26 | 沖電気工業株式会社 | 通信システム、並びに、通信端末及び通信プログラム |
US9578495B2 (en) * | 2011-12-19 | 2017-02-21 | Qualcomm Incorporated | Handling impaired wireless connection in a communication system |
US20140164476A1 (en) * | 2012-12-06 | 2014-06-12 | At&T Intellectual Property I, Lp | Apparatus and method for providing a virtual assistant |
-
2014
- 2014-03-10 JP JP2015505283A patent/JP6284104B2/ja active Active
- 2014-03-10 WO PCT/JP2014/001333 patent/WO2014141676A1/ja active Application Filing
- 2014-03-10 US US14/767,739 patent/US9405504B2/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001209571A (ja) * | 2000-01-26 | 2001-08-03 | Sharp Corp | 情報取得装置および情報取得方法、ならびに情報取得プログラムを記録したコンピュータ読み取り可能な記録媒体 |
JP2003167895A (ja) * | 2001-11-30 | 2003-06-13 | Denso Corp | 情報検索システム、サーバおよび車載端末 |
JP2009124219A (ja) * | 2007-11-12 | 2009-06-04 | Casio Hitachi Mobile Communications Co Ltd | 通信装置、および、プログラム |
JP2009153078A (ja) * | 2007-12-21 | 2009-07-09 | Sony Ericsson Mobilecommunications Japan Inc | 情報通信端末、情報通信システム、情報通信端末の制御方法及び制御プログラム |
WO2012011490A1 (ja) * | 2010-07-20 | 2012-01-26 | シャープ株式会社 | コンテンツ取得装置、コンテンツ送信装置、コンテンツ送受信システム、データ構造、制御方法、制御プログラム、及び記録媒体 |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106055547A (zh) * | 2015-04-02 | 2016-10-26 | 松下知识产权经营株式会社 | 对话方法、记录介质以及对话系统 |
JP2016197227A (ja) * | 2015-04-02 | 2016-11-24 | パナソニックIpマネジメント株式会社 | 対話方法、対話プログラム及び対話システム |
CN106055547B (zh) * | 2015-04-02 | 2021-06-18 | 松下知识产权经营株式会社 | 对话方法、记录介质以及对话系统 |
JP2016206249A (ja) * | 2015-04-15 | 2016-12-08 | シャープ株式会社 | 対話装置、対話システム、及び対話装置の制御方法 |
JP2017083713A (ja) * | 2015-10-29 | 2017-05-18 | シャープ株式会社 | 対話装置、対話機器、対話装置の制御方法、制御プログラム、および記録媒体 |
JP2019120903A (ja) * | 2018-01-11 | 2019-07-22 | トヨタ自動車株式会社 | 音声出力システム、音声出力方法、及びプログラム |
JP7197272B2 (ja) | 2018-01-11 | 2022-12-27 | トヨタ自動車株式会社 | 音声出力システム、音声出力方法、及びプログラム |
JP2020160135A (ja) * | 2019-03-25 | 2020-10-01 | 本田技研工業株式会社 | エージェント装置、エージェント装置の制御方法、およびプログラム |
JP7274903B2 (ja) | 2019-03-25 | 2023-05-17 | 本田技研工業株式会社 | エージェント装置、エージェント装置の制御方法、およびプログラム |
Also Published As
Publication number | Publication date |
---|---|
JPWO2014141676A1 (ja) | 2017-02-16 |
US9405504B2 (en) | 2016-08-02 |
JP6284104B2 (ja) | 2018-02-28 |
US20150378672A1 (en) | 2015-12-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2014141676A1 (ja) | 情報通信端末、対話提供方法 | |
JP6052610B2 (ja) | 情報通信端末、およびその対話方法 | |
JP6834054B2 (ja) | デバイス間ハンドオフ | |
US11676601B2 (en) | Voice assistant tracking and activation | |
CN107111492B (zh) | 跨诸设备缩放数字个人助理代理 | |
KR102091003B1 (ko) | 음성인식 기술을 이용한 상황 인식 서비스 제공 방법 및 장치 | |
JP2018508843A (ja) | 車両ベースのマルチモーダルインターフェース | |
KR20150067521A (ko) | 화면 공유 서비스를 위한 장치 및 방법, 이를 위한 화면 공유 시스템 | |
US9585184B1 (en) | Using multiple wireless connections | |
WO2013180280A1 (ja) | 車載情報システム、情報端末、アプリケーション実行方法 | |
CN105828145A (zh) | 互动方法及装置 | |
CN106976434B (zh) | 用于车辆中的语音识别设备的装置及方法 | |
US8751426B2 (en) | Apparatus and method for generating context-aware information using local service information | |
JP5920104B2 (ja) | 車両用音声制御装置 | |
JP2016101785A (ja) | 情報処理装置および実行管理プログラム | |
JP5494318B2 (ja) | 携帯端末および通信システム | |
US9565304B2 (en) | Method and apparatus for providing audio content, user terminal and computer readable recording medium | |
WO2018034265A1 (ja) | ナビゲーションシステム及びコンピュータプログラム | |
US20140155099A1 (en) | Method and apparatus for displaying location information of call service area in mobile terminal | |
JP2015220533A (ja) | 車載情報システム、車載装置、情報端末、アプリケーション実行方法 | |
US20190346937A1 (en) | Mobile terminal device, information processing device, cooperative system, and method for controlling display | |
JP2010108331A (ja) | 情報処理装置、アプリケーション起動方法およびプログラム | |
WO2013180279A1 (ja) | 車載情報システム、情報端末、アプリケーション実行方法、プログラム | |
EP4366244A1 (en) | Multi-device synchronous playback method and apparatus | |
CN111277976B (zh) | 信息处理设备、信息处理方法和程序 |
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: 14763027 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015505283 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14767739 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14763027 Country of ref document: EP Kind code of ref document: A1 |