CN106782539A - A kind of intelligent sound exchange method, apparatus and system - Google Patents
A kind of intelligent sound exchange method, apparatus and system Download PDFInfo
- Publication number
- CN106782539A CN106782539A CN201710032588.2A CN201710032588A CN106782539A CN 106782539 A CN106782539 A CN 106782539A CN 201710032588 A CN201710032588 A CN 201710032588A CN 106782539 A CN106782539 A CN 106782539A
- Authority
- CN
- China
- Prior art keywords
- intelligent sound
- voice
- acceleration
- information
- interactive device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000004891 communication Methods 0.000 claims abstract description 31
- 230000002452 interceptive effect Effects 0.000 claims description 159
- 230000001133 acceleration Effects 0.000 claims description 155
- 230000003993 interaction Effects 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 17
- 230000005484 gravity Effects 0.000 claims description 8
- 230000005611 electricity Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 15
- 239000000203 mixture Substances 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 4
- 229910052744 lithium Inorganic materials 0.000 description 4
- 238000003780 insertion Methods 0.000 description 3
- 230000037431 insertion Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/38—Transceivers, i.e. devices in which transmitter and receiver form a structural unit and in which at least one part is used for functions of transmitting and receiving
- H04B1/40—Circuits
- H04B1/401—Circuits for selecting or indicating operating mode
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Emergency Management (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Environmental & Geological Engineering (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention proposes a kind of intelligent sound exchange method, apparatus and system, and the device includes：Information receiving module, control module, question and answer search module, dio Output Modules and communication module, wherein, information receiving module, operating mode instruction, other side's speech play control information, request voice messaging and our intercommunication information for receiving user；The control module, for when the operating mode instruction is instructed for question-answering mode, controlling the question and answer search module to be furnished an answer for the request voice messaging；When the operating mode instruction is instructed for talkback mode, the our intercommunication information of control described information receiver module input, and control the communication module that the our intercommunication information is sent into the intercommunication server, when the communication module receives other side's voice that the intercommunication server sends, the dio Output Modules are controlled to play other side's voice.The present invention realizes the intercom function between Intellectual phonetic system and other-end.
Description
Technical field
The present invention relates to technical field of voice interaction, more particularly to a kind of intelligent sound exchange method, apparatus and system.
Background technology
Intelligent sound interactive device can be loaded into robot, household electrical appliance, the middle control of entity as human-computer interaction module
In the equipment such as system, gate control system, ATM, it is also possible to be positioned in toy, as toy for children.Intelligent sound interactive device
Instrument can also be introduced as the article in special venue (such as museum), for visitor provides more direct understanding instrument.When
When introducing instrument as the article of special venue, can be interacted using local preset sound bank, without with high in the clouds
Server communication.
But, existing intelligent sound interactive device can not carry out intercom, interactive voice with the mobile terminal such as mobile phone
Range of application it is narrower.
In addition, in current prior art, fall reminding technology in most fields especially toy for children field not yet
Occur, toy for children is a kind of very short product of service life, it is necessary to realize power down protection before the fall, therefore, current skill
Art cannot meet the demand in toy for children field.Power down protection technology generally occurs in the storage devices such as solid state hard disc, such
Using the method for real-time monitoring magnitude of voltage more than technology, for preventing loss of data or disorder, implementation method during storage device power down
Complexity, need to put into great effort in circuit design.And power down protection technology is not applied to toy for children field yet.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of intelligent sound exchange method, apparatus and system, realizes intelligence
The question and answer function of voice device and the intercom function between other-end.
The technical solution adopted by the present invention is, the intelligent sound interactive device, including：Information receiving module, control mould
Block, question and answer search module, dio Output Modules and communication module, wherein,
Information receiving module, operating mode instruction, other side's speech play control information, request voice for receiving user
Information and our intercommunication information, the operating mode instruction include that talkback mode is instructed or question-answering mode instruction；
The communication module, for carrying out information exchange with outside intercommunication server；
The dio Output Modules, for playing voice；
The question and answer search module, for being furnished an answer for the request voice messaging；
The control module, for when the operating mode instruction is instructed for question-answering mode, controlling the question and answer search
Module furnishes an answer for the request voice messaging；When the operating mode instruction is instructed for talkback mode, the letter is controlled
The our intercommunication information of breath receiver module input, and control the communication module that the our intercommunication information is sent into the intercommunication
Server, when the communication module receives other side's voice that the intercommunication server sends, the control module passes through institute
State dio Output Modules to ask the user whether to play other side's voice, and other side's language is received in described information receiver module
After sound broadcasting control information, the dio Output Modules are controlled to play other side's voice.
Further, described information receiver module, one or more of following form information are received for support：Voice is believed
Breath, text information, key information, gesture information and touch information.
Further, described device also includes：Memory module, for storing the talkback mode instruction and the question and answer mould
Formula is instructed.
Further, the question and answer search module includes：
Voice recognition unit, for the request voice messaging to be converted into request speech text by speech recognition；
Question and answer search unit, for storage problem template and the corresponding answer voice of described problem template；Known by semanteme
The described problem template matched with the request speech text is not obtained, and the corresponding answer is obtained according to described problem template
Voice.
Further, the voice recognition unit, including：Local voice recognition unit and/or high in the clouds voice recognition unit；
The question and answer search unit, including：Local question and answer search unit and/or high in the clouds question and answer search unit.
Further, described device also includes：Memory module, for store remind voice, the prompting voice be used for into
Row calling is reminded；And/or,
Described device also includes：Indicator lamp, for working to carry out calling prompting according to the first flashing mode.
Further, described device also includes：Acceleration transducer, enters for the acceleration to intelligent sound interactive device
Row monitoring；
Power supply, for being the control module, the Audio Input Modules, the dio Output Modules and the communication mould
Block is powered；
The control module, be additionally operable to determine preset duration in the intelligent sound interactive device acceleration with fall plus
When velocity interval is persistently matched, the power supply is closed.
Further, described device also includes：Memory module, audio is reminded for storing emergency；
The control module, is additionally operable to determine the acceleration and the pendant of the intelligent sound interactive device in preset duration
When the acceleration range that falls persistently is matched, control the dio Output Modules to play the emergency and remind audio.
Further, described device, also includes：Indicator lamp, for working fall carrying according to the second flashing mode
Wake up；
The control module, is additionally operable to determine the acceleration and the pendant of the intelligent sound interactive device in preset duration
When the acceleration range that falls persistently is matched, the indicator lamp is controlled to carry out prompting of falling.
Further, described device also includes：Timer, hands over for comparing the intelligent sound in the control module
The acceleration of mutual device starts timing when being matched with the acceleration range of falling, the timing when timing duration reaches preset duration
Terminate；The acceleration range of falling includes：Acceleration of gravity scope during object freely falling body, or, object is thrown downwards
Acceleration range when throwing；
The control module, if for comparing intelligent sound interactive device in the preset duration in the timer
Acceleration still matched with the acceleration range of falling, then close the power supply.
Further, described device also includes：Memory module, thanks to audio for storing；
The control module, is additionally operable to when the notice of the timer is received, if comparing current time intelligence language
The acceleration of sound interactive device falls into acceleration range when object is caught, then control the dio Output Modules to play described
Thank to audio.
Further, the control module, is additionally operable to the acceleration change parameter of intelligent sound interactive device and setting
Acceleration change parameter be compared；If being consistent, the power supply is closed；
The acceleration change parameter of the setting, including：In setting duration, acceleration value occurs positive and negative alternate time
Positive peak threshold value and negative peak threshold value that number and acceleration value reach.
The present invention provides a kind of intelligent speech interactive system, including：Intercommunication server and above-mentioned intelligent sound interaction dress
Put, wherein,
The intercommunication server, for receiving voice that mobile terminal sends and being transmitted to intelligent sound interactive device；Connect
Receive the voice sent of intelligent sound interactive device and be transmitted to mobile terminal.
Further, the intercommunication server, is additionally operable to receive the mobile terminal and the intelligence that mobile terminal is uploaded
The binding information of energy voice interaction device, the forwarding of voice is carried out based on the binding information.
The present invention also provides a kind of intelligent speech interactive system, including：Intercommunication server, mobile terminal and above-mentioned intelligence
Voice interaction device, wherein,
The mobile terminal, for sending voice to the intercommunication server；Receive the institute that the intercommunication server is sent
State the voice of intelligent sound interactive device；
The intercommunication server, for receiving voice that the mobile terminal sends and being transmitted to the intelligent sound interaction
Device；Receive voice that the intelligent sound interactive device sends and be transmitted to the mobile terminal.
The present invention also provides a kind of intelligent sound exchange method, including：
The operating mode instruction of user is received, to determine being to enter question-answering mode or to enter talkback mode；
Under question-answering mode, for the request voice messaging for receiving furnishes an answer；
Under talkback mode, the our intercommunication information being input into is sent to the intercommunication server, it is described right when receiving
When saying other side's voice that server sends, ask the user whether to play other side's voice, and after user agrees to play, broadcast
Put other side's voice.
Further, the determination is to enter question-answering mode or enter talkback mode, specially：
Input information according to user determines it is to enter question-answering mode or enter talkback mode；
The form of the input information of the user includes one or more of following form information：Voice messaging, word letter
Breath, key information, gesture information and touch information.
Further, it is described for the request voice messaging for receiving furnishes an answer, including：
The request voice messaging of user is converted to by request speech text by speech recognition；
Based on the corresponding answer voice of question template and described problem template for prestoring, by semantics recognition obtain with
The described problem template of the request speech text matching, the corresponding answer voice is obtained according to described problem template.
Further, methods described also includes：Voice is reminded in storage, and the prompting voice is for carrying out calling prompting；With/
Or,
Work to carry out calling prompting according to the first flashing mode by indicator lamp.
Further, methods described also includes：Acceleration to intelligent sound interactive device is monitored；
When determining that the acceleration of the intelligent sound interactive device in preset duration is persistently matched with acceleration range of falling,
Close power supply.
Further, methods described also includes：Audio is reminded in storage emergency；
The acceleration of the intelligent sound interactive device and acceleration range of falling is compared in preset duration to continue
Timing, plays the emergency and reminds audio.
Further, methods described also includes：Compare the acceleration of the intelligent sound interactive device in preset duration
Spend when persistently being matched with acceleration range of falling, work to carry out prompting of falling according to the second flashing mode by indicator lamp.
Further, it is described to compare the acceleration of the intelligent sound interactive device and acceleration of falling in preset duration
Degree scope is persistently matched, and closes power supply, including：
Start meter when the acceleration for comparing the intelligent sound interactive device is matched with the acceleration range of falling
When；The acceleration range of falling includes：Acceleration of gravity scope during object freely falling body, or, object is thrown downwards
When acceleration range；
When timing duration reaches preset duration, if compare the acceleration of current time intelligent sound interactive device with
The acceleration range of falling still is matched, then close power supply.
Further, methods described also includes：Storage thanks to audio；
When timing duration reaches preset duration, if the acceleration for comparing current time intelligent sound interactive device falls
Enter acceleration range when object is caught, then play the thanks audio.
Further, methods described also includes：By the acceleration change parameter of intelligent sound interactive device and adding for setting
Speed change parameter is compared；If being consistent, power supply is closed；
The acceleration change parameter of the setting, including：In setting duration, acceleration value occurs positive and negative alternate time
Positive peak threshold value and negative peak threshold value that number and acceleration value reach.
Using above-mentioned technical proposal, the present invention at least has following advantages：
Intelligent sound exchange method of the present invention, apparatus and system, realize between intelligent sound interactive device and user
Question and answer function and the mobile terminal such as intelligent sound interactive device and mobile phone between intercom function, extend intelligence
The interactive voice range of application of voice interaction device.Intelligent sound interactive device of the invention is embedded in the products such as toy,
Toy can be realized with stronger interactive function.Such as, child user can be by insertion toy of the invention and the mobile phone for binding toy
Account carries out intercommunication.Meanwhile, intelligent sound the interactive device of the invention also function with traditional intelligence voice interaction device, youngster
Virgin user can engage in the dialogue with toy.
The present invention is by acceleration transducer, real-time monitoring acceleration magnitude, so that it may judges whether toy has and falls danger simultaneously
Timely play cuing voice.Before falling, controller disconnects each several part power supply successively, it is to avoid because collision causes hardware circuit volume
Outer damage, such as：Immediate current is excessive to burn out main control chip.
Implementation method of the present invention is simple, with low cost, has wide range of applications, and overcomes the deficiencies in the prior art, realizes pendant
Fall to reminding and power down protection, make intelligent sound interactive device interactive performance more preferably, quality is more preferably.
Brief description of the drawings
Fig. 1 is the intelligent sound interactive device composition structural representation of first embodiment of the invention；
Fig. 2 is the intelligent sound interactive device composition structural representation of second embodiment of the invention；
Fig. 3 is the intelligent sound interactive device composition structural representation of third embodiment of the invention；
Fig. 4 is the intelligent sound interactive device composition structural representation of fourth embodiment of the invention；
Fig. 5 is the intelligent sound interactive device composition structural representation of fifth embodiment of the invention；
Fig. 6 is the intelligent sound interactive device composition structural representation of sixth embodiment of the invention；
Fig. 7 is the intelligent sound interactive device composition structural representation of seventh embodiment of the invention；
Fig. 8 is the intelligent sound exchange method flow chart of eleventh embodiment of the invention；
Fig. 9 is the intelligent sound exchange method flow chart of twelveth embodiment of the invention；
Figure 10 is the intelligent sound exchange method flow chart of thriteenth embodiment of the invention；
Figure 11 is the intelligent sound exchange method flow chart of fourteenth embodiment of the invention；
Figure 12 is the intelligent sound exchange method flow chart of fifteenth embodiment of the invention；
Figure 13 is the intelligent sound exchange method flow chart of sixteenth embodiment of the invention；
Figure 14 is the intelligent sound interactive device composition structural representation of seventeenth embodiment of the invention；
Figure 15 is interaction diagrams of the intelligent sound interactive device of seventeenth embodiment of the invention under question-answering mode；
Figure 16 is fall prompting and the power down protection stream of the intelligent sound interactive device of seventeenth embodiment of the invention
Cheng Tu；
Figure 17 initiates the flow chart of intercommunication for the user of seventeenth embodiment of the invention on mobile terminals；
Figure 18 initiates the flow of intercommunication for the user of seventeenth embodiment of the invention at the intelligent sound interactive device end.
Specific embodiment
Further to illustrate the present invention to reach technological means and effect that predetermined purpose is taken, below in conjunction with accompanying drawing
And preferred embodiment, the present invention is described in detail as after.
First embodiment of the invention, a kind of intelligent sound interactive device, as shown in figure 1, including consisting of part：Information
Receiver module 101, control module 102, question and answer search module 103, dio Output Modules 104 and communication module 105, wherein,
Information receiving module 101, operating mode instruction, other side's speech play control information, request for receiving user
Voice messaging and our intercommunication information, the operating mode instruction include that talkback mode is instructed or question-answering mode instruction.Specifically
, information receiving module 101 receives one or more of following form information for support：Voice messaging, text information, press
Key information, gesture information and touch information.
Communication module 105, for carrying out information exchange with outside intercommunication server；
Dio Output Modules 104, for playing voice；
Question and answer search module 103, for being furnished an answer for the request voice messaging；
Control module 102, for when the operating mode instruction is instructed for question-answering mode, controlling question and answer search module
103 furnish an answer for the request voice messaging；When the operating mode instruction is instructed for talkback mode, control information is received
Module 101 is input into our intercommunication information, and controls communication module 105 that the our intercommunication information is sent into the intercommunication service
Device, when communication module 105 receives other side's voice that the intercommunication server sends, control module 102 passes through audio output
Module 104 asks the user whether to play other side's voice, and receives other side's speech play control in information receiving module 101
After information processed, control dio Output Modules 104 play other side's voice.
The intelligent sound interactive device of the embodiment of the present invention can realize and the intercom between the mobile terminal such as mobile phone,
Extend the interactive voice range of application of intelligent sound interactive device.The intelligent sound interactive device of the embodiment of the present invention is embedded in
Into the products such as toy, toy can be realized with stronger interactive function.Such as, child user can by insertion toy of the invention with
The mobile phone account for binding toy carries out intercommunication.Meanwhile, the intelligent sound interactive device of the embodiment of the present invention also has traditional intelligence
The function of voice interaction device, child user can engage in the dialogue question and answer with toy.
A kind of second embodiment of the invention, intelligent sound interactive device, such as Fig. 2 shows, including consisting of part：Information connects
Receive module 101, control module 102, question and answer search module 103, dio Output Modules 104, communication module 105 and memory module
106, wherein,
Information receiving module 101, operating mode instruction, other side's speech play control information, request for receiving user
Voice messaging and our intercommunication information, the operating mode instruction include that talkback mode is instructed or question-answering mode instruction.Specifically
, information receiving module 101 receives one or more of following form information for support：Voice messaging, text information, press
Key information, gesture information and touch information.
Communication module 105, for carrying out information exchange with outside intercommunication server；
Dio Output Modules 104, for playing voice；
Question and answer search module 103, for being furnished an answer for the request voice messaging；
Control module 102, for when the operating mode instruction is instructed for question-answering mode, controlling question and answer search module
103 furnish an answer for the request voice messaging；When the operating mode instruction is instructed for talkback mode, control information is received
Module 101 is input into our intercommunication information, and controls communication module 105 that the our intercommunication information is sent into the intercommunication service
Device, when communication module 105 receives other side's voice that the intercommunication server sends, control module 102 passes through audio output
Module 104 asks the user whether to play other side's voice, and receives other side's speech play control in information receiving module 101
After information processed, control dio Output Modules 104 play other side's voice.
Memory module 106, for storing the talkback mode instruction and question-answering mode instruction.
The intelligent sound interactive device of the embodiment of the present invention is roughly the same with first embodiment, differs only in, the present invention
The described device of embodiment also includes memory module 106, the talkback mode instruction and question-answering mode instruction of the storage of memory module 106
Concrete form can be diversified, can be distinguished by key-press input mode difference, such as：Different key-press inputs
Mode includes：Length button more than or equal to the first preset duration is represented, or, interval is default less than the second preset duration
Button of number of times etc..
A kind of third embodiment of the invention, intelligent sound interactive device, such as Fig. 3 shows, including consisting of part：Information connects
Receive module 101, control module 102, question and answer search module 103, dio Output Modules 104, communication module 105, memory module 106
With indicator lamp 107, wherein,
Information receiving module 101, operating mode instruction, other side's speech play control information, request for receiving user
Voice messaging and our intercommunication information, the operating mode instruction include that talkback mode is instructed or question-answering mode instruction.Specifically
, information receiving module 101 receives one or more of following form information for support：Voice messaging, text information, press
Key information, gesture information and touch information.
Communication module 105, for carrying out information exchange with outside intercommunication server；
Dio Output Modules 104, for playing voice；
Question and answer search module 103, for being furnished an answer for the request voice messaging；
Control module 102, for when the operating mode instruction is instructed for question-answering mode, controlling question and answer search module
103 furnish an answer for the request voice messaging；When the operating mode instruction is instructed for talkback mode, control information is received
Module 101 is input into our intercommunication information, and controls communication module 105 that the our intercommunication information is sent into the intercommunication service
Device, when communication module 105 receives other side's voice that the intercommunication server sends, control module 102 passes through audio output
Module 104 asks the user whether to play other side's voice, and receives other side's speech play control in information receiving module 101
After information processed, control dio Output Modules 104 play other side's voice.
Memory module 106, voice is reminded for storing, and the prompting voice is used to carry out calling prompting；
Indicator lamp 107, for working to carry out calling prompting according to the first flashing mode.
The intelligent sound interactive device of the embodiment of the present invention is roughly the same with first embodiment, differs only in, the present invention
The described device of embodiment also includes memory module 106 and indicator lamp 107, is used to the calling during intercommunication and reminds.
A kind of fourth embodiment of the invention, intelligent sound interactive device, such as Fig. 4 shows, including consisting of part：Information connects
Module 101, control module 102, question and answer search module 103, dio Output Modules 104 and communication module 105 are received, wherein,
Information receiving module 101, operating mode instruction, other side's speech play control information, request for receiving user
Voice messaging and our intercommunication information, the operating mode instruction include that talkback mode is instructed or question-answering mode instruction.Specifically
, information receiving module 101 receives one or more of following form information for support：Voice messaging, text information, press
Key information, gesture information and touch information.
Communication module 105, for carrying out information exchange with outside intercommunication server；
Dio Output Modules 104, for playing voice；
Question and answer search module 103, for being furnished an answer for the request voice messaging；
Specifically, question and answer search module 103 includes：
Voice recognition unit 11, for the request voice messaging to be converted into request speech text by speech recognition；
Question and answer search unit 12, for storage problem template and the corresponding answer voice of described problem template；By semanteme
Identification obtain with the request described problem template that matches of speech text, according to described problem template obtain it is corresponding described in answer
Case voice.
Control module 102, for when the operating mode instruction is instructed for question-answering mode, controlling question and answer search module
103 furnish an answer for the request voice messaging；When the operating mode instruction is instructed for talkback mode, control information is received
Module 101 is input into our intercommunication information, and controls communication module 105 that the our intercommunication information is sent into the intercommunication service
Device, when communication module 105 receives other side's voice that the intercommunication server sends, control module 102 passes through audio output
Module 104 asks the user whether to play other side's voice, and receives other side's speech play control in information receiving module 101
After information processed, control dio Output Modules 104 play other side's voice.
Further, the voice recognition unit 11 of the embodiment of the present invention, including：Local voice recognition unit and/or high in the clouds
Voice recognition unit；
Question and answer search unit 12, including：Local question and answer search unit and/or high in the clouds question and answer search unit.
The intelligent sound interactive device of the embodiment of the present invention is roughly the same with first embodiment, differs only in, the present invention
Pin question and answer search module 103 describes its composition and several concrete implementation modes in the described device of embodiment, such as：Question and answer
Voice recognition unit 11 in search module 103 both can be local voice recognition unit, or high in the clouds speech recognition list
Unit, can also be that local and high in the clouds is respectively provided with voice recognition unit；Similarly, question and answer search unit 12 in question and answer search module 103
Also it is set as accordingly.
Local and in the case that high in the clouds is respectively provided with voice recognition unit and question and answer search unit, local voice is recognized first
Whether the feature of unit judges phonetic entry matches with the phonetic feature in local data base, if being matched with local data, knows
Not Cheng Gong, give local question and answer search unit and search for corresponding answer in the local database；If being mismatched with local data,
Voice messaging is uploaded to speech recognition server i.e. high in the clouds speech recognition list by recognition failures, described device by communication module
Unit, speech recognition server returns to the recognized corresponding text of voice content to described device, gives local question and answer search single
Corresponding answer is searched in the local database by unit.If local question and answer search unit is not searched in the local database answering
Case, the then corresponding text of voice content that will be recognized is uploaded to distal end question and answer search unit and carries out the lookup of answer, and will answer
The voice content of case is done to play to user.
Fifth embodiment of the invention, a kind of intelligent sound interactive device, device of the present invention is with first embodiment substantially
Identical, difference is that such as Fig. 5 shows that embodiment of the present invention described device also includes：
Acceleration transducer 108, is monitored for the acceleration to intelligent sound interactive device；
Power supply 109, for being the control module, the Audio Input Modules, dio Output Modules and described logical
Letter module for power supply；
Control module 102, be additionally operable to determine preset duration in the intelligent sound interactive device acceleration with fall plus
When velocity interval is persistently matched, power supply 109 is closed.
Intelligent sound interactive device of the present invention, by acceleration transducer real-time monitoring acceleration magnitude, so that it may judge
Whether described device has danger of falling.Before falling, controller deenergization, it is to avoid because collision causes hardware circuit additionally to damage
It is bad, such as：Immediate current is excessive to burn out main control chip, greatly extends the service life of the intelligent sound interactive device.
Sixth embodiment of the invention, a kind of intelligent sound interactive device, device of the present invention and the 5th embodiment are substantially
Identical, difference is that such as Fig. 6 shows that embodiment of the present invention described device also includes：
Memory module 106, audio is reminded for storing emergency；
Control module 102, is additionally operable to determine the acceleration and the pendant of the intelligent sound interactive device in preset duration
When the acceleration range that falls persistently is matched, control dio Output Modules 104 play the emergency and remind audio.
Preferably, described device, also includes：
Indicator lamp 107, for working to carry out prompting of falling according to the second flashing mode；
Control module 102, is additionally operable to determine the acceleration and the pendant of the intelligent sound interactive device in preset duration
When the acceleration range that falls persistently is matched, the indicator lamp is controlled to carry out prompting of falling.
Compared with the 5th embodiment, the present embodiment described device also includes indicator lamp 107 to the embodiment of the present invention, such as：LED
Deng rapidly flashing to carry out user prompting of falling, it is adaptable to there is the user of dysaudia.Indicator lamp of the invention 107 dodges
It is bright with emergency is played audio to be reminded to be combined, it is more efficient that prompting of falling is carried out to user.
Seventh embodiment of the invention, a kind of intelligent sound interactive device, device of the present invention and the 5th embodiment are substantially
Identical, difference is that such as Fig. 7 shows that embodiment of the present invention described device also includes：
Timer 110, for comparing the acceleration of the intelligent sound interactive device in the control module and falling
Acceleration range starts timing when matching, and when timing duration reaches preset duration, timing terminates；The acceleration range of falling
Including：Acceleration of gravity scope during object freely falling body, or, acceleration range when object is thrown downwards；
Control module 102, if for comparing the intelligent sound interactive device in the preset duration of the timing of timer 110
Acceleration is still matched with the acceleration range of falling, then close power supply 109.
The described device of the present embodiment has added a timer with the 5th embodiment, and the present embodiment can also be directed to two kinds
The state fallen close the operation of power supply, and both states fallen are：Object freely falling body, or, object is downward
Throw.More comprehensively protect intelligent sound interactive device.
Eighth embodiment of the invention, a kind of intelligent sound interactive device, device of the present invention and the 5th embodiment are substantially
Identical, difference is that embodiment of the present invention described device also includes：
Memory module 106, thanks to audio for storing；
Control module 102, is additionally operable to when the notice of the timer is received, if comparing current time intelligent sound
The acceleration of interactive device falls into acceleration range when object is caught, then control the dio Output Modules to play the sense
Thank to audio.
Preferably, the intelligent sound interactive device of the embodiment of the present invention can be supported to rock the function of shutdown, specifically, control
Module 102, is additionally operable to be compared the acceleration change parameter of intelligent sound interactive device with the acceleration change parameter of setting
Compared with；If being consistent, the power supply is closed；
The acceleration change parameter of the setting, including：In setting duration, acceleration value occurs positive and negative alternate time
Positive peak threshold value and negative peak threshold value that number and acceleration value reach.
Ninth embodiment of the invention, a kind of intelligent speech interactive system, including：Intercommunication server and the present invention first and second,
3rd, the intelligent sound interactive device of four, five, six, seven or eight embodiments, wherein,
The intercommunication server, for receiving voice that mobile terminal sends and being transmitted to intelligent sound interactive device；Connect
Receive the voice sent of intelligent sound interactive device and be transmitted to mobile terminal.
Preferably, the intercommunication server, is additionally operable to receive the mobile terminal and the intelligence that mobile terminal is uploaded
The binding information of voice interaction device, the forwarding of voice is carried out based on the binding information.
Tenth embodiment of the invention, a kind of intelligent speech interactive system, including：Intercommunication server, mobile terminal and Ben Fa
The intelligent sound interactive device of the embodiment of bright first, second, third and fourth, five, six, seven or eight, wherein, the mobile terminal, for
The intercommunication server sends voice；Receive the voice of the intelligent sound interactive device that the intercommunication server is sent；
The intercommunication server, for receiving voice that the mobile terminal sends and being transmitted to the intelligent sound interaction
Device；Receive voice that the intelligent sound interactive device sends and be transmitted to the mobile terminal.
Eleventh embodiment of the invention, as shown in figure 8, a kind of intelligent sound exchange method, including step in detail below：
Step S101, receives the operating mode instruction of user, to determine being to enter question-answering mode or to enter talkback mode；
Specifically, in step S101, it is determined that be to enter question-answering mode or enter talkback mode, specially：
Input information according to user determines it is to enter question-answering mode or enter talkback mode；
The form of the input information of the user includes one or more of following form information：Voice messaging, word letter
Breath, key information, gesture information and touch information.
Step S102, under question-answering mode, for the request voice messaging for receiving furnishes an answer；
Specifically, step S102 includes：
The request voice messaging of user is converted to by request speech text by speech recognition；
Based on the corresponding answer voice of question template and described problem template for prestoring, by semantics recognition obtain with
The described problem template of the request speech text matching, the corresponding answer voice is obtained according to described problem template.
Step S103, under talkback mode, the intercommunication server is sent to by the our intercommunication information being input into, and works as reception
During the other side's voice sent to the intercommunication server, ask the user whether to play other side's voice, and agree to broadcast in user
After putting, other side's voice is played.
Preferably, the methods described of the embodiment of the present invention also includes：
Under talkback mode, when other side's voice that the intercommunication server sends is received, calling also is carried out to user
Remind to ask the user whether to play other side's voice, such as：Calling prompting is carried out by the prompting voice for playing storage；
And/or, work to carry out calling prompting according to the first flashing mode by indicator lamp.
The intelligent sound exchange method of the embodiment of the present invention can realize and the intercom between the mobile terminal such as mobile phone,
Extend the interactive voice range of application of intelligent sound interactive device.The intelligent sound interactive device of the embodiment of the present invention is embedded in
Into the products such as toy, toy can be realized with stronger interactive function.Such as, child user can by insertion toy of the invention with
The mobile phone account for binding toy carries out intercommunication.Meanwhile, the intelligent sound interactive device of the embodiment of the present invention also has traditional intelligence
The function of voice interaction device, child user can engage in the dialogue question and answer with toy.
Twelveth embodiment of the invention, as shown in figure 9, a kind of intelligent sound exchange method, including step in detail below：
Step S101, receives the operating mode instruction of user, to determine being to enter question-answering mode or to enter talkback mode；
Specifically, in step S101, it is determined that be to enter question-answering mode or enter talkback mode, specially：
Input information according to user determines it is to enter question-answering mode or enter talkback mode；
The form of the input information of the user includes one or more of following form information：Voice messaging, word letter
Breath, key information, gesture information and touch information.
Step S102, under question-answering mode, for the request voice messaging for receiving furnishes an answer；Jump procedure S105；
Specifically, step S102 includes：
The request voice messaging of user is converted to by request speech text by speech recognition；
Based on the corresponding answer voice of question template and described problem template for prestoring, by semantics recognition obtain with
The described problem template of the request speech text matching, the corresponding answer voice is obtained according to described problem template.
Step S103, under talkback mode, the intercommunication server is sent to by the our intercommunication information being input into, and works as reception
During the other side's voice sent to the intercommunication server, ask the user whether to play other side's voice, and agree to broadcast in user
After putting, other side's voice is played.
Step S104, the acceleration to intelligent sound interactive device is monitored；
Step S105, determines that the acceleration of the intelligent sound interactive device is held with acceleration range of falling in preset duration
During continuous matching, power supply is closed.
Intelligent sound exchange method of the present invention, by acceleration transducer real-time monitoring acceleration magnitude, so that it may judge
Whether intelligent sound interactive device has the dangerous and timely play cuing voice that falls.Before falling, controller deenergization is kept away
Exempt to cause hardware circuit excessive wear because of collision, such as：Immediate current is excessive to burn out main control chip, greatly extends the intelligence
The service life of voice interaction device.
Thriteenth embodiment of the invention, as shown in Figure 10, a kind of intelligent sound exchange method, including step in detail below：
Step S201, receives the operating mode instruction of user, to determine being to enter question-answering mode or to enter talkback mode；
Specifically, in step s 201, it is determined that be to enter question-answering mode or enter talkback mode, specially：
Input information according to user determines it is to enter question-answering mode or enter talkback mode；
The form of the input information of the user includes one or more of following form information：Voice messaging, word letter
Breath, key information, gesture information and touch information.
Step S202, under question-answering mode, for the request voice messaging for receiving furnishes an answer；Jump procedure S204；
Specifically, step S202 includes：
The request voice messaging of user is converted to by request speech text by speech recognition；
Based on the corresponding answer voice of question template and described problem template for prestoring, by semantics recognition obtain with
The described problem template of the request speech text matching, the corresponding answer voice is obtained according to described problem template.
Step S203, under talkback mode, the intercommunication server is sent to by the our intercommunication information being input into, and works as reception
During the other side's voice sent to the intercommunication server, ask the user whether to play other side's voice, and agree to broadcast in user
After putting, other side's voice is played.
Audio is reminded in step S204, storage emergency；
Step S205, the acceleration to intelligent sound interactive device is monitored；
Step S206, determines that the acceleration of the intelligent sound interactive device is held with acceleration range of falling in preset duration
During continuous matching, play the emergency and remind audio, close power supply.
Preferably, in step S206, while the emergency prompting audio is played, dodged according to second by indicator lamp
Bright mode works to carry out prompting of falling.
The embodiment of the present invention by indicator lamp flash can also with play emergency remind audio be combined, it is more efficient to
Family carries out prompting of falling.
Fourteenth embodiment of the invention, as shown in figure 11, a kind of intelligent sound exchange method, including step in detail below：
Step S301, receives the operating mode instruction of user, to determine being to enter question-answering mode or to enter talkback mode；
Specifically, in step S301, it is determined that be to enter question-answering mode or enter talkback mode, specially：
Input information according to user determines it is to enter question-answering mode or enter talkback mode；
The form of the input information of the user includes one or more of following form information：Voice messaging, word letter
Breath, key information, gesture information and touch information.
Step S302, under question-answering mode, for the request voice messaging for receiving furnishes an answer；Jump procedure S304；
Specifically, step S302 includes：
The request voice messaging of user is converted to by request speech text by speech recognition；
Based on the corresponding answer voice of question template and described problem template for prestoring, by semantics recognition obtain with
The described problem template of the request speech text matching, the corresponding answer voice is obtained according to described problem template.
Step S303, under talkback mode, the intercommunication server is sent to by the our intercommunication information being input into, and works as reception
During the other side's voice sent to the intercommunication server, ask the user whether to play other side's voice, and agree to broadcast in user
After putting, other side's voice is played.
Step S304, the acceleration to intelligent sound interactive device is monitored；
Step S305, matches in the acceleration for comparing the intelligent sound interactive device with the acceleration range of falling
When start timing；The acceleration range of falling includes：Acceleration of gravity scope during object freely falling body, or, object quilt
Acceleration range when throwing downwards；
Step S306, when timing duration reaches preset duration, if comparing current time intelligent sound interactive device
Acceleration still matched with the acceleration range of falling, then close power supply.
The embodiment of the present invention can be directed to two kinds of states fallen and close the operation of power supply, both states fallen
It is：Object freely falling body, or, object is thrown downwards.More comprehensively protect intelligent sound interactive device.
Fifteenth embodiment of the invention, as shown in figure 12, a kind of intelligent sound exchange method, including step in detail below：
Step S401, receives the operating mode instruction of user, to determine being to enter question-answering mode or to enter talkback mode；
Specifically, in step S401, it is determined that be to enter question-answering mode or enter talkback mode, specially：
Input information according to user determines it is to enter question-answering mode or enter talkback mode；
The form of the input information of the user includes one or more of following form information：Voice messaging, word letter
Breath, key information, gesture information and touch information.
Step S402, under question-answering mode, for the request voice messaging for receiving furnishes an answer；Jump procedure S404；
Specifically, step S402 includes：
The request voice messaging of user is converted to by request speech text by speech recognition；
Based on the corresponding answer voice of question template and described problem template for prestoring, by semantics recognition obtain with
The described problem template of the request speech text matching, the corresponding answer voice is obtained according to described problem template.
Step S403, under talkback mode, the intercommunication server is sent to by the our intercommunication information being input into, and works as reception
During the other side's voice sent to the intercommunication server, ask the user whether to play other side's voice, and agree to broadcast in user
After putting, other side's voice is played.
Step S404, storage thanks to audio；
Step S405, the acceleration to intelligent sound interactive device is monitored；
Step S406, matches in the acceleration for comparing the intelligent sound interactive device with the acceleration range of falling
When start timing；The acceleration range of falling includes：Acceleration of gravity scope during object freely falling body, or, object quilt
Acceleration range when throwing downwards；
Step 407, when timing duration reaches preset duration, if comparing current time intelligent sound interactive device
Acceleration falls into acceleration range when object is caught, then play the thanks audio；If comparing current time intelligence language
The acceleration of sound interactive device is still matched with the acceleration range of falling, then close power supply.
The embodiment of the present invention perceives intelligent sound interactive device and is currently falling and stretches out one's hand the feelings caught in view of user
Under condition, played to user and thank to audio.
Sixteenth embodiment of the invention, as shown in figure 13, a kind of intelligent sound exchange method, including step in detail below：
Step S501, receives the operating mode instruction of user, to determine being to enter question-answering mode or to enter talkback mode；
Specifically, in step S501, it is determined that be to enter question-answering mode or enter talkback mode, specially：
Input information according to user determines it is to enter question-answering mode or enter talkback mode；
The form of the input information of the user includes one or more of following form information：Voice messaging, word letter
Breath, key information, gesture information and touch information.
Step S502, under question-answering mode, for the request voice messaging for receiving furnishes an answer；Jump procedure S504；
Specifically, step S502 includes：
The request voice messaging of user is converted to by request speech text by speech recognition；
Based on the corresponding answer voice of question template and described problem template for prestoring, by semantics recognition obtain with
The described problem template of the request speech text matching, the corresponding answer voice is obtained according to described problem template.
Step S503, under talkback mode, the intercommunication server is sent to by the our intercommunication information being input into, and works as reception
During the other side's voice sent to the intercommunication server, ask the user whether to play other side's voice, and agree to broadcast in user
After putting, other side's voice is played.
Step S504, the acceleration to intelligent sound interactive device is monitored；
Step S505, the acceleration change parameter of intelligent sound interactive device is carried out with the acceleration change parameter of setting
Compare；If being consistent, power supply is closed；
The acceleration change parameter of the setting, including：In setting duration, acceleration value occurs positive and negative alternate time
Positive peak threshold value and negative peak threshold value that number and acceleration value reach.
The intelligent sound exchange method of the embodiment of the present invention is also supported to rock the function of shutdown, when the hand-held intelligence of user
Voice interaction device and when rocking, to intelligent sound interactive device can close the operation of power supply.
Seventeenth embodiment of the invention, the present embodiment is on the basis of above-described embodiment, to be introduced with reference to accompanying drawing 14~18
One application example of the invention.
As shown in figure 14, intelligent sound interactive device of the present invention includes 11 parts, is respectively：Charge Management
Device, lithium battery, power supply changeover device, controller, wifi module, flash chip, information receiving module, dio Output Modules, question and answer
Search module, acceleration transducer and LED light.
The 5V that power line is input into is converted to charging manager the charging voltage of lithium battery, and controls the whole charging of battery
Process.
Lithium battery is the power supply of whole intelligent sound interactive device.
The 3.7V voltage conversions of lithium battery are to be adapted to the 3.3V that other parts are powered by power supply changeover device.
Information receiving module picks up the sound of user input, and is transferred to controller；The operating mode instruction of reception user,
Request voice messaging and our intercommunication information, the operating mode instruction include that talkback mode is instructed or question-answering mode instruction.
Controller respectively with wifi module, flash chip, Audio Input Modules, dio Output Modules, acceleration transducer
Communicated with LED light.
Controller is used to receive the instruction of user input, and correspondence mode of operation is entered according to the instruction, when entering question and answer
During pattern, question and answer search module is controlled to be furnished an answer for the request voice messaging；When talkback mode is entered, control information connects
The our intercommunication information of module input is received, and controls wifi module that the our intercommunication information is sent into intercommunication server, when
When wifi module receives other side's voice of intercommunication server transmission, controller asks the user whether to broadcast by dio Output Modules
Other side's voice is put, and after information receiving module receives other side's speech play control information, controls audio output
Module plays other side's voice.
Question and answer search module, for being furnished an answer for the request voice messaging.Comprising long-range in question and answer search module
Server for answering question and speech recognition server.
The local information that flash chip storage needs.
Wifi module provides network-connectivity, with intercommunication server interaction.
Play the other side's voice or broadcasting answer voice that wifi module is received in dio Output Modules part.
Acceleration transducer can perceive acceleration change information during user's operation intelligent sound interactive device.
The intelligent sound interactive device also add prompting of falling on the basis of the basic functions such as interactive voice are realized
And power-down protection, while can realize rocking shut-off function.Make intelligent sound interactive device Man machine interaction more preferably, and prolong
Long life.
As shown in figure 15, interaction flow of the intelligent sound interactive device under question-answering mode, mainly includes six steps, point
It is not：
Step 1, user key-press is spoken, and is input into voice.
Step 2, picks up the voice of user input, and voice messaging is uploaded into speech-recognition services by wifi module
Device.
Step 3, speech recognition server returns to the recognized corresponding text of voice content.
Step 4, the content of text that will be recognized by wifi module is uploaded to server for answering question, and asks to answer.
Step 5, server for answering question carries out semantics recognition to question text, and corresponding answering then is found in server for answering question
Case and by wifi module return answer voice.Response in server for answering question can be：To poem, game, local song, net
Network song etc..
Step 6, user is played to by the voice messaging that server for answering question is returned.
As shown in figure 16, fall prompting and the power down protection flow of the described device of the embodiment of the present invention are as follows：
Step 1, intelligent sound interactive device trigger acceleration transducer, real-time monitoring acceleration magnitude after switching on power.
Step 2, judge acceleration magnitude size, if acceleration magnitude is close to gravity acceleration g, show the device free falling；
If acceleration magnitude shows that user's (especially child user) is throwing voice module more than g.
Step 3, call the emergency voice document in flash chip and play, while controlling LED flickers, point out line module
Will fall.
Step 4, whether acceleration transducer is judged again close to 0, if so, then performing step 5, otherwise perform step 6.Cause
Caught by user during to fall or stop throwing, acceleration magnitude is close to 0.
Step 5, acceleration magnitude point out user without danger of falling close to 0 thanks voice document played in flash memories.
If step 6, acceleration magnitude protect hardware circuit without significant change, power cutoff.
The intercommunication function of the invention intelligent sound interactive device is divided into two kinds of situations：
The first situation, user initiates intercommunication on mobile terminals, and voice messaging is pushed into intelligent sound interactive device.
As shown in figure 17, user initiates the flow of intercommunication mainly comprising six steps on mobile terminals, is respectively：
Step 1, user logs in client on mobile terminal (such as mobile phone) and is bound with intelligent sound interactive device, initiates
Intercommunication is simultaneously input into voice.
The voice messaging of pickup is uploaded to intercommunication server by step 2, mobile terminal.
Voice messaging is pushed to step 3, intercommunication server the intelligent sound interactive device of binding.
Step 4, intelligent sound interactive device play cuing voice points out user to have received the voice of push.
Step 5, user's button on intelligent sound interactive device,.
The voice messaging of mobile terminal side is played to user by step 6, intelligent sound interactive device.
Second situation, user initiates intercommunication at the intelligent sound interactive device end, and voice messaging is pushed into binding
Mobile terminal on.
As shown in figure 18, user initiates the flow of intercommunication mainly comprising five steps at the intelligent sound interactive device end
Suddenly, it is respectively：
Step 1, user's button on intelligent sound interactive device enters talkback mode, and user speaks, and is input into voice.
Step 2, intelligent sound interactive device pick up user input voice, and voice messaging is uploaded to by wifi it is right
Say server.
Voice messaging is pushed to step 3, intercommunication server the mobile terminal that account is bound with intelligent sound interactive device.
Step 4, mobile terminal prompting user receives voice messaging push.
Step 5, user opens mobile terminal, and voice messaging is played after click.
By the explanation of specific embodiment, should to the present invention for reach technological means that predetermined purpose is taken and
Effect is able to more go deep into and specific understanding, but appended diagram is only to provide reference and purposes of discussion, not for originally
Invention is any limitation as.
Claims (25)
1. a kind of intelligent sound interactive device, it is characterised in that including：Information receiving module, control module, question and answer search mould
Block, dio Output Modules and communication module, wherein,
Information receiving module, operating mode instruction, other side's speech play control information, request voice messaging for receiving user
And our intercommunication information, the operating mode instruction is instructed including talkback mode or question-answering mode is instructed；
The communication module, for carrying out information exchange with outside intercommunication server；
The dio Output Modules, for playing voice；
The question and answer search module, for being furnished an answer for the request voice messaging；
The control module, for when the operating mode instruction is instructed for question-answering mode, controlling the question and answer search module
For the request voice messaging furnishes an answer；When the operating mode instruction is instructed for talkback mode, control described information connects
The our intercommunication information of module input is received, and controls the communication module that the our intercommunication information is sent into the intercommunication service
Device, when the communication module receives other side's voice that the intercommunication server sends, the control module passes through the sound
Frequency output module asks the user whether to play other side's voice, and receives other side's voice in described information receiver module and broadcast
Put after control information, control the dio Output Modules to play other side's voice.
2. intelligent sound interactive device according to claim 1, it is characterised in that described information receiver module, for propping up
Hold one or more for receiving following form information：Voice messaging, text information, key information, gesture information and touch letter
Breath.
3. intelligent sound interactive device according to claim 1, it is characterised in that described device also includes：Memory module,
For storing the talkback mode instruction and question-answering mode instruction.
4. intelligent sound interactive device according to claim 1, it is characterised in that the question and answer search module includes：
Voice recognition unit, for the request voice messaging to be converted into request speech text by speech recognition；
Question and answer search unit, for storage problem template and the corresponding answer voice of described problem template；Obtained by semantics recognition
To the described problem template matched with the request speech text, the corresponding answer language is obtained according to described problem template
Sound.
5. intelligent sound interactive device according to claim 4, it is characterised in that the voice recognition unit, including：This
Ground voice recognition unit and/or high in the clouds voice recognition unit；
The question and answer search unit, including：Local question and answer search unit and/or high in the clouds question and answer search unit.
6. intelligent sound interactive device according to claim 1, it is characterised in that described device also includes：Memory module,
Voice is reminded for storing, the prompting voice is used to carry out calling prompting；And/or,
Described device also includes：Indicator lamp, for working to carry out calling prompting according to the first flashing mode.
7. intelligent sound interactive device according to claim 1, it is characterised in that described device also includes：Acceleration is passed
Sensor, is monitored for the acceleration to intelligent sound interactive device；
Power supply, for being supplied for the control module, the Audio Input Modules, the dio Output Modules and the communication module
Electricity；
The control module, is additionally operable to determine the acceleration and the acceleration that falls of the intelligent sound interactive device in preset duration
When scope is persistently matched, the power supply is closed.
8. intelligent sound interactive device according to claim 7, it is characterised in that described device also includes：Memory module,
Audio is reminded for storing emergency；
The control module, is additionally operable to determine in preset duration that the acceleration of the intelligent sound interactive device adds with described falling
When velocity interval is persistently matched, control the dio Output Modules to play the emergency and remind audio.
9. the intelligent sound interactive device according to claim 7 or 8, it is characterised in that described device, also includes：Indicate
Lamp, for working to carry out prompting of falling according to the second flashing mode；
The control module, is additionally operable to determine in preset duration that the acceleration of the intelligent sound interactive device adds with described falling
When velocity interval is persistently matched, the indicator lamp is controlled to carry out prompting of falling.
10. intelligent sound interactive device according to claim 7, it is characterised in that described device also includes：Timer,
Acceleration for comparing the intelligent sound interactive device in the control module is matched with the acceleration range of falling
When start timing, when timing duration reaches preset duration, timing terminates；The acceleration range of falling includes：Object freely falls
Acceleration of gravity scope during body, or, acceleration range when object is thrown downwards；
The control module, if for compare intelligent sound interactive device in the preset duration in the timer plus
Speed is still matched with the acceleration range of falling, then close the power supply.
11. intelligent sound interactive devices according to claim 10, it is characterised in that described device also includes：Storage mould
Block, thanks to audio for storing；
The control module, is additionally operable to when the notice of the timer is received, if comparing the friendship of current time intelligent sound
The acceleration of mutual device falls into acceleration range when object is caught, then control the dio Output Modules to play the thanks
Audio.
12. intelligent sound interactive devices according to claim 9, it is characterised in that
The control module, is additionally operable to join the acceleration change parameter of intelligent sound interactive device with the acceleration change of setting
Number is compared；If being consistent, the power supply is closed；
The acceleration change parameter of the setting, including：In setting duration, acceleration value occur positive and negative alternate number of times with
And the positive peak threshold value and negative peak threshold value that acceleration value reaches.
A kind of 13. intelligent speech interactive systems, it is characterised in that including：It is any in intercommunication server and such as claim 1~12
Intelligent sound interactive device described in, wherein,
The intercommunication server, for receiving voice that mobile terminal sends and being transmitted to intelligent sound interactive device；Receive intelligence
The voice sent of voice interaction device and mobile terminal can be transmitted to.
14. intelligent speech interactive systems according to claim 13, it is characterised in that
The intercommunication server, is additionally operable to receive the mobile terminal and the intelligent sound interactive device that mobile terminal is uploaded
Binding information, the forwarding of voice is carried out based on the binding information.
A kind of 15. intelligent speech interactive systems, it is characterised in that including：Intercommunication server, mobile terminal and such as claim 1
Intelligent sound interactive device any one of~12, wherein,
The mobile terminal, for sending voice to the intercommunication server；Receive the intelligence that the intercommunication server is sent
The voice of energy voice interaction device；
The intercommunication server, for receiving voice that the mobile terminal sends and being transmitted to the intelligent sound interaction dress
Put；Receive voice that the intelligent sound interactive device sends and be transmitted to the mobile terminal.
A kind of 16. intelligent sound exchange methods, it is characterised in that including：
The operating mode instruction of user is received, to determine being to enter question-answering mode or to enter talkback mode；
Under question-answering mode, for the request voice messaging for receiving furnishes an answer；
Under talkback mode, the our intercommunication information being input into is sent to the intercommunication server, is taken when the intercommunication is received
During other side's voice that business device sends, ask the user whether to play other side's voice, and after user agrees to play, play institute
State other side's voice.
17. intelligent sound exchange methods according to claim 16, it is characterised in that the determination is to enter question-answering mode
Still talkback mode is entered, specially：
Input information according to user determines it is to enter question-answering mode or enter talkback mode；
The form of the input information of the user includes one or more of following form information：Voice messaging, text information, press
Key information, gesture information and touch information.
18. intelligent sound exchange methods according to claim 16, it is characterised in that described is the request voice for receiving
Information furnishes an answer, including：
The request voice messaging of user is converted to by request speech text by speech recognition；
Based on the corresponding answer voice of question template and described problem template for prestoring, by semantics recognition obtain with it is described
The described problem template of request speech text matching, the corresponding answer voice is obtained according to described problem template.
19. intelligent sound exchange methods according to claim 16, it is characterised in that methods described also includes：Storage is carried
Awake voice, the prompting voice is used to carry out calling prompting；And/or,
Work to carry out calling prompting according to the first flashing mode by indicator lamp.
20. intelligent sound exchange methods according to claim 16, it is characterised in that methods described also includes：To intelligence
The acceleration of voice interaction device is monitored；
When determining that the acceleration of the intelligent sound interactive device in preset duration is persistently matched with acceleration range of falling, close
Power supply.
21. intelligent sound exchange methods according to claim 20, it is characterised in that methods described also includes：Storage is asked
Rescue prompting audio；
When the acceleration for comparing the intelligent sound interactive device in preset duration is persistently matched with acceleration range of falling,
Play the emergency and remind audio.
22. intelligent sound exchange methods according to claim 20, it is characterised in that methods described also includes：Compare
When the acceleration of the intelligent sound interactive device is persistently matched with acceleration range of falling in preset duration, by indicator lamp
Work to carry out prompting of falling according to the second flashing mode.
23. intelligent sound exchange methods according to claim 20, it is characterised in that described to compare in preset duration
The acceleration of the intelligent sound interactive device is persistently matched with acceleration range of falling, and closes power supply, including：
Start timing when the acceleration for comparing the intelligent sound interactive device is matched with the acceleration range of falling；Institute
Stating acceleration range of falling includes：Acceleration of gravity scope during object freely falling body, or, adding when object is thrown downwards
Velocity interval；
When timing duration reaches preset duration, if compare the acceleration of current time intelligent sound interactive device with it is described
Acceleration range of falling still is matched, then close power supply.
24. intelligent sound exchange methods according to claim 23, it is characterised in that methods described also includes：Storage sense
Thank to audio；
When timing duration reaches preset duration, if the acceleration for comparing current time intelligent sound interactive device falls into thing
Acceleration range when body is caught, then play the thanks audio.
25. intelligent sound exchange methods according to claim 16, it is characterised in that methods described also includes：Will intelligence
The acceleration change parameter of voice interaction device is compared with the acceleration change parameter of setting；If being consistent, power supply is closed；
The acceleration change parameter of the setting, including：In setting duration, acceleration value occur positive and negative alternate number of times with
And the positive peak threshold value and negative peak threshold value that acceleration value reaches.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710032588.2A CN106782539A (en) | 2017-01-16 | 2017-01-16 | A kind of intelligent sound exchange method, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710032588.2A CN106782539A (en) | 2017-01-16 | 2017-01-16 | A kind of intelligent sound exchange method, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106782539A true CN106782539A (en) | 2017-05-31 |
Family
ID=58947101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710032588.2A Pending CN106782539A (en) | 2017-01-16 | 2017-01-16 | A kind of intelligent sound exchange method, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106782539A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154579A (en) * | 2017-12-22 | 2018-06-12 | 深圳市天和荣科技有限公司 | A kind of intelligent access control system and exchange method that can be interacted with visitor |
| CN108172226A (en) * | 2018-01-27 | 2018-06-15 | 上海萌王智能科技有限公司 | A kind of voice control robot for learning response voice and action |
| CN108189026A (en) * | 2017-12-01 | 2018-06-22 | 北京建筑大学 | Guest-meeting robot interaction control method and device |
| CN109102804A (en) * | 2018-08-17 | 2018-12-28 | 飞救医疗科技（赣州）有限公司 | A kind of method and its system of the input of voice case history terminal |
| CN109887176A (en) * | 2019-01-10 | 2019-06-14 | 北京市燃气集团有限责任公司 | For the indoor intelligent safety control device and method of intelligent gas meter |
| CN110473555A (en) * | 2019-09-10 | 2019-11-19 | 上海朗绿建筑科技股份有限公司 | A kind of exchange method and device based on distributed sound equipment |
| CN110909133A (en) * | 2018-09-17 | 2020-03-24 | 上海智臻智能网络科技股份有限公司 | Intelligent question and answer testing method and device, electronic equipment and storage medium |
| CN111326137A (en) * | 2018-12-13 | 2020-06-23 | 允匠智能科技(上海)有限公司 | Voice robot interaction system based on office intelligence |
| CN112511406A (en) * | 2020-10-30 | 2021-03-16 | 国网山东省电力公司泰安供电公司 | Voice playing method and system of instant messaging software |
| CN113225364A (en) * | 2020-10-29 | 2021-08-06 | 深圳市芯中芯科技有限公司 | AI intelligent monitoring attendance system and method |
| CN113689663A (en) * | 2021-08-05 | 2021-11-23 | 浙江晨逸新声物联科技有限公司 | System and method for monitoring infant emergency |
| CN114639395A (en) * | 2020-12-16 | 2022-06-17 | 观致汽车有限公司 | Voice control method and device for vehicle-mounted virtual character and vehicle with voice control device |
| CN116705026A (en) * | 2023-08-02 | 2023-09-05 | 江西科技学院 | Artificial intelligence interaction method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101592536A (en) * | 2008-05-30 | 2009-12-02 | 鸿富锦精密工业（深圳）有限公司 | The portable electric appts of gravity sensor and application thereof |
| CN101819615A (en) * | 2010-03-15 | 2010-09-01 | 湖南德沐数码科技有限公司 | Method for protecting multimedia product through gravity acceleration |
| CN102005722A (en) * | 2010-10-29 | 2011-04-06 | 北京播思软件技术有限公司 | Method and device for preventing short circuit of handheld terminal |
| CN103949072A (en) * | 2014-04-16 | 2014-07-30 | 上海元趣信息技术有限公司 | Interaction method and transmission method of intelligent toy and intelligent toy |
| CN104090821A (en) * | 2014-07-10 | 2014-10-08 | 东莞市乐升电子有限公司 | Full-touch system activating method and system |
| US20150221308A1 (en) * | 2012-10-02 | 2015-08-06 | Denso Corporation | Voice recognition system |
| CN105094533A (en) * | 2015-06-30 | 2015-11-25 | 努比亚技术有限公司 | Method and mobile terminal for entering single-hand mode based on multi-functional key |
| CN106200886A (en) * | 2015-04-30 | 2016-12-07 | 包伯瑜 | A kind of intelligent movable toy manipulated alternately based on language and toy using method |
| CN106253415A (en) * | 2016-09-14 | 2016-12-21 | 努比亚技术有限公司 | A kind of charge control method and device |
| CN206489874U (en) * | 2017-01-16 | 2017-09-12 | 上海智臻智能网络科技股份有限公司 | A kind of intelligent sound interactive device and system |
-
2017
- 2017-01-16 CN CN201710032588.2A patent/CN106782539A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101592536A (en) * | 2008-05-30 | 2009-12-02 | 鸿富锦精密工业（深圳）有限公司 | The portable electric appts of gravity sensor and application thereof |
| CN101819615A (en) * | 2010-03-15 | 2010-09-01 | 湖南德沐数码科技有限公司 | Method for protecting multimedia product through gravity acceleration |
| CN102005722A (en) * | 2010-10-29 | 2011-04-06 | 北京播思软件技术有限公司 | Method and device for preventing short circuit of handheld terminal |
| US20150221308A1 (en) * | 2012-10-02 | 2015-08-06 | Denso Corporation | Voice recognition system |
| CN103949072A (en) * | 2014-04-16 | 2014-07-30 | 上海元趣信息技术有限公司 | Interaction method and transmission method of intelligent toy and intelligent toy |
| CN104090821A (en) * | 2014-07-10 | 2014-10-08 | 东莞市乐升电子有限公司 | Full-touch system activating method and system |
| CN106200886A (en) * | 2015-04-30 | 2016-12-07 | 包伯瑜 | A kind of intelligent movable toy manipulated alternately based on language and toy using method |
| CN105094533A (en) * | 2015-06-30 | 2015-11-25 | 努比亚技术有限公司 | Method and mobile terminal for entering single-hand mode based on multi-functional key |
| CN106253415A (en) * | 2016-09-14 | 2016-12-21 | 努比亚技术有限公司 | A kind of charge control method and device |
| CN206489874U (en) * | 2017-01-16 | 2017-09-12 | 上海智臻智能网络科技股份有限公司 | A kind of intelligent sound interactive device and system |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108189026A (en) * | 2017-12-01 | 2018-06-22 | 北京建筑大学 | Guest-meeting robot interaction control method and device |
| CN108154579A (en) * | 2017-12-22 | 2018-06-12 | 深圳市天和荣科技有限公司 | A kind of intelligent access control system and exchange method that can be interacted with visitor |
| CN108172226A (en) * | 2018-01-27 | 2018-06-15 | 上海萌王智能科技有限公司 | A kind of voice control robot for learning response voice and action |
| CN109102804A (en) * | 2018-08-17 | 2018-12-28 | 飞救医疗科技（赣州）有限公司 | A kind of method and its system of the input of voice case history terminal |
| CN110909133B (en) * | 2018-09-17 | 2022-06-24 | 上海智臻智能网络科技股份有限公司 | Intelligent question and answer testing method and device, electronic equipment and storage medium |
| CN110909133A (en) * | 2018-09-17 | 2020-03-24 | 上海智臻智能网络科技股份有限公司 | Intelligent question and answer testing method and device, electronic equipment and storage medium |
| CN111326137A (en) * | 2018-12-13 | 2020-06-23 | 允匠智能科技(上海)有限公司 | Voice robot interaction system based on office intelligence |
| CN109887176A (en) * | 2019-01-10 | 2019-06-14 | 北京市燃气集团有限责任公司 | For the indoor intelligent safety control device and method of intelligent gas meter |
| CN110473555B (en) * | 2019-09-10 | 2020-09-08 | 上海朗绿建筑科技股份有限公司 | Interaction method and device based on distributed voice equipment |
| CN110473555A (en) * | 2019-09-10 | 2019-11-19 | 上海朗绿建筑科技股份有限公司 | A kind of exchange method and device based on distributed sound equipment |
| CN113225364A (en) * | 2020-10-29 | 2021-08-06 | 深圳市芯中芯科技有限公司 | AI intelligent monitoring attendance system and method |
| CN113225364B (en) * | 2020-10-29 | 2022-05-27 | 深圳市芯中芯科技有限公司 | AI intelligent monitoring attendance system and method |
| CN112511406A (en) * | 2020-10-30 | 2021-03-16 | 国网山东省电力公司泰安供电公司 | Voice playing method and system of instant messaging software |
| CN114639395A (en) * | 2020-12-16 | 2022-06-17 | 观致汽车有限公司 | Voice control method and device for vehicle-mounted virtual character and vehicle with voice control device |
| CN113689663A (en) * | 2021-08-05 | 2021-11-23 | 浙江晨逸新声物联科技有限公司 | System and method for monitoring infant emergency |
| CN113689663B (en) * | 2021-08-05 | 2022-10-04 | 浙江晨逸新声物联科技有限公司 | System and method for monitoring infant emergency |
| CN116705026A (en) * | 2023-08-02 | 2023-09-05 | 江西科技学院 | Artificial intelligence interaction method and system |
| CN116705026B (en) * | 2023-08-02 | 2023-10-13 | 江西科技学院 | Artificial intelligence interaction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106782539A (en) | A kind of intelligent sound exchange method, apparatus and system | |
| CN105288972B (en) | A kind of control device and method of Basketball Intellectual machine | |
| US20170118291A1 (en) | Information processing system applied in a vehicle system | |
| CN209017333U (en) | Blue tooth voice controls equipment | |
| CN108573703B (en) | Control method of electric appliance system | |
| CN104702783B (en) | Article searching method and automatic answering system based on voice signal | |
| CN109003609A (en) | Voice equipment, intelligent voice system, equipment control method and device | |
| CN109871238A (en) | Voice interactive method, device and storage medium | |
| CN109741740A (en) | Voice interactive method and device based on external trigger | |
| CN108597520A (en) | A kind of control method of Intelligent socket and Intelligent socket | |
| CN105978098A (en) | Charging control method and device | |
| CN109150675A (en) | Interaction method and device for household appliances | |
| CN206489874U (en) | A kind of intelligent sound interactive device and system | |
| CN111163448B (en) | Interphone system and use method thereof | |
| CN105049599A (en) | Intelligent conversation method and device | |
| CN110584278A (en) | Smart wristband with voice interaction function and method | |
| CN208031857U (en) | A kind of true man CS water bullet fighting system | |
| CN106888431A (en) | The method and system of good friend are added on a kind of intelligent watch | |
| CN206684928U (en) | Intelligent remote controller and by remote terminal | |
| CN210642705U (en) | Voice interaction device based on helmet | |
| WO2016033874A1 (en) | Wireless charging processing method and apparatus, and wireless charger | |
| CN207264552U (en) | A kind of Portable safety protection intelligent alarm device and system | |
| CN206424555U (en) | A kind of intelligent sound interactive device, system and intelligent toy | |
| CN105611076A (en) | Medicine management system and management method for intelligent home medicine box based on internet of things | |
| CN202075687U (en) | Wireless wake-up system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |