CN110223683A - Voice interactive method and system - Google Patents
Voice interactive method and system Download PDFInfo
- Publication number
- CN110223683A CN110223683A CN201910369542.9A CN201910369542A CN110223683A CN 110223683 A CN110223683 A CN 110223683A CN 201910369542 A CN201910369542 A CN 201910369542A CN 110223683 A CN110223683 A CN 110223683A
- Authority
- CN
- China
- Prior art keywords
- data
- voice
- cloud
- feedback
- audio
- 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
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000005457 optimization Methods 0.000 claims abstract description 39
- 230000003993 interaction Effects 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims description 46
- 238000012544 monitoring process Methods 0.000 claims description 20
- 230000007704 transition Effects 0.000 claims description 14
- 230000000712 assembly Effects 0.000 claims description 10
- 238000000429 assembly Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 230000010365 information processing Effects 0.000 claims description 5
- 230000001960 triggered effect Effects 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 19
- 238000004590 computer program Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000005236 sound signal Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 206010000210 abortion Diseases 0.000 description 2
- 231100000176 abortion Toxicity 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000005055 memory storage Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241001062009 Indigofera Species 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 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
- 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
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- 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
- G10L15/28—Constructional details of speech recognition systems
- G10L15/34—Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
-
- 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
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
A kind of voice interactive method and system, comprising: acquisition exhibition booth voice data;Exhibition booth voice data is handled, to obtain optimization audio data;Optimization audio data is sent to cloud, obtains voice feedback data accordingly;Calculation optimization audio data and voice feedback data, to obtain pre- interaction data;Play pre- interaction data and voice feedback data.The present invention solves the low technical problem of voice interactive function applicability existing in the prior art.
Description
Technical field
The present invention relates to a kind of system adjusting methods, more particularly to a kind of voice interactive method and system.
Background technique
With the continuous social and economic development and the raising of living standards of the people, investment power of the people in culture and education intermediate item
Degree continues to increase, and the interminable content that place showpiece character introduction is popularized in the science and cultures such as traditional museum, science and technology center may
The reading fatigue that will cause tourist, is not easy to appreciate showpiece, so all character introductions are equipped with corresponding phonetic explaining, facilitates trip
The objective phonetic explaining that showpiece is listened to when visiting showpiece largely relies on artificial guide to visitors during exhibition and the introduction of content is spelled in exhibition,
Only a small amount of biggish venue of the volume of the flow of passengers uses easy interaction technique.The intelligent sound of science and technology center existing in theprior art
In showpiece, there is the function of much requiring online interactive voice, since there are client terminal, screen and exhibition booth interactive devices and clothes
End be engaged in by network connection, is easy Xiang and is handed over as caused by the factors such as network delay and network transmission speed and flow restriction
Mutually delay, the problem that interactive signal is second-rate and interactive experience effect is poor, also, different such as interactive voice
When interactive application scene such as back-end server fails to timely feedback result because of factors such as treatment effeciency and temporary faults, front end
There is the state that interaction delay is even stagnated in exhibition booth interactive device, and lacks buffering effect to the interaction problems of delay class, reduces
The interactivity of showpiece.
In conclusion exchange method interactive quality in exhibition booth in the prior art and the interactive experience of user are poor, and
Interaction is depended on unduly manually, and interactive intelligence is lower and is unsuitable for popularizing, and there are the lower technical problems of interactive function applicability.
Summary of the invention
The shortcomings that in view of the above prior art, the purpose of the present invention is to provide a kind of voice interactive method and systems, answer
It adjusts and corrects for flexiblesystem, asked to solve the lower technology of voice interactive function applicability existing in the prior art
Topic, the present invention provide a kind of voice interactive method and system, a kind of voice interactive method, comprising: acquisition exhibition booth voice data;Place
Exhibition booth voice data is managed, to obtain optimization audio data;Optimization audio data is sent to cloud, obtains voice feedback number accordingly
According to;Calculation optimization audio data and voice feedback data, to obtain pre- interaction data;Play pre- interaction data and voice feedback number
According to.
In one embodiment of the present invention, handle exhibition booth voice the step of, comprising: numeralization processing exhibition booth voice data
For input data set;Obtain audio filter information;Input data set is screened with audio filter information, to obtain optimization audio number
According to.
In one embodiment of the present invention, the step of obtaining voice feedback, comprising: send optimization audio data to cloud
End;Extract the cloud flag data in optimization audio data;Obtain cloud feedback database;According to cloud flag data traversal
With cloud feedback database, to obtain voice feedback data.
In one embodiment of the present invention, the step of obtaining interactive audio data is calculated, comprising: obtain adjustment parameter letter
Breath;Voice feedback data are monitored, to obtain cloud monitoring data;Optimize audio data according to adjustment parameter information processing, with
To pre- feedback characteristic data;Adjustment parameter information is calculated according to pre- feedback characteristic data and cloud monitoring data, to be pre-payed
Mutual data.
In one embodiment of the present invention, play interaction data the step of, comprising: by pre- interaction data and voice feedback
Data are converted to output audio data;Preset audio playback equipment is triggered, to play output audio data.
In one embodiment of the present invention, a kind of voice interactive system, system includes: exhibition booth acquisition unit, to adopt
Collect exhibition booth voice data;Audio treatment unit, to handle exhibition booth voice data, to obtain optimization audio data, audio processing
Unit is connect with exhibition booth acquisition unit;It is anti-to obtain voice to send optimization audio data to cloud accordingly for cloud feedback unit
Data are presented, cloud feedback unit is connect with audio treatment unit;Pre- interactive data cell, to calculation optimization audio data and language
Sound feedback data, to obtain pre- interaction data, pre- interactive data cell is connect with audio treatment unit, pre- interactive data cell with
The connection of cloud feedback unit;Audio playing unit, to play pre- interaction data and voice feedback data, audio playing unit with
Pre- interactive data cell connection.
In one embodiment of the present invention, audio treatment unit, comprising: input processing component, to the processing that quantizes
Exhibition booth voice data is input data set;Audio data component, to obtain audio filter information;Filter assemblies, for sound
Frequency filter information screens input data set, and to obtain optimization audio data, filter assemblies are connect with input processing component, filtering group
Part is connect with audio data component.
In one embodiment of the present invention, cloud feedback unit, comprising: communication component, to send optimization audio number
According to cloud;Cloud data package, to extract optimization audio data in cloud flag data, cloud data package with communicate
Component connection;Cloud storage assembly, to obtain cloud feedback database, cloud storage assembly is connect with communication component;Feedback
Processing component, to traverse matching cloud feedback database according to cloud flag data, to obtain voice feedback data, at feedback
Reason component is connect with cloud data package, and feedback processing component is connect with cloud storage assembly.
In one embodiment of the present invention, pre- interactive data cell, comprising: adjust data package, adjusted to obtain
Parameter information;Cloud monitoring assembly, to monitor voice feedback data, to obtain cloud monitoring data;Recording processing component, is used
To optimize audio data according to adjustment parameter information processing, to obtain pre- feedback characteristic data, recording processing component and adjusting number
It is connected according to component;Interactive audio component, to calculate adjustment parameter information according to pre- feedback characteristic data and cloud monitoring data,
To obtain pre- interaction data, interactive audio component is connect with cloud monitoring assembly, and interactive audio component and recording processing component connect
It connects.
In one embodiment of the present invention, audio playing unit, comprising: output transition components, to by pre- interactive number
Output audio data is converted to according to voice feedback data;Player module is triggered, to trigger preset audio playback equipment, to broadcast
Output audio data is put, triggering player module is connect with output transition components.
In one embodiment of the present invention, a kind of computer readable storage medium is stored thereon with computer program, should
Voice interactive method is realized when program is executed by processor.
In one embodiment of the present invention, a kind of interactive voice equipment, comprising: processor and memory;Memory is used
In storage computer program, processor is used to execute the computer program of memory storage, so that speech ciphering equipment executes voice and hands over
Mutual method.
As described above, a kind of voice interactive method provided by the invention and system, have the advantages that of the invention
A kind of language exchange method and system are improved the interactivity of showpiece, are failed in speech cloud by the way of voice transitional module
Before timely feedbacking result, showpiece can give user feedback relevant information, persistently interact convenient for user.The algorithm of this patent
Simply, it does not need to set up complicated Processing Algorithm, arithmetic speed is fast, and real-time is high.Voice transitional module not will receive field simultaneously
Scape, brightness, illumination, visitor's relative influence, wide adaptation range.Program component is simple, is not only easy to dispose, and is also convenient for extending,
This is particularly advantageous to be promoted in each scientific and technological venue, and meets different interactive voice applied fields by parameter preset
Scape demand.
In conclusion being interacted using such as voice transitional module in the non-feedback result of speech cloud, improving showpiece
Interactivity, the present invention solve the lower technical problem of voice interactive function applicability existing in the prior art.
Detailed description of the invention
Fig. 1 shows voice interactive method step schematic diagram of the invention.
Fig. 2 is shown as the cell data transmission schematic diagram of the present invention in one embodiment.
Fig. 3 is shown as the idiographic flow schematic diagram of step S2 in one embodiment in Fig. 1.
Fig. 4 is shown as the idiographic flow schematic diagram of step S3 in one embodiment in Fig. 1.
Fig. 5 is shown as the idiographic flow schematic diagram of step S4 in one embodiment in Fig. 1.
Fig. 6 is shown as the idiographic flow schematic diagram of step S5 in one embodiment in Fig. 1.
The voice interactive system unit connection book that Fig. 7 is shown as of the invention is intended to.
Fig. 8 is shown as the specific component connection schematic diagram of Fig. 7 sound intermediate frequency processing unit 2 in one embodiment.
Fig. 9 is shown as the specific component connection schematic diagram of cloud feedback unit 3 in one embodiment in Fig. 7.
Figure 10 is shown as the specific component connection schematic diagram of pre- interactive data cell 4 in one embodiment in Fig. 7.
Figure 11 is shown as the specific component connection schematic diagram of Fig. 7 sound intermediate frequency broadcast unit 5 in one embodiment.
Component label instructions
1 exhibition booth acquisition unit
2 audio treatment units
3 cloud feedback units
4 pre- interactive data cells
5 audio playing units
21 input processing components
22 audio data components
23 filter assemblies
31 communication components
32 cloud data packages
33 cloud storage assemblies
34 feedback processing components
41 adjust data package
42 cloud monitoring assemblies
43 recording processing components
44 interactive audio components
51 output transition components
52 triggering player modules
Recommend receiving module step numbers explanation
Fig. 1 S1~S5
Fig. 3 S21~S23
Fig. 4 S31~S34
Fig. 5 S41~S44
Fig. 6 S51~S52
Specific embodiment
Embodiments of the present invention are illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book is understood other advantages and efficacy of the present invention easily.
Fig. 1 is please referred to Figure 11, it should however be clear that this specification structure depicted in this specification institute accompanying drawings, only to cooperate specification
Revealed content is not intended to limit the invention enforceable restriction item so that those skilled in the art understands and reads
Part, therefore do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing
Under the effect of present invention can be generated and the purpose that can reach, should all still fall in disclosed technology contents can contain
In the range of lid.Meanwhile in this specification it is cited such as " on ", " under ", " left side ", " right side ", " centre " and " one " term,
It is merely convenient to being illustrated for narration, rather than to limit the scope of the invention, relativeness is altered or modified,
It is changed under technology contents without essence, when being also considered as the enforceable scope of the present invention.
Fig. 1 and Fig. 2 is please referred to, is shown as voice interactive method step schematic diagram and the present invention of the invention in an embodiment
In cell data transmit schematic diagram, as shown in Figures 1 and 2, a kind of voice interactive method, comprising:
S1, acquisition exhibition booth voice data, in the present embodiment, acquisition exhibition booth voice data can pass through exhibition booth own computer
On mouse, interactive apparatus selection speech interaction mode etc. the editables option control that either connect with computer of keyboard records
Sound equipment such as microphone carries out data under voice;
S2, processing exhibition booth voice data need the language in showpiece in the present embodiment to obtain optimization audio data
Outside sound control module, add a such as voice transit data processor, in the present embodiment, the processor can for such as S51 or
S52 single-chip microcontroller;
S3, optimization audio data being sent to cloud, obtaining voice feedback data accordingly, in the present embodiment, cloud can be with
Such as the connection of venue central control host, for storing exhibition room content-data, in the present embodiment, cloud server schedule backup
Data, ensures equipment, content normal operation, and central control host obtains from cloud server and caches corresponding displaying audio
And interaction data is for example classified audio data.In the present embodiment, cloud parameter setting and editor need to have administrator right;
S4, calculation optimization audio data and voice feedback data, to obtain pre- interaction data, in the present embodiment, voice
Feedback data can be played and be saved in terminal device such as mobile phone, tablet computer or laptop etc., in the present embodiment, can
It by terminal device or is installed on the sound pick-up outfit of exhibition booth microphone for example arranged side by side and obtains tourist's voice messaging, and by tourist information
Send the processing of the background devices such as cloud platform, server platform;
S5, pre- interaction data and voice feedback data are played, in the present embodiment, showpiece interactive module is in voice control mould
After block obtains the feedback of speech cloud, the data of processing speech cloud feedback, if not obtaining the feedback of speech cloud always, using eventually
Only parameter calls the content of voice transitional module, and the transition voice to prove an abortion is fed back to showpiece user.
Referring to Fig. 3, the idiographic flow schematic diagram of step S2 in one embodiment in Fig. 1 is shown as, as shown in figure 3, place
Manage the step S2 of exhibition booth voice, comprising:
S21, numeralization processing exhibition booth voice data are input data set, in the present embodiment, are started and showpiece in user
Carry out interactive voice when, showpiece interactive module calls speech control module first, and voice module carries out preliminary judgement, see whether
It is suitable voice;
S22, audio filter information is obtained, in the present embodiment, if not the voice for closing rule, then directly filtered, if
It is the voice for closing rule, then carries out the processing of next step;
S23, input data set is screened with audio filter information, it in the present embodiment can example to obtain optimization audio data
It is sent to speech input device such as wireless speech as exhibition booth voice data is converted to after radiofrequency signal by RF radiofrequency launcher and connects
Receive device.
Referring to Fig. 4, the idiographic flow schematic diagram of step S3 in one embodiment in Fig. 1 is shown as, as shown in figure 4, obtaining
Take the step S3 of voice feedback, comprising:
S31, optimization audio data is sent to cloud;
S32, cloud flag data in optimization audio data is extracted, in the present embodiment, each exhibition booth can be for example, by
The table and data that bluetooth transmitters broadcast the exhibition booth be for example: device name or device id etc., in the present embodiment, Bluetooth signal hair
4.0 or more standard of bluetooth, including such as 4.0 standard of bluetooth, 4.1 standard of bluetooth, 4.2 standard of bluetooth, bluetooth 4.0 can be used in emitter
The above standard compatibility is strong, it includes that classical bluetooth, High Speed Bluetooth and Bluetooth Low Energy agreement, classical bluetooth then include old indigo plant
Tooth association, High Speed Bluetooth are based on Wi-Fi, so Bluetooth signal receiver receives signal suitable for more mobile terminals;
S33, cloud feedback database is obtained, in the present embodiment, user speech is committed to voice by speech control module
Cloud, while voice transitional module is called according to parameter, the voice recording for obtaining transition submits to showpiece interactive module;
S34, matching cloud feedback database is traversed according to cloud flag data, to obtain voice feedback data, in this reality
It applies in example, pre- interactive voice data calls voice transitional module to be handled by speech control module according to algorithm.
Referring to Fig. 5, the idiographic flow schematic diagram of step S4 in one embodiment in Fig. 1 is shown as, as shown in figure 5, meter
Calculate the step S4 for obtaining interactive audio data, comprising:
S41, adjustment parameter information is obtained, in the present embodiment, adjustment parameter information can be by being installed on exhibition booth shell
Control equipment such as liquid crystal touch screen or key panel are modified;
S42, monitoring voice feedback data, to obtain cloud monitoring data;
S43, audio data is optimized according to adjustment parameter information processing, to obtain pre- feedback characteristic data, in the present embodiment
In, different types of voice recording built in voice transitional module, the recording including variety classes and different content, in the present embodiment
In, type includes for example: male voice, female voice, child's voice, standard sound etc.;
S44, adjustment parameter information is calculated according to pre- feedback characteristic data and cloud monitoring data, to obtain pre- interactive number
According in the present embodiment, playing voice content in the state of the delay of showpiece interactive voice may include such as " waiting a moment ", " allows
I thinks of " or " this problem is excellent ", in the present embodiment, the type and content of recording can be with edit-modifies.
Referring to Fig. 6, the idiographic flow schematic diagram of step S5 in one embodiment in Fig. 1 is shown as, as shown in fig. 6, broadcasting
Put the step S5 of interaction data, comprising:
S51, pre- interaction data and voice feedback data are converted into output audio data, in the present embodiment, showpiece is handed over
Mutual module calls the voice recording of transition, and the feedback of waiting voice cloud, in the present embodiment, mountable example around each exhibition booth
Such as Bluetooth signal transmitter, device name, the device id of Bluetooth signal transmitter are broadcasted, Bluetooth signal transmitter can be installed and be put
It sets in the showcase edge of showpiece or the lower section of showcase;
Voice in the present embodiment, is played number to play output audio data by S52, triggering preset audio playback equipment
It is integrated according to such as radiofrequency signal, is converted to audio signal, and be transferred to playing device, playing device via audio switch
In power amplifier processing is amplified to audio signal, and the audio signal after enhanced processing is sent to loudspeaker, will
Sound is put outside, in the present embodiment, can check the text explanation data and static map of this exhibition object by clicking the exhibition object on picture
Piece data, and the speech sound eeplaining equipped with the guide recorded in advance about sight spot, visitor can select according to personal preference
Select different guides.
It is intended to referring to Fig. 7, being shown as voice interactive system unit connection book of the invention, as shown in fig. 7, a kind of voice
Interactive system includes that exhibition booth acquisition unit 1, audio treatment unit 2, cloud feedback unit 3, pre- interactive data cell 4 and audio are broadcast
Unit 5 is put, exhibition booth acquisition unit 1, to acquire exhibition booth voice data, in the present embodiment, acquisition exhibition booth voice data can lead to
Mouse, keyboard or the interactive apparatus selection speech interaction mode being connect with computer for crossing on the own computer of exhibition booth etc.
Editable option controls sound pick-up outfit such as microphone and carries out data under voice;Audio treatment unit 2, to handle exhibition booth language
Sound data, to obtain optimization audio data, audio treatment unit 2 connect with exhibition booth acquisition unit 1, in the present embodiment, needs
Outside speech control module in showpiece, a such as voice transit data processor is added, in the present embodiment, which can
For such as S51 or S52 single-chip microcontroller;It is anti-to obtain voice to send optimization audio data to cloud accordingly for cloud feedback unit 3
Data are presented, cloud feedback unit 3 is connect with audio treatment unit 2, and in the present embodiment, cloud can be controlled with such as venue center
Host connection, for storing exhibition room content-data, control server schedule backup data ensures equipment, content normal operation, in
Centre control host, which is obtained and cached from control server, corresponding shows that audio and interaction data are for example classified audio data.?
In the present embodiment, cloud parameter setting and editor need to have such as administrator right;Pre- interactive data cell 4, it is excellent to calculate
Change audio data and voice feedback data, to obtain pre- interaction data, pre- interactive data cell 4 is connect with audio treatment unit 2,
Pre- interactive data cell 4 is connect with cloud feedback unit 3, in the present embodiment, voice feedback data can terminal device for example
Mobile phone, tablet computer or laptop etc. are played and are saved, and in the present embodiment, by terminal device or can be installed on exhibition booth
Sound pick-up outfit such as microphone arranged side by side obtain tourist's voice messaging, and tourist information is sent into such as cloud platform, server and is put down
The processing of the background devices such as platform;Audio playing unit 5, to play pre- interaction data and voice feedback data, audio playing unit 5
It is connect with pre- interactive data cell 4, in the present embodiment, showpiece interactive module obtains the feedback of speech cloud in speech control module
Afterwards, the data of processing speech cloud feedback call voice transition using terminal parameter if not obtaining the feedback of speech cloud always
The content of module, and the transition voice to prove an abortion is fed back into showpiece user.
Referring to Fig. 8, being shown as the specific component connection schematic diagram of Fig. 7 sound intermediate frequency processing unit 2 in one embodiment, such as
Shown in Fig. 8, audio treatment unit 2 includes input processing component 21, audio data component 22 and filter assemblies 23, input processing
Component 21, to quantize handle exhibition booth voice data be input data set, in the present embodiment, user start and showpiece into
When row interactive voice, showpiece interactive module calls speech control module first, and voice module carries out preliminary judgement, see whether be
Suitable voice;Audio data component 22, to obtain audio filter information, in the present embodiment, if not the language for closing rule
Sound then directly filters, and if it is the voice for closing rule, then carries out the processing of next step;Filter assemblies 23 are believed for being screened with audio
Breath screening input data set, to obtain optimization audio data, filter assemblies 23 are connect with input processing component 21, filter assemblies 23
It is connect with audio data component 22, in the present embodiment, for example RF radiofrequency launcher exhibition booth voice data can be converted to radio frequency
Speech input device such as wireless speech receiver is sent to after signal.
Referring to Fig. 9, being shown as the specific component connection schematic diagram of cloud feedback unit 3 in one embodiment in Fig. 7, such as
Shown in Fig. 9, cloud feedback unit 3 includes communication component 31, cloud data package 32, cloud storage assembly 33 and feedback processing
Component 34, communication component 31, to send optimization audio data to cloud;Cloud data package 32, to extract optimization audio
Cloud flag data in data, cloud data package 32 are connect with communication component 31, and in the present embodiment, each exhibition booth can lead to
It crosses such as the table and data that bluetooth transmitters broadcast the exhibition booth for example: device name or device id, in the present embodiment, bluetooth
4.0 or more standard of bluetooth, including such as 4.0 standard of bluetooth, 4.1 standard of bluetooth, 4.2 standard of bluetooth can be used in signal projector,
4.0 or more standard compatibility of bluetooth is strong, it includes that classical bluetooth, High Speed Bluetooth and Bluetooth Low Energy agreement, classical bluetooth are then wrapped
Old bluetooth association is included, High Speed Bluetooth is based on Wi-Fi, so Bluetooth signal receiver receives letter suitable for more mobile terminals
Number;Cloud storage assembly 33, to obtain cloud feedback database, cloud storage assembly 33 is connect with communication component 31, at this
In embodiment, user speech is committed to speech cloud by speech control module, while calling voice transitional module according to parameter, is obtained
The voice recording of transition submits to showpiece interactive module;Feedback processing component 34 is matched to be traversed according to cloud flag data
Cloud feedback database, to obtain voice feedback data, feedback processing component 34 is connect with cloud data package 32, feedback processing
Component 34 is connect with cloud storage assembly 33, and in the present embodiment, pre- interactive voice data is by speech control module according to algorithm
Voice transitional module is called to be handled.
Referring to Fig. 10, being shown as the specific component connection signal of pre- interactive data cell 4 in one embodiment in Fig. 7
Figure, as shown in Figure 10, pre- interactive data cell 4 include adjusting data package 41, cloud monitoring assembly 42, recording processing component 43
With interactive audio component 44, data package 41 is adjusted, to obtain adjustment parameter information, in the present embodiment, adjustment parameter letter
Breath can be modified by being installed on control the equipment such as liquid crystal touch screen or key panel of exhibition booth shell;Cloud monitoring assembly
42, to monitor voice feedback data, to obtain cloud monitoring data;Recording processing component 43, to be believed according to adjustment parameter
Breath processing optimization audio data, to obtain pre- feedback characteristic data, recording processing component 43 is connect with data package 41 is adjusted,
In the present embodiment, different types of voice recording built in voice transitional module, the recording including variety classes and different content,
In the present embodiment, type includes for example: male voice, female voice, child's voice, standard sound etc.;Interactive audio component 44, to according to pre- feedback
Characteristic and cloud monitoring data calculate adjustment parameter information, to obtain pre- interaction data, interactive audio component 44 and cloud
Monitoring assembly 42 connects, and interactive audio component 44 is connect with recording processing component 43, in the present embodiment, in showpiece interactive voice
It may include such as " waiting a moment ", " let me think for a while " or " this problem is excellent " that voice content is played in the state of delay, at this
In embodiment, the type and content of recording can be with edit-modifies.
Figure 11 is please referred to, the specific component connection schematic diagram of Fig. 7 sound intermediate frequency broadcast unit 5 in one embodiment is shown as,
As shown in figure 11, audio playing unit 5 includes output transition components 51 and triggering player module 52, exports transition components 51, is used
Pre- interaction data and voice feedback data are converted to output audio data, in the present embodiment, showpiece interactive module is called
The voice recording of transition, and the feedback of waiting voice cloud, in the present embodiment, mountable such as Bluetooth signal around each exhibition booth
Transmitter, broadcasts device name, the device id of Bluetooth signal transmitter, and Bluetooth signal transmitter can be installed and be placed on showpiece
The lower section at showcase edge or showcase;Player module 52 is triggered, to trigger preset audio playback equipment, to play output audio
Data, triggering player module 52 are connect with output transition components 51, and in the present embodiment, data voice playback such as radio frequency is believed
It number is integrated, is converted to audio signal, and be transferred to playing device via audio switch, the power amplification in playing device
Device amplifies processing to audio signal, and the audio signal after enhanced processing is sent to loudspeaker, will put outside sound, at this
In embodiment, the text explanation data and static images data of this exhibition object can be checked, and be furnished with by clicking the exhibition object on picture
Speech sound eeplaining of the guide recorded in advance about sight spot, visitor can select different guides according to personal preference.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
Voice interactive method, those of ordinary skill in the art will appreciate that: realize all or part of the steps of above-mentioned each method embodiment
It can be completed by the relevant hardware of computer program.Computer program above-mentioned can store in a computer-readable storage
In medium.When being executed, execution includes the steps that above-mentioned each method embodiment to the program;And storage medium above-mentioned includes:
The various media that can store program code such as ROM, RAM, magnetic or disk.
A kind of interactive voice equipment, comprising: processor and memory;Memory is for storing computer program, processor
For executing the computer program of memory storage, so that interactive voice equipment executes voice interactive method, memory may be wrapped
Containing random access memory (RandomAccessMemory, abbreviation RAM), it is also possible to further include nonvolatile memory (non-
Volatilememory), a for example, at least magnetic disk storage.Above-mentioned processor can be general processor, including center
Processor (CentralProcessingUnit, abbreviation CPU), network processing unit (NetworkProcessor, abbreviation NP) etc.;
It can also be digital signal processor (DigitalSignalProcessing, abbreviation DSP), specific integrated circuit (Applic
AtionSpecificIntegratedCircuit, abbreviation ASIC), field programmable gate array (Field-
ProgrammableGateArray, abbreviation FPGA) either other programmable logic device, discrete gate or transistor logic device
Part, discrete hardware components.
A kind of voice interactive method provided by the invention and system have the advantages that a kind of language of the invention
Exchange method and system improve the interactivity of showpiece by the way of voice transitional module, fail to timely feedback in speech cloud
As a result before, showpiece can give user feedback relevant information, persistently interact convenient for user.The algorithm of this patent is simple, no
Need to set up complicated Processing Algorithm, arithmetic speed is fast, and real-time is high.Simultaneously voice transitional module not will receive scene, brightness,
Illumination, visitor's relative influence, wide adaptation range.Program component is simple, is not only easy to dispose, and is also convenient for extending, this especially has
It is promoted conducive in each scientific and technological venue, and meets different interactive voice application scenarios demands by parameter preset.
In conclusion being interacted using such as voice transitional module in the non-feedback result of speech cloud, improving showpiece
Interactivity, the present invention solve the lower technical problem of voice interactive function applicability existing in the prior art.
Claims (10)
1. a kind of voice interactive method, which is characterized in that the described method includes:
Acquire exhibition booth voice data;
The exhibition booth voice data is handled, to obtain optimization audio data;
The optimization audio data is sent to cloud, obtains voice feedback data accordingly;
The optimization audio data and the voice feedback data are calculated, to obtain pre- interaction data;
Play the pre- interaction data and the voice feedback data.
2. the method according to claim 1, wherein the step of processing exhibition booth voice, comprising:
It is input data set that numeralization, which handles the exhibition booth voice data,;
Obtain audio filter information;
The input data set is screened with the audio filter information, to obtain the optimization audio data.
3. the method according to claim 1, wherein the step of acquisition voice feedback, comprising:
The optimization audio data is sent to cloud;
Extract the cloud flag data in the optimization audio data;
Obtain cloud feedback database;
The cloud feedback database is matched according to cloud flag data traversal, to obtain the voice feedback data.
4. the method according to claim 1, wherein the calculating obtains the step of interactive audio data, comprising:
Obtain adjustment parameter information;
The voice feedback data are monitored, to obtain cloud monitoring data;
Optimize audio data according to the adjustment parameter information processing, to obtain pre- feedback characteristic data;
The adjustment parameter information is calculated according to the pre- feedback characteristic data and the cloud monitoring data, it is described pre- to obtain
Interaction data.
5. the method according to claim 1, wherein the step of broadcasting interaction data, comprising:
The pre- interaction data and the voice feedback data are converted into output audio data;
Preset audio playback equipment is triggered, to play the output audio data.
6. a kind of voice interactive system, which is characterized in that the system comprises:
Exhibition booth acquisition unit, to acquire exhibition booth voice data;
Audio treatment unit, to handle the exhibition booth voice data, to obtain optimization audio data;
Cloud feedback unit obtains voice feedback data to send the optimization audio data to cloud accordingly;
Pre- interactive data cell, to calculate the optimization audio data and the voice feedback data, to obtain pre- interactive number
According to;
Audio playing unit, to play the pre- interaction data and the voice feedback data.
7. system according to claim 6, which is characterized in that the audio treatment unit, comprising:
Input processing component handles the exhibition booth voice data to quantize as input data set;
Audio data component, to obtain audio filter information;
Filter assemblies, for screening the input data set with the audio filter information, to obtain the optimization audio data.
8. system according to claim 6, which is characterized in that the cloud feedback unit, comprising:
Communication component, to send the optimization audio data to cloud;
Cloud data package, to extract the cloud flag data in the optimization audio data;
Cloud storage assembly, to obtain cloud feedback database;
Feedback processing component, to match the cloud feedback database according to cloud flag data traversal, to obtain
Predicate sound feedback data.
9. system according to claim 6, which is characterized in that the pre- interactive data cell, comprising:
Data package is adjusted, to obtain adjustment parameter information;
Cloud monitoring assembly, to monitor the voice feedback data, to obtain cloud monitoring data;
Recording processing component, it is special to obtain pre- feedback to optimize audio data according to the adjustment parameter information processing
Levy data;
Interactive audio component, to calculate the adjustment parameter according to the pre- feedback characteristic data and the cloud monitoring data
Information, to obtain the pre- interaction data.
10. system according to claim 6, which is characterized in that the audio playing unit, comprising:
Transition components are exported, the pre- interaction data and the voice feedback data are converted to output audio data;
Player module is triggered, to trigger preset audio playback equipment, to play the output audio data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910369542.9A CN110223683A (en) | 2019-05-05 | 2019-05-05 | Voice interactive method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910369542.9A CN110223683A (en) | 2019-05-05 | 2019-05-05 | Voice interactive method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110223683A true CN110223683A (en) | 2019-09-10 |
Family
ID=67820340
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910369542.9A Pending CN110223683A (en) | 2019-05-05 | 2019-05-05 | Voice interactive method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110223683A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103440867A (en) * | 2013-08-02 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for recognizing voice |
CN106328148A (en) * | 2016-08-19 | 2017-01-11 | 上汽通用汽车有限公司 | Natural speech recognition method, natural speech recognition device and natural speech recognition system based on local and cloud hybrid recognition |
CN107294837A (en) * | 2017-05-22 | 2017-10-24 | 北京光年无限科技有限公司 | Engaged in the dialogue interactive method and system using virtual robot |
CN107731231A (en) * | 2017-09-15 | 2018-02-23 | 福州瑞芯微电子股份有限公司 | A kind of method for supporting more high in the clouds voice services and a kind of storage device |
CN208013692U (en) * | 2017-12-05 | 2018-10-26 | 厦门日华科技股份有限公司 | A kind of wisdom exhibition room control system based on interactive voice mode |
CN108818569A (en) * | 2018-07-30 | 2018-11-16 | 浙江工业大学 | Intelligent robot system towards public service scene |
CN108958698A (en) * | 2018-07-20 | 2018-12-07 | 珠海格力电器股份有限公司 | A kind of method, apparatus, storage medium and terminal for adding equipment |
CN109104634A (en) * | 2017-06-20 | 2018-12-28 | 中兴通讯股份有限公司 | A kind of set-top box working method, set-top box and computer readable storage medium |
-
2019
- 2019-05-05 CN CN201910369542.9A patent/CN110223683A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103440867A (en) * | 2013-08-02 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for recognizing voice |
CN106328148A (en) * | 2016-08-19 | 2017-01-11 | 上汽通用汽车有限公司 | Natural speech recognition method, natural speech recognition device and natural speech recognition system based on local and cloud hybrid recognition |
CN107294837A (en) * | 2017-05-22 | 2017-10-24 | 北京光年无限科技有限公司 | Engaged in the dialogue interactive method and system using virtual robot |
CN109104634A (en) * | 2017-06-20 | 2018-12-28 | 中兴通讯股份有限公司 | A kind of set-top box working method, set-top box and computer readable storage medium |
CN107731231A (en) * | 2017-09-15 | 2018-02-23 | 福州瑞芯微电子股份有限公司 | A kind of method for supporting more high in the clouds voice services and a kind of storage device |
CN208013692U (en) * | 2017-12-05 | 2018-10-26 | 厦门日华科技股份有限公司 | A kind of wisdom exhibition room control system based on interactive voice mode |
CN108958698A (en) * | 2018-07-20 | 2018-12-07 | 珠海格力电器股份有限公司 | A kind of method, apparatus, storage medium and terminal for adding equipment |
CN108818569A (en) * | 2018-07-30 | 2018-11-16 | 浙江工业大学 | Intelligent robot system towards public service scene |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107844586A (en) | News recommends method and apparatus | |
CN102160115A (en) | Upstream quality enhancement signal processing for resource constrained client devices | |
US20100146398A1 (en) | Method and system for on-demand narration of a customized story | |
CN109448709A (en) | A kind of terminal throws the control method and terminal of screen | |
CN102160358A (en) | Upstream signal processing for client devices in a small-cell wireless network | |
CN109658935B (en) | Method and system for generating multi-channel noisy speech | |
CN106792013A (en) | A kind of method, the TV interactive for television broadcast sounds | |
CN108337543A (en) | A kind of video broadcasting method, terminal and computer readable storage medium | |
CN107948623A (en) | Projecting apparatus and its music related information display methods | |
CN109920416A (en) | A kind of sound control method, device, storage medium and control system | |
US11822854B2 (en) | Automatic volume adjustment method and apparatus, medium, and device | |
CN110198375A (en) | The way of recording, terminal and computer readable storage medium | |
CN107027053A (en) | Audio frequency playing method, terminal and computer-readable recording medium | |
CN110769355A (en) | Sound effect adjusting method and system of audio equipment and storage medium | |
CN108881996A (en) | Generate and show method, apparatus, equipment and the medium of the sequence of multi-media segment | |
CN110223683A (en) | Voice interactive method and system | |
CN110600021A (en) | Outdoor intelligent voice interaction method, device and system | |
CN106657621A (en) | Sound signal adaptive adjustment device and sound signal adaptive adjustment method | |
CN109300472A (en) | A kind of audio recognition method, device, equipment and medium | |
CN109215688A (en) | With scene audio processing method, device, computer readable storage medium and system | |
CN110459239A (en) | Role analysis method, apparatus and computer readable storage medium based on voice data | |
CN112788489B (en) | Control method and device and electronic equipment | |
CN109413663A (en) | A kind of information processing method and equipment | |
CN112333531A (en) | Audio data playing method and device and readable storage medium | |
CN103685523B (en) | Method and device for processing multimedia data |
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 |
Application publication date: 20190910 |
|
RJ01 | Rejection of invention patent application after publication |