CN107146612A - Voice guide method, device, smart machine and server - Google Patents
Voice guide method, device, smart machine and server Download PDFInfo
- Publication number
- CN107146612A CN107146612A CN201710230097.9A CN201710230097A CN107146612A CN 107146612 A CN107146612 A CN 107146612A CN 201710230097 A CN201710230097 A CN 201710230097A CN 107146612 A CN107146612 A CN 107146612A
- Authority
- CN
- China
- Prior art keywords
- voice
- smart machine
- guiding
- server
- voice messaging
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000002618 waking effect Effects 0.000 claims abstract description 15
- 230000007547 defect Effects 0.000 claims description 21
- 230000005540 biological transmission Effects 0.000 claims description 17
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 230000005611 electricity Effects 0.000 claims 2
- 241000894007 species Species 0.000 description 9
- 240000001417 Vigna umbellata Species 0.000 description 6
- 235000011453 Vigna umbellata Nutrition 0.000 description 6
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000000151 deposition Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the invention discloses voice guide method, device, smart machine and server, method includes:Smart machine receives the voice messaging that user sends;The voice messaging is sent to server, server is parsed to voice messaging, if analysis result meets default guiding conditions, guiding voice is sent to smart machine;Smart machine receives and exports guiding voice;Or, smart machine judges whether in the first preset time period in the case where including wake-up word in detecting voice messaging, receives predetermined number part only comprising the voice messaging for waking up word;If it is, the default guiding voice of output.As can be seen here, in this programme, smart machine output guiding voice is guided to user, improves service quality.
Description
Technical field
The present invention relates to technical field of intelligent equipment, more particularly to a kind of voice guide method, device, smart machine and clothes
Business device.
Background technology
Smart machine brings increasing facility for user, such as, and user can pass through Voice command intelligence
Device plays audio resource, video resource or other multimedia resources.But during using smart machine, user also passes through
Some problems are commonly encountered, such as, user is unfamiliar with functions of the equipments, after equipment is waken up, user does not know that next step needs to hold
What kind of operation of row;Or, the instruction that user is sent by voice can not be recognized by equipment, lead to not meet user's need
Ask;Or some other problem.
Existing smart machine can only could provide the money required for user after the phonetic order of user's specification is recognized
Source or service.If there is above-mentioned scene, otherwise smart machine is waited, otherwise it can not recognize, it is impossible to user is guided, taken
Business is of poor quality.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of voice guide method, device, smart machine and server, with right
User guides, and improves service quality.
It is described applied to smart machine the embodiment of the invention discloses a kind of voice guide method to reach above-mentioned purpose
Method includes:
Receive the voice messaging that user sends;
The voice messaging is sent to server, so that the server is parsed to the voice messaging, if solution
Analysis result meets default guiding conditions, and guiding voice is sent to the smart machine;
Receive and export the guiding voice;
Or, in the case of in detecting the voice messaging comprising word is waken up, judge whether in the first preset time
In section, predetermined number part is received only comprising the voice messaging for waking up word;
If it is, the default guiding voice of output.
Optionally, methods described can also include:
In the case of the feedback of server not being received in the second preset time period, output default guiding voice or pre-
If suggestion voice.
Optionally, it is described do not receive the feedback of server in the second preset time period in the case of, output is default to be carried
The step of showing voice, it can include:
In the case of not receiving the feedback of server in the second preset time period, the defect of the voice messaging is determined
Factor;
In default suggestion voice, target prompting voice of the selection for the defect factors;
Export the target prompting voice.
Optionally, the step of defect factors of the determination voice messaging, can include:
The corresponding each influence factor parameter of the voice messaging is determined, the species of the influence factor is to preset
, one preset range of each influence factor correspondence;
Judge the influence factor parameter whether in its corresponding preset range;
If not, the influence factor to be defined as to the defect factors of the voice messaging.
Optionally, the species of the influence factor include it is following any one or more:
The volume of noise, the volume of the voice messaging, the voice in sound source and the distance of the smart machine, environment
Network where the tone color of information, the word speed of the voice messaging, the corresponding category of language of the voice messaging, the smart machine
Speed.
Optionally, methods described can also include:
At least one guiding voice is included in the fresh information that the reception server is sent, the fresh information;
According to the fresh information, the default guiding voice is updated.
It is described applied to server the embodiment of the invention also discloses a kind of voice guide method to reach above-mentioned purpose
Method includes:
Receive the voice messaging that smart machine is sent;
The voice messaging is parsed;
Judge whether analysis result meets default guiding conditions;
If met, guiding voice is sent to the smart machine, so that the smart machine exports the guiding voice.
Optionally, it is described that the step of whether analysis result meets default guiding conditions judged, it can include:
If analysis result neither corresponds to control instruction, resource request instruction is not corresponded to yet, represents that analysis result meets first
Class presets guiding conditions;
If analysis result correspondence resource request instruction, the target money that the analysis result is asked is searched in resources bank
Source;
If do not found, represent that analysis result meets Equations of The Second Kind and presets guiding conditions;
It is described to send the step of guiding voice to the smart machine, including:
If analysis result, which meets the first kind, presets guiding conditions, first kind guiding voice is sent to the smart machine;
If analysis result, which meets Equations of The Second Kind, presets guiding conditions, Equations of The Second Kind guiding voice is sent to the smart machine.
Optionally, if the analysis result meets the first kind and presets guiding conditions, the first kind is sent to the smart machine
The step of guiding voice, can include:
If analysis result, which meets the first kind, presets guiding conditions, the keyword in analysis result is determined;
In server side the Resources list, the corresponding resource identification of the keyword is searched;
First kind guiding voice is sent to the smart machine, the first kind guiding voice, which is included, to be found at least
One resource identification.
Optionally, if not finding the corresponding resource identification of the keyword, methods described can also include:
The first kind set in advance guiding voice is sent to the smart machine.
Optionally, the server storage has the Resources list and/or feature list;Methods described also includes:
Updated if detecting the Resources list presence, for the Resources list after renewal, it is determined that new guiding voice, is incited somebody to action
The new guiding voice is sent to the smart machine as fresh information;So that the smart machine is believed according to described update
Breath, is updated to the guiding voice set in the smart machine;
And/or,
Updated if detecting the feature list presence, for the feature list after renewal, it is determined that new guiding voice, is incited somebody to action
The new guiding voice is sent to the smart machine as fresh information;So that the smart machine is believed according to described update
Breath, is updated to the guiding voice set in the smart machine.
To reach above-mentioned purpose, the embodiment of the invention also discloses a kind of voice guide device, applied to smart machine, institute
Stating device includes:First receiving module, the first sending module and the first output module;Or including:First receiving module, first
Judge module and the second output module;Or including:First receiving module, the first sending module, the first output module, first are sentenced
Disconnected module and the second output module;Wherein,
First receiving module, the voice messaging for receiving user's transmission;
First sending module, for the voice messaging to be sent into server, so that the server is to the voice
Information is parsed, if analysis result meets default guiding conditions, and guiding voice is sent to the smart machine;
First output module, for receiving and exporting the guiding voice;
First judge module, in the case where including wake-up word in detecting the voice messaging, judging whether
In first preset time period, predetermined number part is received only comprising the voice messaging for waking up word;If it is, triggering second exports mould
Block;
Second output module, for exporting default guiding voice.
Optionally, described device can also include:
3rd output module, in the case of not receiving the feedback of server in the second preset time period, output
Default guiding voice or default suggestion voice.
Optionally, the 3rd output module, can include:
Determination sub-module, in the case of not receiving the feedback of server in the second preset time period, determines institute
State the defect factors of voice messaging;
Submodule is selected, in default suggestion voice, selection to be directed to the target prompting voice of the defect factors;
Output sub-module, for exporting the target prompting voice.
Optionally, the determination sub-module, specifically can be used for:
The corresponding each influence factor parameter of the voice messaging is determined, the species of the influence factor is to preset
, one preset range of each influence factor correspondence;
Judge the influence factor parameter whether in its corresponding preset range;
If not, the influence factor to be defined as to the defect factors of the voice messaging.
Optionally, the species of the influence factor include it is following any one or more:
The volume of noise, the volume of the voice messaging, the voice in sound source and the distance of the smart machine, environment
Network where the tone color of information, the word speed of the voice messaging, the corresponding category of language of the voice messaging, the smart machine
Speed.
Optionally, described device can also include:
At least one is included in second receiving module, the fresh information sent for the reception server, the fresh information
Guide voice;
Update module, for according to the fresh information, being updated to the default guiding voice.
It is described applied to server the embodiment of the invention also discloses a kind of voice guide device to reach above-mentioned purpose
Device includes:
3rd receiving module, the voice messaging for receiving smart machine transmission;
Parsing module, for being parsed to the voice messaging;
Second judge module, for judging whether analysis result meets default guiding conditions;If met, triggering second is sent out
Send module;
Second sending module, for sending guiding voice to the smart machine, so that smart machine output is described
Guide voice.
Optionally, second judge module, specifically can be used for:
If analysis result neither corresponds to control instruction, resource request instruction is not corresponded to yet, represents that analysis result meets first
Class presets guiding conditions;
If analysis result correspondence resource request instruction, the target money that the analysis result is asked is searched in resources bank
Source;
If do not found, represent that analysis result meets Equations of The Second Kind and presets guiding conditions;
Second sending module, can include:
First sending submodule, if meeting the first kind for analysis result presets guiding conditions, sends out to the smart machine
The first kind is sent to guide voice;
Second sending submodule, if meeting Equations of The Second Kind for analysis result presets guiding conditions, sends out to the smart machine
Equations of The Second Kind is sent to guide voice.
Optionally, first sending submodule, specifically can be used for:
If analysis result, which meets the first kind, presets guiding conditions, the keyword in analysis result is determined;
In server side the Resources list, the corresponding resource identification of the keyword is searched;
First kind guiding voice is sent to the smart machine, the first kind guiding voice, which is included, to be found at least
One resource identification.
Optionally, described device can also include:
3rd sending module, in the case where not finding the corresponding resource identification of the keyword, will set in advance
Fixed first kind guiding voice is sent to the smart machine.
Optionally, the server storage has the Resources list and/or feature list;Described device also includes:
4th sending module, for depositing in the case of an update detecting described the Resources list, for the money after renewal
Source list, it is determined that new guiding voice, the smart machine is sent to using the new guiding voice as fresh information;So that
The smart machine is updated according to the fresh information to the guiding voice set in the smart machine;
And/or,
Deposited in the case of an update detecting the feature list, for the feature list after renewal, it is determined that new draws
Lead sound, the smart machine is sent to using the new guiding voice as fresh information;So that the smart machine according to
The fresh information, is updated to the guiding voice set in the smart machine.
To reach above-mentioned purpose, the embodiment of the invention also discloses a kind of smart machine, the smart machine includes:Shell
Body, processor, memory, circuit board and power circuit, wherein, circuit board is placed in the interior volume that housing is surrounded, processor
Set on circuit boards with memory;Power circuit, for being powered for each circuit or device of smart machine;Memory is used for
Store executable program code;The executable program code that processor is stored by reading in memory is run and executable journey
The corresponding program of sequence code, for performing above-mentioned voice guide method.
To reach above-mentioned purpose, the embodiment of the invention also discloses a kind of server, the server includes:Housing, place
Device, memory, circuit board and power circuit are managed, wherein, circuit board is placed in the interior volume that housing is surrounded, processor and storage
Device is set on circuit boards;Power circuit, for being powered for each circuit or device of server;Memory is used to store and can hold
Line program code;The executable program code that processor is stored by reading in memory is run and executable program code pair
The program answered, for performing above-mentioned voice guide method.
Using the embodiment of the present invention, smart machine is received after the voice messaging of user's transmission, and voice messaging is sent to
Server, if after server is parsed to the voice messaging, it is impossible to which obtaining effective information, (analysis result meets default draw
Sliver part), then guiding voice is sent to smart machine, smart machine exports the guiding voice;So, smart machine can to
Family is guided, and improves service quality.Or, if smart machine is repeatedly received only comprising the voice messaging for waking up word,
This represents that user does not know what kind of operation performed after equipment is waken up, in this case, the default guiding of smart machine output
Voice, is guided to user, improves service quality.
Certainly, any product or method for implementing the present invention it is not absolutely required to while reaching all the above excellent
Point.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 illustrates for the first flow of the voice guide method provided in an embodiment of the present invention applied to smart machine
Figure;
Fig. 2 illustrates for second of flow of the voice guide method provided in an embodiment of the present invention applied to smart machine
Figure;
Fig. 3 is a kind of schematic flow sheet of voice guide method applied to server provided in an embodiment of the present invention;
Fig. 4 is the first structural representation of the voice guide device provided in an embodiment of the present invention applied to smart machine
Figure;
Fig. 5 is second of structural representation of the voice guide device provided in an embodiment of the present invention applied to smart machine
Figure;
Fig. 6 is a kind of structural representation of voice guide device applied to server provided in an embodiment of the present invention;
A kind of structural representation for smart machine that Fig. 7 is provided by the embodiment of the present invention;
A kind of structural representation for server that Fig. 8 is provided by the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
In order to solve the above-mentioned technical problem, the embodiments of the invention provide voice guide method, device, smart machine and clothes
A kind of business device, voice guide method and device can apply to various smart machines, such as intelligent sound box, intelligent players, intelligence
Energy robot etc., is not limited specifically;Another voice guide method and device can apply to server, such as cloud service
Device, or other servers.
A kind of voice response method applied to smart machine provided in an embodiment of the present invention is carried out first below detailed
Explanation.
Fig. 1 illustrates for the first flow of the voice guide method provided in an embodiment of the present invention applied to smart machine
Figure, including:
S101:Receive the voice messaging that user sends.
It is appreciated that user can be interacted by voice with smart machine, smart machine can receive user's transmission
Voice messaging.
S102:The voice messaging is sent to server, so that the server is parsed to the voice messaging,
If analysis result meets default guiding conditions, guiding voice is sent to the smart machine.
Can be stored with more rich semantic base in server, and smart machine can receive the voice letter received in S101
Breath is sent to server and parsed.
As a kind of embodiment, the default guiding conditions can be divided into following several situations:
The first, control instruction is neither corresponded to the analysis result of voice messaging, and resource request instruction is not corresponded to yet, this
In the case of, it is believed that analysis result meets the first kind and presets guiding conditions.
In general, the voice messaging that user sends can be " I will listen music ", and " I wants to see a film " etc. asks resource
The information of (audio resource, video resource), this kind of voice messaging correspondence resource request instruction.Or, the voice letter that user sends
Breath can carry the information of control instruction for " broadcasting " " pause " " next " " upper one " etc., and this kind of voice messaging correspondence is controlled
System instruction.
And if analysis result neither corresponds to control instruction, resource request instruction is not corresponded to yet, represent that user may not have
Effective instruction is sent, in this case, it is believed that meet the first kind and preset guiding conditions, the first kind can be sent to smart machine
Guide voice.The first kind guiding voice can be:" if you want to listen music, please said to me ' I wants to listen music ' " or " if
You want to see a film, and please I are said ' I wants to see a film ' " etc., guiding voice here is used to guide user to send effective instruction,
Specific guiding voice is not limited.
Second of situation, if analysis result correspondence resource request instruction, searches the analysis result institute in resources bank
The target resource of request;If do not found, represent that analysis result meets Equations of The Second Kind and presets guiding conditions.
That is, user have issued effective instruction, such as " I wants to listen ' red bean ' ", but do not found in resources bank
" red bean " this song.In this case, it is believed that analysis result meets Equations of The Second Kind and presets guiding conditions, can be sent to smart machine
Equations of The Second Kind guides voice.Equations of The Second Kind guiding voice can be:" I'm it is sorry, this song is not found, but singer * * have gone out newly
* * are sung, you want to hear " or " I'm it is sorry, this song is not found, you can download should in * * APP, * * APP
Have this song " etc., guiding voice here is used to provide the user the mode solved the problems, such as, and specific guiding voice is not limited
It is fixed.
S103:Receive and export received guiding voice.
Server will guide voice to be sent to smart machine, and smart machine exports the guiding voice, user is guided,
Improve service quality.
As a kind of embodiment, if smart machine does not receive the feedback of server in the second preset time period,
Default guiding voice or default suggestion voice can be exported.
The feedback of server is not received, refers to not receive any forms such as resource, instruction, the voice of server transmission
Feedback.In this case, in order to reduce stand-by period of user, improve service quality, smart machine can export its own
Guiding voice and suggestion voice set in advance.
Second preset time period can be set, such as, 1s or 2s according to actual conditions, not limited specifically.
It is emphasized that " guiding voice " is different from " suggestion voice " in the present embodiment, guiding voice has to user to be drawn
The effect lead, educated, can help the function of user's learning intelligence equipment, or provide the user mode solved the problems, such as etc..
And suggestion voice does not have this kind of purposes, suggestion voice can be understood as " not finding resource " or " let down, do not listen
The voice of this class clearly ".
In the present embodiment, guiding voice can be preset in smart machine, similar to " if you want to listen music,
Please I is said ' I wants to listen music ' " etc.;Or, suggestion voice can also be preset in smart machine, similar to " not kindness
Think, do not hear ";Or, guiding voice can also be both set in smart machine, suggestion voice is set again.
Smart machine does not receive the feedback of server in preset time period, and can export guiding voice can also export
Suggestion voice, or, can also the two all export, such as " it is too shy, do not hear, if you want to listen music, please I said
' I wants to listen music ' ".
It should be noted that a variety of guiding voices or a variety of suggestion voices can be preset in smart machine;Intelligence
Equipment can according to itself output rule, this it is a variety of guiding voices or suggestion voice in select this export guiding voice or
Suggestion voice.The output rule can be Sequential output, random output etc., not limit specifically.
As a kind of embodiment, in the case of not receiving the feedback of server in the second preset time period, output
Default suggestion voice, can include:
In the case of not receiving the feedback of server in the second preset time period, the defect of the voice messaging is determined
Factor;In default suggestion voice, target prompting voice of the selection for the defect factors;Export the target prompting language
Sound.
Specifically, determining the defect factors of the voice messaging, it can include:
The corresponding each influence factor parameter of the voice messaging is determined, the species of the influence factor is to preset
, one preset range of each influence factor correspondence;
Judge the influence factor parameter whether in its corresponding preset range;
If not, the influence factor to be defined as to the defect factors of the voice messaging.
The species of above-mentioned influence factor include it is following any one or more:
The volume of noise, the volume of the voice messaging, the voice in sound source and the distance of the smart machine, environment
Network where the tone color of information, the word speed of the voice messaging, the corresponding category of language of the voice messaging, the smart machine
Speed.
As an example it is assumed that the species for presetting influence factor is:In sound source and the distance of the smart machine, environment
The volume of noise, three kinds of the word speed of the voice messaging;Also, this is 0-8m, noise ration pair apart from corresponding preset range
The preset range answered is<50dB, the corresponding preset range of word speed is 90-140 words per minute clocks.
Smart machine does not receive the feedback of server within the advance period, in this case, it is determined that the language received
Message ceases corresponding each influence factor parameter:Assuming that the distance for determining sound source and smart machine is that noise is in 11m, environment
20dB, the word speed of voice messaging is 100 words per minute clocks.
The corresponding preset range of identified each parameter is contrasted, sound source and the distance of smart machine is determined
(11m) in its corresponding preset range (0-8m), the distance of sound source and smart machine is not defined as the defect of the voice messaging
Factor.In other words, smart machine does not receive the feedback of server, it may be possible to make because of user with smart machine away from too far away
Voice messaging is defective, the server None- identified voice messaging.
In this case, smart machine is in default suggestion voice, and selection is directed to the target prompting voice of the defect factors,
Such as " please near from me " or " too remote, please near from me " or other similar suggestion voices.Export the target prompting
Voice.
Using this embodiment, the defect of voice messaging can be directed to, suggestion voice is targetedly exported, effect is pointed out
Fruit is more preferably.
Fig. 2 illustrates for second of flow of the voice guide method provided in an embodiment of the present invention applied to smart machine
Figure, including:
S201:Receive the voice messaging that user sends.
S202:In the case of in detecting the voice messaging comprising word is waken up, judge whether in the first preset time
In section, predetermined number part is received only comprising the voice messaging for waking up word, if it is, performing S203.
S203:The default guiding voice of output.
Parsed it will be understood by those skilled in the art that voice messaging is generally sent to server by smart machine, but
Smart machine can recognize the wake-up word in voice messaging.
Specifically, smart machine can be learnt and be modeled to wake-up word in advance.It will be understood by those skilled in the art that
Voice messaging of the different user for wake-up word can be gathered, these voice messagings are learnt using machine learning algorithm,
And then set up the model for being directed to and waking up word.Such as, it is possible to use wake-up word speech data is trained to deep neural network to be built
Vertical speech recognition modeling, specific learning algorithm is not limited.
The voice messaging got in S201 is input in the model and is identified, if called out in recognition result comprising this
Awake word, then it represents that the wake-up word is included in the voice messaging.
If smart machine receives many parts only comprising the voice messaging for waking up word in preset time period, it may represent to use
Family repeatedly wakes up equipment, and what kind of operation of subsequent execution is not known but, in this case, default leading question can be directly exported
Sound.
It should be noted that the predetermined number can be set according to actual conditions, such as it is set as 3, it is preceding to connect twice
Receive and only may be considered the maloperation of user comprising the voice messaging for waking up word, or other numerical value can also be set as, have
Body is not limited.
First preset time period can be set according to actual conditions, such as, 1 minute or 2 minutes, not done specifically
Limit.
Default guiding voice can be for " if you want to listen music, please saying ' I wants to listen music ' " or " if you think to me
See a film, please I said ' I wants to see a film ' " etc., guiding voice here is used to guide user to send effective instruction, specifically
Guiding voice do not limit.
Using embodiment illustrated in fig. 2 of the present invention, if smart machine is repeatedly received only comprising the voice messaging for waking up word,
This represents that user does not know what kind of operation performed after equipment is waken up, in this case, the default guiding of smart machine output
Voice, is guided to user, improves service quality.
In above-mentioned Fig. 1 embodiment illustrated in fig. 2, the fresh information that smart machine can be sent with the reception server, it is described more
At least one guiding voice is included in fresh information;According to the fresh information, the default guiding voice is updated.
That is, the fresh information that smart machine can be sent according to server, enters to the guiding voice of setting themselves
Row updates.Update mode can be increase, replacement etc., not limit specifically.
The voice guide method applied to server is described in detail below, the server can be cloud server
It can also be other, not limit specifically.
Fig. 3 is a kind of schematic flow sheet of voice guide method applied to server provided in an embodiment of the present invention, bag
Include:
S301:Receive the voice messaging that smart machine is sent.
Described according to content above, smart machine is received after voice messaging, and the voice messaging is sent into server enters
Row parsing.
S302:The voice messaging is parsed.
It will be understood by those skilled in the art that the more rich semantic base that can be stored with server, server can be by
The voice messaging received changes into text message, and text information is matched with the information in semantic base, so that
To analysis result.
S303:Judge whether analysis result meets default guiding conditions;If it is, performing S304.
S304:Guiding voice is sent to the smart machine, so that the smart machine exports the guiding voice.
As a kind of embodiment, the default guiding conditions can be divided into following several situations:
The first, control instruction is neither corresponded to the analysis result of voice messaging, and resource request instruction is not corresponded to yet, this
In the case of, it is believed that analysis result meets the first kind and presets guiding conditions.
In general, the voice messaging that user sends can be " I will listen music ", and " I wants to see a film " etc. asks resource
The information of (audio resource, video resource), this kind of voice messaging correspondence resource request instruction.Or, the voice letter that user sends
Breath can carry the information of control instruction for " broadcasting " " pause " " next " " upper one " etc., and this kind of voice messaging correspondence is controlled
System instruction.
And if analysis result neither corresponds to control instruction, resource request instruction is not corresponded to yet, represent that user may not have
Effective instruction is sent, in this case, it is believed that meet the first kind and preset guiding conditions, the first kind can be sent to smart machine
Guide voice.The first kind guiding voice can be:" if you want to listen music, please said to me ' I wants to listen music ' " or " if
You want to see a film, and please I are said ' I wants to see a film ' " etc., guiding voice here is used to guide user to send effective instruction,
Specific guiding voice is not limited.
Second of situation, the analysis result correspondence resource request instruction to voice messaging, then search the solution in resources bank
The target resource that analysis result is asked;If do not found, represent that analysis result meets Equations of The Second Kind and presets guiding conditions.
That is, user have issued effective instruction, such as " I wants to listen ' red bean ' ", but do not found in resources bank
" red bean " this song.In this case, it is believed that analysis result meets Equations of The Second Kind and presets guiding conditions, can be sent to smart machine
Equations of The Second Kind guides voice.Equations of The Second Kind guiding voice can be:" I'm it is sorry, this song is not found, but singer A has gone out newly
* * are sung, you want to hear " or " I'm it is sorry, this song is not found, you can download should in * * APP, * * APP
Have this song " etc., guiding voice here is used to provide the user the mode solved the problems, such as, and specific guiding voice is not limited
It is fixed.
As a kind of embodiment, if above-mentioned analysis result meets the first kind and presets guiding conditions, determine in analysis result
Keyword;
In server side the Resources list, the corresponding resource identification of the keyword is searched;
First kind guiding voice is sent to the smart machine, the first kind guiding voice, which is included, to be found at least
One resource identification.
Meet the default guiding conditions of the first kind and refer to that analysis result neither corresponds to control instruction, also do not correspond to resource request and refer to
Order, in this case, user may not organize language or by ambient influnence, cause smart machine not to be indexed to complete language
Sound, and then cause server can not parse effective instruction, still, user is possible to say some keywords.Therefore, in parsing
As a result in the case of meeting the default guiding conditions of the first kind, it may be determined that the keyword in analysis result.
Server searches the corresponding resource identification of the keyword, in first kind leading question in server side the Resources list
At least one resource identification found is added in sound.
For example, if including keyword " Wang Fei " in analysis result, server is looked into server side the Resources list
" Wang Fei " corresponding resource identification is looked for, the resource identification can be song title, or Ge Shouming, or other, tool
Body is not limited.
If song title, it is assumed that find " red bean " this song, the first kind guiding voice of transmission can be that " may I ask you
It is intended to listen ' red bean ' this song ".If singer's name, " Wang Fei " this singer, the first kind guiding voice of transmission are found
Can be " may I ask you and be intended to listen the song of ' Wang Fei ' ".
Or, if not finding the corresponding resource identification of the keyword, the first kind set in advance can be guided
Voice is sent to the smart machine.
First kind set in advance guiding voice can be:If " you want to listen music, please say that ' I thinks audition to me
It is happy ' " or " if you want to see a film, please being said to me ' I wants to see a film ' " etc., guiding voice here is used to guide user
Effective instruction is sent, specific guiding voice is not limited.
As a kind of embodiment, be stored with the Resources list in server, if server detects described the Resources list and deposited
Updating, for the Resources list after renewal, it is determined that new guiding voice, the new guiding voice is sent out as fresh information
Give the smart machine;So that the smart machine is according to the fresh information, the guiding to being set in the smart machine
Voice is updated.
Or, be stored with feature list in server, if server detects the feature list and there is renewal, for more
Feature list after new, it is determined that new guiding voice, the intelligence is sent to using the new guiding voice as fresh information
Equipment;So that the smart machine is updated according to the fresh information to the guiding voice set in the smart machine.
Or, be stored with the Resources list and feature list in server:
If server, which detects described the Resources list, has renewal, for the Resources list after renewal, it is determined that new guiding
Voice, the smart machine is sent to using the new guiding voice as fresh information;So that the smart machine is according to institute
Fresh information is stated, the guiding voice set in the smart machine is updated;
If server, which detects the feature list, has renewal, for the feature list after renewal, it is determined that new guiding
Voice, the smart machine is sent to using the new guiding voice as fresh information;So that the smart machine is according to institute
Fresh information is stated, the guiding voice set in the smart machine is updated.
Specifically, for the Resources list after renewal, it is determined that new guiding voice, the new guiding voice can be similar to
" I has increased * * song newly again, and you will hear ", or " I has increased * * film newly again, and you will look at " etc..
For the feature list after renewal, it is determined that new guiding voice, the new guiding voice can be similar to " I am again new
Increase * * functions, you will have a try " etc..
Using embodiment illustrated in fig. 3 of the present invention, smart machine is received after the voice messaging of user's transmission, by voice messaging
Server is sent to, if after server is parsed to the voice messaging, it is impossible to which obtaining effective information, (analysis result meets
Default guiding conditions), then guiding voice is sent to smart machine, smart machine exports the guiding voice;So, smart machine energy
It is enough that user is guided, improve service quality.
Corresponding with above method embodiment, the embodiment of the present invention also provides a kind of voice guide applied to smart machine
Device and a kind of voice guide device applied to server.
Fig. 4 is the first structural representation of the voice guide device provided in an embodiment of the present invention applied to smart machine
Figure, including:
First receiving module 401, the voice messaging for receiving user's transmission;
First sending module 402, for the voice messaging to be sent into server, so that the server is to institute's predicate
Message breath is parsed, if analysis result meets default guiding conditions, and guiding voice is sent to the smart machine;
First output module 403, for receiving and exporting the guiding voice.
As a kind of embodiment, described device can also include:
3rd output module, in the case of not receiving the feedback of server in the second preset time period, output
Default guiding voice or default suggestion voice.
As a kind of embodiment, the 3rd output module can include:
Determination sub-module, in the case of not receiving the feedback of server in the second preset time period, determines institute
State the defect factors of voice messaging;
Submodule is selected, in default suggestion voice, selection to be directed to the target prompting voice of the defect factors;
Output sub-module, for exporting the target prompting voice.
As a kind of embodiment, the determination sub-module specifically can be used for:
The corresponding each influence factor parameter of the voice messaging is determined, the species of the influence factor is to preset
, one preset range of each influence factor correspondence;
Judge the influence factor parameter whether in its corresponding preset range;
If not, the influence factor to be defined as to the defect factors of the voice messaging.
As a kind of embodiment, the species of the influence factor include it is following any one or more:
The volume of noise, the volume of the voice messaging, the voice in sound source and the distance of the smart machine, environment
Network where the tone color of information, the word speed of the voice messaging, the corresponding category of language of the voice messaging, the smart machine
Speed.
As a kind of embodiment, described device can also include:
At least one is included in second receiving module, the fresh information sent for the reception server, the fresh information
Guide voice;
Update module, for according to the fresh information, being updated to the default guiding voice.
Using embodiment illustrated in fig. 4 of the present invention, smart machine is received after the voice messaging of user's transmission, by voice messaging
Server is sent to, if after server is parsed to the voice messaging, it is impossible to which obtaining effective information, (analysis result meets
Default guiding conditions), then guiding voice is sent to smart machine, smart machine exports the guiding voice;So, smart machine energy
It is enough that user is guided, improve service quality.
Fig. 5 is second of structural representation of the voice guide device provided in an embodiment of the present invention applied to smart machine
Figure, including:
First receiving module 501, the voice messaging for receiving user's transmission;
First judge module 502, in the case where including wake-up word in detecting the voice messaging, judging whether
In the first preset time period, predetermined number part is received only comprising the voice messaging for waking up word;If it is, triggering second is exported
Module 503;
Second output module 503, for exporting default guiding voice.
As a kind of embodiment, described device can also include:
At least one is included in second receiving module, the fresh information sent for the reception server, the fresh information
Guide voice;
Update module, for according to the fresh information, being updated to the default guiding voice.
Using embodiment illustrated in fig. 5 of the present invention, if smart machine is repeatedly received only comprising the voice messaging for waking up word,
This represents that user does not know what kind of operation performed after equipment is waken up, in this case, the default guiding of smart machine output
Voice, is guided to user, improves service quality.
Or, the voice guide device can also include the first receiving module, the first hair in embodiment illustrated in fig. 4 simultaneously
The first judge module and the second output module in module, the first output module and embodiment illustrated in fig. 5 are sent, is not limited specifically.
Fig. 6 is a kind of structural representation of voice guide device applied to server provided in an embodiment of the present invention, bag
Include:
3rd receiving module 601, the voice messaging for receiving smart machine transmission;
Parsing module 602, for being parsed to the voice messaging;
Second judge module 603, for judging whether analysis result meets default guiding conditions;If met, triggering the
Two sending modules 604;
Second sending module 604, for sending guiding voice to the smart machine, so that the smart machine exports institute
State guiding voice.
As a kind of embodiment, the second judge module 603 specifically can be used for:
If analysis result neither corresponds to control instruction, resource request instruction is not corresponded to yet, represents that analysis result meets first
Class presets guiding conditions;
If analysis result correspondence resource request instruction, the target money that the analysis result is asked is searched in resources bank
Source;
If do not found, represent that analysis result meets Equations of The Second Kind and presets guiding conditions;
Second sending module 604, can include:
First sending submodule, if meeting the first kind for analysis result presets guiding conditions, sends out to the smart machine
The first kind is sent to guide voice;
Second sending submodule, if meeting Equations of The Second Kind for analysis result presets guiding conditions, sends out to the smart machine
Equations of The Second Kind is sent to guide voice.
As a kind of embodiment, first sending submodule specifically can be used for:
If analysis result, which meets the first kind, presets guiding conditions, the keyword in analysis result is determined;
In server side the Resources list, the corresponding resource identification of the keyword is searched;
First kind guiding voice is sent to the smart machine, the first kind guiding voice, which is included, to be found at least
One resource identification.
As a kind of embodiment, described device can also include:
3rd sending module, in the case where not finding the corresponding resource identification of the keyword, will set in advance
Fixed first kind guiding voice is sent to the smart machine.
As a kind of embodiment, the server storage has the Resources list and/or feature list;Described device is also wrapped
Include:
4th sending module, for depositing in the case of an update detecting described the Resources list, for the money after renewal
Source list, it is determined that new guiding voice, the smart machine is sent to using the new guiding voice as fresh information;So that
The smart machine is updated according to the fresh information to the guiding voice set in the smart machine;
And/or,
Deposited in the case of an update detecting the feature list, for the feature list after renewal, it is determined that new draws
Lead sound, the smart machine is sent to using the new guiding voice as fresh information;So that the smart machine according to
The fresh information, is updated to the guiding voice set in the smart machine.
Using embodiment illustrated in fig. 6 of the present invention, smart machine is received after the voice messaging of user's transmission, by voice messaging
Server is sent to, if after server is parsed to the voice messaging, it is impossible to which obtaining effective information, (analysis result meets
Default guiding conditions), then guiding voice is sent to smart machine, smart machine exports the guiding voice;So, smart machine energy
It is enough that user is guided, improve service quality.
The embodiment of the present invention additionally provides a kind of smart machine, the smart machine as shown in fig. 7, comprises:Housing 701, place
Device 702, memory 703, circuit board 704 and power circuit 705 are managed, wherein, circuit board 704 is placed in the sky that housing 701 is surrounded
Between it is internal, processor 702 and memory 703 are arranged on circuit board 704;Power circuit 705, for each for smart machine
Circuit or device are powered;Memory 703 is used to store executable program code;Processor 702 is deposited by reading in memory 703
The executable program code of storage runs program corresponding with executable program code, for performing the voice guide side
Method, method includes:
Receive the voice messaging that user sends;
The voice messaging is sent to server, so that the server is parsed to the voice messaging, if solution
Analysis result meets default guiding conditions, and guiding voice is sent to the smart machine;
Receive and export the guiding voice;
Or, in the case of in detecting the voice messaging comprising word is waken up, judge whether in the first preset time
In section, predetermined number part is received only comprising the voice messaging for waking up word;
If it is, the default guiding voice of output.
The smart machine can be intelligent sound box, intelligent players, intelligent robot etc., not limit specifically.
Using embodiment illustrated in fig. 7 of the present invention, smart machine is received after the voice messaging of user's transmission, by voice messaging
Server is sent to, if after server is parsed to the voice messaging, it is impossible to which obtaining effective information, (analysis result meets
Default guiding conditions), then guiding voice is sent to smart machine, smart machine exports the guiding voice;So, smart machine energy
It is enough that user is guided, improve service quality.Or, if smart machine is repeatedly received only comprising the voice for waking up word
Information, this represents that user does not know what kind of operation performed after equipment is waken up, and in this case, smart machine output is default
Voice is guided, user is guided, service quality is improved.
The embodiment of the present invention additionally provides a kind of server, the server as shown in figure 8, including:Housing 801, processor
802nd, memory 803, circuit board 804 and power circuit 805, wherein, circuit board 804 is placed in the space that housing 801 is surrounded
Portion, processor 802 and memory 803 are arranged on circuit board 804;Power circuit 805, for each circuit for server or
Device is powered;Memory 803 is used to store executable program code;What processor 802 was stored by reading in memory 803 can
Configuration processor code runs program corresponding with executable program code, for performing the voice guide method, method
Including:
Receive the voice messaging that smart machine is sent;
The voice messaging is parsed;
Judge whether analysis result meets default guiding conditions;
If met, guiding voice is sent to the smart machine, so that the smart machine exports the guiding voice.
The server can for cloud server or other, do not limit specifically.
Using embodiment illustrated in fig. 8 of the present invention, smart machine is received after the voice messaging of user's transmission, by voice messaging
Server is sent to, if after server is parsed to the voice messaging, it is impossible to which obtaining effective information, (analysis result meets
Default guiding conditions), then guiding voice is sent to smart machine, smart machine exports the guiding voice;So, smart machine energy
It is enough that user is guided, improve service quality.
It is noted that herein, such as first and second or the like relational terms are used merely to an entity
Or operation makes a distinction with another entity or operation, and not necessarily require or imply exist between these entities or operation
Any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant be intended to it is non-
It is exclusive to include, so that process, method, article or equipment including a series of key elements not only include those key elements,
But also other key elements including being not expressly set out, or also include solid by this process, method, article or equipment
Some key elements.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including
Also there is other identical element in process, method, article or the equipment of the key element.
Each embodiment in this specification is described by the way of related, identical similar portion between each embodiment
Divide mutually referring to what each embodiment was stressed is the difference with other embodiment.It is real especially for device
Apply for example, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
Can one of ordinary skill in the art will appreciate that realizing that all or part of step in above method embodiment is
To instruct the hardware of correlation to complete by program, described program can be stored in computer read/write memory medium,
The storage medium designated herein obtained, such as:ROM/RAM, magnetic disc, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent substitution and improvements made within the spirit and principles in the present invention etc., are all contained in protection scope of the present invention
It is interior.
Claims (10)
1. a kind of voice guide method, it is characterised in that applied to smart machine, methods described includes:
Receive the voice messaging that user sends;
The voice messaging is sent to server, so that the server is parsed to the voice messaging, if parsing knot
Fruit meets default guiding conditions, and guiding voice is sent to the smart machine;
Receive and export the guiding voice;
Or, in the case of in detecting the voice messaging comprising word is waken up, judge whether in the first preset time period,
Predetermined number part is received only comprising the voice messaging for waking up word;
If it is, the default guiding voice of output.
2. according to the method described in claim 1, it is characterised in that methods described also includes:
In the case of not receiving the feedback of server in the second preset time period, output is preset guiding voice or preset and carries
Show voice.
3. method according to claim 2, it is characterised in that described not receive server in the second preset time period
Feedback in the case of, the step of output default suggestion voice, including:
In the case of not receiving the feedback of server in the second preset time period, determine the defect of the voice messaging because
Element;
In default suggestion voice, target prompting voice of the selection for the defect factors;
Export the target prompting voice.
4. method according to claim 3, it is characterised in that the step of the defect factors of the determination voice messaging
Suddenly, including:
Determine the corresponding each influence factor parameter of the voice messaging, the species of the influence factor be it is set in advance, often
One preset range of individual influence factor correspondence;
Judge the influence factor parameter whether in its corresponding preset range;
If not, the influence factor to be defined as to the defect factors of the voice messaging.
5. method according to claim 4, it is characterised in that the species of the influence factor include it is following any one or
It is a variety of:
The volume of noise, the volume of the voice messaging, the voice messaging in sound source and the distance of the smart machine, environment
Tone color, the word speed of the voice messaging, the corresponding category of language of the voice messaging, the speed of network where the smart machine
Degree.
6. a kind of voice guide method, it is characterised in that applied to server, methods described includes:
Receive the voice messaging that smart machine is sent;
The voice messaging is parsed;
Judge whether analysis result meets default guiding conditions;
If met, guiding voice is sent to the smart machine, so that the smart machine exports the guiding voice.
7. a kind of voice guide device, it is characterised in that applied to smart machine, described device includes:First receiving module,
One sending module and the first output module;Or including:First receiving module, the first judge module and the second output module;Or
Person includes:First receiving module, the first sending module, the first output module, the first judge module and the second output module;Its
In,
First receiving module, the voice messaging for receiving user's transmission;
First sending module, for the voice messaging to be sent into server, so that the server is to the voice messaging
Parsed, if analysis result meets default guiding conditions, guiding voice is sent to the smart machine;
First output module, for receiving and exporting the guiding voice;
First judge module, in the case where including wake-up word in detecting the voice messaging, judging whether first
In preset time period, predetermined number part is received only comprising the voice messaging for waking up word;If it is, the second output module of triggering;
Second output module, for exporting default guiding voice.
8. a kind of voice guide device, it is characterised in that applied to server, described device includes:
3rd receiving module, the voice messaging for receiving smart machine transmission;
Parsing module, for being parsed to the voice messaging;
Second judge module, for judging whether analysis result meets default guiding conditions;If met, triggering second sends mould
Block;
Second sending module, for sending guiding voice to the smart machine, so that the smart machine exports the guiding
Voice.
9. a kind of smart machine, it is characterised in that the smart machine includes:Housing, processor, memory, circuit board and electricity
Source circuit, wherein, circuit board is placed in the interior volume that housing is surrounded, and processor and memory are set on circuit boards;Power supply
Circuit, for being powered for each circuit or device of smart machine;Memory is used to store executable program code;Processor leads to
Cross and read in memory the executable program code that stores to run program corresponding with executable program code, for performing
Voice guide method described in claim any one of 1-5.
10. a kind of server, it is characterised in that the server includes:Housing, processor, memory, circuit board and power supply electricity
Road, wherein, circuit board is placed in the interior volume that housing is surrounded, and processor and memory are set on circuit boards;Power circuit,
For being powered for each circuit or device of server;Memory is used to store executable program code;Processor is by reading
The executable program code stored in memory runs program corresponding with executable program code, will for perform claim
Seek the voice guide method described in 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710230097.9A CN107146612B (en) | 2017-04-10 | 2017-04-10 | Voice guidance method and device, intelligent equipment and server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710230097.9A CN107146612B (en) | 2017-04-10 | 2017-04-10 | Voice guidance method and device, intelligent equipment and server |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107146612A true CN107146612A (en) | 2017-09-08 |
CN107146612B CN107146612B (en) | 2020-05-15 |
Family
ID=59773656
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710230097.9A Active CN107146612B (en) | 2017-04-10 | 2017-04-10 | Voice guidance method and device, intelligent equipment and server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107146612B (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108022082A (en) * | 2017-12-18 | 2018-05-11 | 北京三快在线科技有限公司 | Business bootstrap technique, device, system, server and electronic equipment |
CN108320742A (en) * | 2018-01-31 | 2018-07-24 | 广东美的制冷设备有限公司 | Voice interactive method, smart machine and storage medium |
CN108520748A (en) * | 2018-02-01 | 2018-09-11 | 百度在线网络技术(北京)有限公司 | A kind of smart machine functional guide and system |
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 |
CN109545206A (en) * | 2018-10-29 | 2019-03-29 | 百度在线网络技术(北京)有限公司 | Voice interaction processing method, device and the smart machine of smart machine |
CN109545207A (en) * | 2018-11-16 | 2019-03-29 | 广东小天才科技有限公司 | A kind of voice awakening method and device |
CN109727597A (en) * | 2019-01-08 | 2019-05-07 | 未来电视有限公司 | The interaction householder method and device of voice messaging |
CN109827590A (en) * | 2019-01-11 | 2019-05-31 | 北京猎户星空科技有限公司 | A kind of control method of robot, device, equipment and medium |
CN109903760A (en) * | 2019-01-02 | 2019-06-18 | 百度在线网络技术(北京)有限公司 | Voice interactive method, device and storage medium |
CN109901899A (en) * | 2019-01-28 | 2019-06-18 | 百度在线网络技术(北京)有限公司 | Video speech technical ability processing method, device, equipment and readable storage medium storing program for executing |
CN109976829A (en) * | 2019-03-18 | 2019-07-05 | 百度在线网络技术(北京)有限公司 | A kind of voice technical ability signal language configuration method and device |
CN110096249A (en) * | 2018-01-31 | 2019-08-06 | 阿里巴巴集团控股有限公司 | Methods, devices and systems for prompting fast to wake up word |
CN110503938A (en) * | 2019-08-30 | 2019-11-26 | 北京太极华保科技股份有限公司 | The recognition methods of machine conversational language and device, identification engine switching method and device |
CN111661065A (en) * | 2019-03-07 | 2020-09-15 | 本田技研工业株式会社 | Agent device, control method for agent device, and storage medium |
CN112114770A (en) * | 2019-06-19 | 2020-12-22 | 百度在线网络技术(北京)有限公司 | Interface guiding method, device and equipment based on voice interaction |
CN112579032A (en) * | 2019-09-27 | 2021-03-30 | 百度在线网络技术(北京)有限公司 | Intelligent equipment guiding method and device |
CN112735391A (en) * | 2020-12-29 | 2021-04-30 | 科大讯飞股份有限公司 | Distributed voice response method and related device |
CN113555016A (en) * | 2021-06-24 | 2021-10-26 | 北京房江湖科技有限公司 | Voice interaction method, electronic equipment and readable storage medium |
CN114115790A (en) * | 2021-11-12 | 2022-03-01 | 上汽通用五菱汽车股份有限公司 | Voice conversation prompting method, device, equipment and computer readable storage medium |
WO2022234930A1 (en) * | 2021-05-06 | 2022-11-10 | 삼성전자 주식회사 | Electronic device for providing update information via artificial intelligent (ai) agent service |
CN112735391B (en) * | 2020-12-29 | 2024-05-31 | 科大讯飞股份有限公司 | Distributed voice response method and related device |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103517147A (en) * | 2012-06-14 | 2014-01-15 | 三星电子株式会社 | Display apparatus, interactive server, and method for providing response information |
CN103533021A (en) * | 2012-07-03 | 2014-01-22 | 三星电子株式会社 | Display apparatus, interactive system and method for providing response information |
EP2806422A1 (en) * | 2013-05-21 | 2014-11-26 | Samsung Electronics Co., Ltd | Voice recognition apparatus, voice recognition server and voice recognition guide method |
CN105607887A (en) * | 2014-11-17 | 2016-05-25 | 三星电子株式会社 | Voice recognition system, server, display apparatus and control methods thereof |
CN105702254A (en) * | 2012-05-24 | 2016-06-22 | 上海博泰悦臻电子设备制造有限公司 | Voice control system based on mobile terminal and voice control method thereof |
CN106297782A (en) * | 2016-07-28 | 2017-01-04 | 北京智能管家科技有限公司 | A kind of man-machine interaction method and system |
US20170004826A1 (en) * | 2014-06-11 | 2017-01-05 | Honeywell International Inc. | Adaptive beam forming devices, methods, and systems |
CN106462380A (en) * | 2014-04-15 | 2017-02-22 | 谷歌公司 | Systems and methods for providing prompts for voice commands |
JP6100326B2 (en) * | 2015-07-15 | 2017-03-22 | ソフトバンク株式会社 | Automatic voice response system |
CN106548773A (en) * | 2016-11-04 | 2017-03-29 | 百度在线网络技术(北京)有限公司 | Child user searching method and device based on artificial intelligence |
-
2017
- 2017-04-10 CN CN201710230097.9A patent/CN107146612B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105702254A (en) * | 2012-05-24 | 2016-06-22 | 上海博泰悦臻电子设备制造有限公司 | Voice control system based on mobile terminal and voice control method thereof |
CN103517147A (en) * | 2012-06-14 | 2014-01-15 | 三星电子株式会社 | Display apparatus, interactive server, and method for providing response information |
CN103533021A (en) * | 2012-07-03 | 2014-01-22 | 三星电子株式会社 | Display apparatus, interactive system and method for providing response information |
EP2806422A1 (en) * | 2013-05-21 | 2014-11-26 | Samsung Electronics Co., Ltd | Voice recognition apparatus, voice recognition server and voice recognition guide method |
CN106462380A (en) * | 2014-04-15 | 2017-02-22 | 谷歌公司 | Systems and methods for providing prompts for voice commands |
US20170004826A1 (en) * | 2014-06-11 | 2017-01-05 | Honeywell International Inc. | Adaptive beam forming devices, methods, and systems |
CN105607887A (en) * | 2014-11-17 | 2016-05-25 | 三星电子株式会社 | Voice recognition system, server, display apparatus and control methods thereof |
JP6100326B2 (en) * | 2015-07-15 | 2017-03-22 | ソフトバンク株式会社 | Automatic voice response system |
CN106297782A (en) * | 2016-07-28 | 2017-01-04 | 北京智能管家科技有限公司 | A kind of man-machine interaction method and system |
CN106548773A (en) * | 2016-11-04 | 2017-03-29 | 百度在线网络技术(北京)有限公司 | Child user searching method and device based on artificial intelligence |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108022082A (en) * | 2017-12-18 | 2018-05-11 | 北京三快在线科技有限公司 | Business bootstrap technique, device, system, server and electronic equipment |
CN110096249A (en) * | 2018-01-31 | 2019-08-06 | 阿里巴巴集团控股有限公司 | Methods, devices and systems for prompting fast to wake up word |
CN108320742A (en) * | 2018-01-31 | 2018-07-24 | 广东美的制冷设备有限公司 | Voice interactive method, smart machine and storage medium |
CN108520748A (en) * | 2018-02-01 | 2018-09-11 | 百度在线网络技术(北京)有限公司 | A kind of smart machine functional guide and system |
US10937423B2 (en) | 2018-02-01 | 2021-03-02 | Baidu Online Network Technology (Beijing) Co., Ltd. | Smart device function guiding method and system |
JP2019133634A (en) * | 2018-02-01 | 2019-08-08 | バイドゥ オンライン ネットワーク テクノロジー (ベイジン) カンパニー リミテッド | Smart device function guiding method and system |
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 |
CN109545206A (en) * | 2018-10-29 | 2019-03-29 | 百度在线网络技术(北京)有限公司 | Voice interaction processing method, device and the smart machine of smart machine |
CN109545206B (en) * | 2018-10-29 | 2024-01-30 | 百度在线网络技术(北京)有限公司 | Voice interaction processing method and device of intelligent equipment and intelligent equipment |
CN109545207A (en) * | 2018-11-16 | 2019-03-29 | 广东小天才科技有限公司 | A kind of voice awakening method and device |
CN109903760A (en) * | 2019-01-02 | 2019-06-18 | 百度在线网络技术(北京)有限公司 | Voice interactive method, device and storage medium |
CN109727597A (en) * | 2019-01-08 | 2019-05-07 | 未来电视有限公司 | The interaction householder method and device of voice messaging |
CN109827590A (en) * | 2019-01-11 | 2019-05-31 | 北京猎户星空科技有限公司 | A kind of control method of robot, device, equipment and medium |
CN109901899A (en) * | 2019-01-28 | 2019-06-18 | 百度在线网络技术(北京)有限公司 | Video speech technical ability processing method, device, equipment and readable storage medium storing program for executing |
CN111661065A (en) * | 2019-03-07 | 2020-09-15 | 本田技研工业株式会社 | Agent device, control method for agent device, and storage medium |
CN111661065B (en) * | 2019-03-07 | 2024-02-13 | 本田技研工业株式会社 | Agent device, method for controlling agent device, and storage medium |
CN109976829A (en) * | 2019-03-18 | 2019-07-05 | 百度在线网络技术(北京)有限公司 | A kind of voice technical ability signal language configuration method and device |
CN112114770A (en) * | 2019-06-19 | 2020-12-22 | 百度在线网络技术(北京)有限公司 | Interface guiding method, device and equipment based on voice interaction |
CN110503938A (en) * | 2019-08-30 | 2019-11-26 | 北京太极华保科技股份有限公司 | The recognition methods of machine conversational language and device, identification engine switching method and device |
CN112579032B (en) * | 2019-09-27 | 2023-10-03 | 百度在线网络技术(北京)有限公司 | Intelligent device guiding method and device |
CN112579032A (en) * | 2019-09-27 | 2021-03-30 | 百度在线网络技术(北京)有限公司 | Intelligent equipment guiding method and device |
CN112735391A (en) * | 2020-12-29 | 2021-04-30 | 科大讯飞股份有限公司 | Distributed voice response method and related device |
CN112735391B (en) * | 2020-12-29 | 2024-05-31 | 科大讯飞股份有限公司 | Distributed voice response method and related device |
WO2022234930A1 (en) * | 2021-05-06 | 2022-11-10 | 삼성전자 주식회사 | Electronic device for providing update information via artificial intelligent (ai) agent service |
CN113555016A (en) * | 2021-06-24 | 2021-10-26 | 北京房江湖科技有限公司 | Voice interaction method, electronic equipment and readable storage medium |
CN114115790A (en) * | 2021-11-12 | 2022-03-01 | 上汽通用五菱汽车股份有限公司 | Voice conversation prompting method, device, equipment and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107146612B (en) | 2020-05-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107146612A (en) | Voice guide method, device, smart machine and server | |
CN109410927B (en) | Voice recognition method, device and system combining offline command word and cloud analysis | |
CN107145329A (en) | Apparatus control method, device and smart machine | |
CN108958810A (en) | A kind of user identification method based on vocal print, device and equipment | |
US9053704B2 (en) | System and method for standardized speech recognition infrastructure | |
CN107147618A (en) | A kind of user registering method, device and electronic equipment | |
US20220076674A1 (en) | Cross-device voiceprint recognition | |
CN109949783A (en) | Song synthetic method and system | |
JP6783339B2 (en) | Methods and devices for processing audio | |
CN108469966A (en) | Voice broadcast control method and device, intelligent device and medium | |
CN105159977A (en) | Information interaction processing method and apparatus | |
CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
CN110459222A (en) | Sound control method, phonetic controller and terminal device | |
CN111462741B (en) | Voice data processing method, device and storage medium | |
CN107909998A (en) | Phonetic order processing method, device, computer equipment and storage medium | |
CN111178081B (en) | Semantic recognition method, server, electronic device and computer storage medium | |
CN104898821B (en) | The method and electronic equipment of a kind of information processing | |
CN111933108A (en) | Automatic testing method for intelligent voice interaction system of intelligent network terminal | |
CN112735418B (en) | Voice interaction processing method, device, terminal and storage medium | |
CN108986805A (en) | Method and apparatus for sending information | |
CN108614851A (en) | Notes content display methods in tutoring system and device | |
CN106239506A (en) | The multi-modal input data processing method of intelligent robot and robot operating system | |
CN109376363A (en) | A kind of real-time voice interpretation method and device based on earphone | |
CN109920429A (en) | It is a kind of for vehicle-mounted voice recognition data processing method and system | |
CN111144132B (en) | Semantic recognition method and device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |