CN107452386A - A kind of voice data processing method and system - Google Patents
A kind of voice data processing method and system Download PDFInfo
- Publication number
- CN107452386A CN107452386A CN201710703578.7A CN201710703578A CN107452386A CN 107452386 A CN107452386 A CN 107452386A CN 201710703578 A CN201710703578 A CN 201710703578A CN 107452386 A CN107452386 A CN 107452386A
- Authority
- CN
- China
- Prior art keywords
- speech data
- electronic equipment
- distance
- voice assistant
- multiple electronic
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 230000005540 biological transmission Effects 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000001755 vocal effect Effects 0.000 claims description 25
- 230000005611 electricity Effects 0.000 claims description 6
- 230000002452 interceptive effect Effects 0.000 description 11
- 241001269238 Data Species 0.000 description 4
- 108091064702 1 family Proteins 0.000 description 1
- 230000018199 S phase Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 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
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a kind of voice data processing method and system, method includes：Obtain the voice assistant for the multiple electronic equipments for belonging to same group while the speech data sent；Determine the sender with speech data at a distance of nearest target electronic device from the multiple electronic equipment；The voice assistant of the target electronic device is controlled to respond the speech data；As can be seen here, in the present invention, when the voice assistant of multiple electronic equipments receives the speech data of user's transmission, only the speech data can be just responded at a distance of the voice assistant of nearest target electronic device with user, it is manually operated without user, improve Consumer's Experience.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of voice data processing method and it is
System.
Background technology
At present, most of electronic equipments, such as mobile phone, intelligent sound, intelligent television all support voice assistant, voice assistant
With realizing the functions such as Voice command, information inquiry by interactive voice mode.
In the case where the voice assistant of electronic equipment is in wake-up states, interactive voice can be carried out.
As a kind of application scenarios, when user wants to carry out interactive voice with an electronic equipment, if user is at one's side
When voice assistant on multiple electronic equipments is in wake-up states, then the plurality of electronic equipment can be believed the voice of user
Breath responds, it is clear that is disagreed with the original idea of user.When this occurs, user needs to control other electronic equipments
Voice assistant exits wake-up states, cumbersome, reduces Consumer's Experience.
The content of the invention
In view of this, the present invention provides a kind of voice data processing method and system, to simplify user's operation, improves user
Experience.
To achieve the above object, the present invention provides following technical scheme：
A kind of voice data processing method, including：
Obtain the voice assistant for the multiple electronic equipments for belonging to same group while the speech data sent；
Determine the sender with speech data at a distance of nearest target electronic device from the multiple electronic equipment；
The voice assistant of the target electronic device is controlled to respond the speech data.
Preferably, in addition to：
Judge whether the multiple electronic equipment is located at consolidated network；
Accordingly, it is described to be determined from the multiple electronic equipment with the sender of speech data at a distance of nearest target electricity
Sub- equipment, including：
It is subordinated to and is determined in multiple electronic equipments of consolidated network with the sender of speech data at a distance of nearest target electricity
Sub- equipment.
Preferably, in addition to：
Judge the voice assistant of the multiple electronic equipment while whether the speech data sent belongs to same vocal print；
Accordingly, it is described to be determined from the multiple electronic equipment with the sender of speech data at a distance of nearest target electricity
Sub- equipment, including：
Belong to from speech data in multiple electronic equipments of same vocal print and determine the sender with speech data at a distance of nearest
Target electronic device.
Preferably, in addition to：
If it is not, the voice assistant of the multiple electronic equipment is controlled to respond the speech data respectively.
Preferably, determine to set at a distance of nearest target electronic with the sender of speech data from the multiple electronic equipment
It is standby, including：
Receive the distance parameter that the multiple electronic equipment is sent respectively；Wherein, the distance parameter is electronic equipment base
Its determined in the attribute information of speech data is the distance between with the sender of speech data；
Determine that the minimum electronic equipment of distance parameter is target electronic device.
Preferably, determine to set at a distance of nearest target electronic with the sender of speech data from the multiple electronic equipment
It is standby, including：
Obtain the attribute information of the speech data；
Determine that the attribute information meets that the electronic equipment of preparatory condition is target electronic device.
A kind of voice data processing system, including：
Multiple electronic equipments, have been separately operable voice assistant, for gathering speech data by the voice assistant；
Server, for the voice number for obtaining the voice assistant for the multiple electronic equipments for belonging to same group while sending
According to being determined from the multiple electronic equipment with the sender of speech data at a distance of nearest target electronic device, described in control
The voice assistant of target electronic device responds the speech data.
Preferably, the server is additionally operable to judge whether the multiple electronic equipment is located at consolidated network, and specifically uses
Determine the sender with speech data at a distance of nearest target electronic device in the multiple electronic equipments for be subordinated to consolidated network.
Preferably, institute's predicate that the server is additionally operable to judge the voice assistant of the multiple electronic equipment while sent
Whether sound data belong to same vocal print, and determined in multiple electronic equipments specifically for belonging to same vocal print from speech data with
The sender of speech data is at a distance of nearest target electronic device.
Preferably, the electronic equipment determines itself and the speech data for the attribute information based on the speech data
The distance between sender parameter；
The server is specifically used for receiving the distance parameter that the multiple electronic equipment is sent respectively, determines distance parameter
Minimum electronic equipment is target electronic device.
Preferably, the server is specifically used for the attribute information for obtaining the speech data, determines the attribute information
The electronic equipment for meeting preparatory condition is target electronic device.
Understood via above-mentioned technical scheme, compared with prior art, at a kind of speech data
Reason method, including：The speech data of the voice assistant transmission simultaneously for the multiple electronic equipments for belonging to same group is received, from multiple
Determine the sender with speech data at a distance of nearest target electronic device, the voice of control targe electronic equipment in electronic equipment
Assistant responds the speech data；As can be seen here, in the present invention, when the voice assistant of multiple electronic equipments receives user's hair
During the speech data sent, the speech data can be just only responded at a distance of the voice assistant of nearest target electronic device with user,
It is manually operated without user, improve Consumer's Experience.
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 required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of voice data processing method disclosed in one embodiment of the invention；
Fig. 2 is a kind of structural representation of the application scenarios of voice data processing method disclosed in one embodiment of the invention
Figure；
Fig. 3 is a kind of schematic flow sheet of voice data processing method disclosed in another embodiment of the present invention；
Fig. 4 is a kind of schematic flow sheet of voice data processing method disclosed in further embodiment of this invention；
Fig. 5 is a kind of structural representation of voice-data system disclosed in one embodiment of the 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 describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
One embodiment of the invention discloses a kind of voice data processing method, as shown in figure 1, this method includes following step
Suddenly：
Step 101：Obtain the voice assistant for the multiple electronic equipments for belonging to same group while the speech data sent；
A kind of data processing method in the application can apply in server, and server is used to receive electronic equipment
The speech data that voice assistant is sent, when the speech data that the voice assistant for receiving multiple electronic equipments is sent, determine
Belong to the voice assistant of multiple electronic equipments of same group while the speech data sent.
It should be understood that the implication of " simultaneously " is synchronization, but due to the factors such as network delay be present, in of the invention
To may refer to " simultaneously " be the time difference in preset time, and preset time is especially short, such as 0.5 second, 1 second.For example, two
The time difference for the speech data that individual electronic equipment voice assistant is sent is at a distance of 1 second it can be assumed that sent out for two electronic equipments simultaneously
Speech data is sent.
Optionally, the speech data sent simultaneously for the voice assistant of multiple electronic equipments of reception, need to determine to belong to
In the speech data that the voice assistant of multiple electronic equipments of same group is sent simultaneously, wherein it is possible to pass through electronic equipment
Identity determines its affiliated group, and the electronic equipment with common identity mark belongs to same group.The identity can
That thinks user's setting is used to characterize the mark that multiple electronic equipments belong to same holder, and the specific implementation form present invention is not
Limit.
It should be noted that the identity of electronic equipment may refer to the identity for electronic equipment in itself, can also
It is referred to as the identity of the voice assistant of electronic equipment.
Wherein, the voice assistant of electronic equipment can carry identity when sending speech data to server, certainly
The identity of each electronic equipment can also be stored in the server in advance so that server carries out drawing for group in advance
Point.
Step 102：Determine the sender with speech data at a distance of nearest target electronic device from multiple electronic equipments；
In actual applications, when user wants to carry out interactive voice with electronic equipment, typically can close to the electronic equipment,
That is, if user has multiple electronic equipments at one's side, then, the user wants to carry out the electronic equipment of interactive voice from it
It is closest.Therefore, in the application, sender's phase with speech data can be determined from multiple electronic equipments by server
Away from nearest target electronic device.
Wherein, it is at a distance of most with the sender of speech data that at least one electronic equipment is determined from multiple electronic equipments
Near target electronic device.
Optionally, in one embodiment, determine the sender with speech data at a distance of nearest from multiple electronic equipments
Target electronic device, including procedure below：
(1) distance parameter that multiple electronic equipments are sent respectively is received；
Wherein, distance parameter is its transmission with speech data that attribute information of the electronic equipment based on speech data determines
The distance between person.
The attribute information for the speech data that electronic equipment is gathered based on voice assistant calculates its sender with speech data
The distance between parameter, and send it to server.It should be noted that electronic equipment can carry the distance parameter
Server is transmitted directly in speech data, or, distance parameter is individually sent to server.
The attribute information of speech data includes one or more of following parameter：Signal to noise ratio parameter, energy intensity.Electronics
Equipment is previously stored with the corresponding relation of different attribute informations and distance parameter, from the corresponding relation prestored search with
Distance parameter corresponding to the attribute information of speech data, and send it to server.
(2) determine that the minimum electronic equipment of distance parameter is target electronic device.
After server receives the distance parameter of electronic equipment transmission, it is subordinated in multiple electronic equipments of same group really
It is target electronic device to make the minimum electronic equipment of distance parameter.
Optionally, in another embodiment, determined from multiple electronic equipments with the sender of speech data at a distance of most
Near target electronic device, including procedure below：
(1) attribute information of the speech data is obtained；
After the speech data that the voice assistant for receiving electronic equipment is sent, the attribute information of the speech data is determined,
The attribute information of speech data includes one or more of following parameter：Signal to noise ratio parameter, energy intensity.
(2) determine that the attribute information meets that the electronic equipment of preparatory condition is target electronic device.
, can be by the speech data of the voice assistant transmission of multiple electronic equipments of same group in a kind of implementation
Attribute information is contrasted, and determines that attribute information meets that the electronic equipment of preparatory condition is target electronic device, wherein, this is pre-
If condition is the distance between the sender for determining electronic equipment and speech data nearest condition.In one embodiment
In, when attribute information is signal to noise ratio parameter, preparatory condition is signal to noise ratio optimal conditions in multiple speech datas；Work as attribute
When information is energy intensity, preparatory condition is the most strong condition of energy intensity in multiple speech datas.Using attribute information as noise
Exemplified by parameter, determined in the attribute information for the speech data that need to be sent from the voice assistant of multiple electronic equipments of same group
It is target electronic device to go out the optimal electronic equipment of signal to noise ratio.
, can be by the speech data of the voice assistant transmission of multiple electronic equipments of same group in another implementation
Attribute information compared with a default attribute information, it is determined that the electronic equipment for meeting default attribute information is target
Electronic equipment.
Step 103：The voice assistant voice responsive data of control targe electronic equipment.
The target electronic device be with the sender of speech data at a distance of nearest electronic equipment, as user want and its
The electronic equipment of interactive voice is carried out, therefore control targe electronic equipment voice assistant responds the speech data.
The embodiments of the invention provide a kind of data processing method, including：Multiple electronics that reception belongs to same group are set
The speech data that standby voice assistant is sent simultaneously, determine the sender with speech data at a distance of nearest from multiple electronic equipments
Target electronic device, the voice assistant of control targe electronic equipment responds the speech data；As can be seen here, in the present invention,
When the voice assistant of multiple electronic equipments receives the speech data of user's transmission, only with user at a distance of nearest target
The voice assistant of electronic equipment can just respond the speech data, manually operated without user, improve Consumer's Experience.
Under an application scenarios, as shown in Fig. 2 server 100 receives voice assistant, the electricity of electronic equipment 201 respectively
The speech data that the voice assistant of sub- equipment 202 and the voice assistant of electronic equipment 203 are sent simultaneously, determines electronic equipment
201 and electronic equipment 202 belong to same group, so as to determining electronic equipment from electronic equipment 201 and electronic equipment 202
201 is closest with speech data sender, then, then the voice assistant of control electronics 201 responds its voice assistant
The speech data of transmission, and forbid electronic equipment 202 to respond the speech data that its voice assistant is sent.Due to electronic equipment 203
Belong to different groups from electronic equipment 201 and electronic equipment 202, then also control electronics 203 respond its voice assistant
The speech data of transmission.
That is, under above-mentioned scene, user has electronic equipment 201 and electronic equipment 202 at one's side, and user wants
Interactive voice is carried out with electronic equipment 201, because the voice assistant of electronic equipment 201 and the voice assistant of electronic equipment 202 are equal
In wake-up states, therefore, the voice assistant of electronic equipment 201 and the voice assistant of electronic equipment 202 can receive this
Speech data, and send it to server.
Another embodiment of the present invention discloses a kind of voice data processing method, as shown in figure 3, this method includes following step
Suddenly：
Step 301：Obtain the voice assistant for the multiple electronic equipments for belonging to same group while the speech data sent；
Step 302：Judge whether the multiple electronic equipment is located at consolidated network, if so, into step 303；It is such as no, enter
Enter step 305；
Specifically, the plurality of electronic equipment is referred to as belonging to same group and its voice assistant is sent to server simultaneously
The electronic equipment of speech data, by judging whether the plurality of electronic equipment is located at consolidated network to determine the plurality of electronic equipment
It is whether co-located, if located in consolidated network, determining that the plurality of electronic equipment is co-located, if located in not
With in network, determining that the plurality of electronic equipment is located at different positions.
Optionally, can based on electronic equipment network address or network identity come determine the plurality of electronic equipment whether position
In consolidated network, there is same network address or the electronic equipment of identical network mark to be located at consolidated network, there are heterogeneous networks
The electronic equipment of address or heterogeneous networks mark is located at heterogeneous networks.
Step 303：It is subordinated in multiple electronic equipments of consolidated network and determines with the sender of speech data at a distance of most
Near target electronic device；
The multiple electronic equipments for belonging to consolidated network are located at same position, and the speech data that its voice assistant is gathered is by same
One sender sends, and therefore, is subordinated in multiple electronic equipments of consolidated network and determines with the sender of speech data apart
Nearest target electronic device.
Step 304：The voice assistant of control targe electronic equipment responds the speech data；
Step 305：The voice assistant for the multiple electronic equipments for belonging to heterogeneous networks is controlled to respond the speech data respectively.
Because the electronic equipment for belonging to heterogeneous networks is located at diverse location, therefore, even if the voice of the plurality of electronic equipment
Assistant is while sends speech data to server, belongs to same group, the language that the voice assistant of each electronic equipment is received
Sound data are nor what same sender sent.
As an application scenarios, electronic equipment A and electronic equipment B belong to same group, and electronic equipment A is located at user 1
Family in, electronic equipment B is located at the company of user 1, such a moment be present, and the household 2 of user 1 is entered using electronic equipment A
While row interactive voice, user 1 is also carrying out interactive voice using electronic equipment B.Therefore, in this case, even if electronics
Device A and electronic equipment B belong to same group, while have sent speech data to server by voice assistant, due to two
Electronic equipment belongs to different networks, and therefore, server controls electronic equipment A voice assistant and electronic equipment B voice help
Hand responds its speech data received respectively.
The embodiments of the invention provide a kind of data processing method, including：Multiple electronics that reception belongs to same group are set
The speech data that standby voice assistant is sent simultaneously, judges whether the multiple electronic equipment is located at consolidated network, is subordinated to same
Determined in multiple electronic equipments of one network with the sender of speech data at a distance of nearest target electronic device, control targe
The voice assistant of electronic equipment responds the speech data；As can be seen here, in the present embodiment, when the voice of multiple electronic equipments helps
When hand receives the speech data of user's transmission, it can be subordinated in the electronic equipment of consolidated network and determine with user apart
Nearest target electronic device, and control its voice assistant to respond the speech data, it is manually operated without user, improve user
Experience, and improve the accuracy of data processing.
Further embodiment of this invention discloses a kind of voice data processing method, as shown in figure 4, this method includes following step
Suddenly：
Step 401：Obtain the voice assistant for the multiple electronic equipments for belonging to same group while the speech data sent；
Step 402：Judge the voice assistant of the multiple electronic equipment while whether the speech data sent belongs to
Same vocal print, if so, into step 403；If it is not, into step 405；
Specifically, the plurality of electronic equipment is referred to as belonging to same group and its voice assistant is sent to server simultaneously
The electronic equipment of speech data, by judging whether the plurality of electronic equipment belongs to same vocal print to determine the plurality of electronic equipment
The speech data that is gathered of voice assistant whether be what same sender sent, if belonged in same vocal print, determine that this is more
The speech data that the voice assistant of individual electronic equipment is gathered sends for same sender, if belonging to different vocal prints, really
The speech data that the voice assistant of fixed the plurality of electronic equipment is gathered sends for different senders.
Step 403：Belong in multiple electronic equipments of same vocal print the sender determined with speech data from speech data
At a distance of nearest target electronic device；
Step 404：The voice assistant of control targe electronic equipment responds the speech data；
Step 405：Control voice data belong to multiple electronics of different vocal prints and the voice assistant of equipment responds institute respectively
State speech data.
Because speech data belongs to different vocal prints, thus may determine that the voice that distinct electronic apparatuses voice assistant is gathered
Data are sent by different senders.
As an application scenarios, electronic equipment A and electronic equipment B belong to same group, and are respectively positioned on the family of user 1
In, such a moment be present, while user 1 carries out interactive voice using electronic equipment A, the household 2 of user 1 uses electricity
Sub- equipment B is also carrying out interactive voice.Therefore, in this case, even if electronic equipment A and electronic equipment B belong to same group,
Speech data have sent to server by voice assistant simultaneously, the voice gathered by the voice assistant of two electronic equipments
Data are sent by different senders, and therefore, server controls electronic equipment A voice assistant and electronic equipment B voice help
Hand responds its speech data received respectively.
The embodiments of the invention provide a kind of data processing method, including：Multiple electronics that reception belongs to same group are set
The speech data that standby voice assistant is sent simultaneously, the institute's predicate for judging the voice assistant of the multiple electronic equipment while sending
Whether sound data belong to same vocal print, are determined in the multiple electronic equipments for belonging to same vocal print from speech data and speech data
Sender at a distance of nearest target electronic device, the voice assistant of control targe electronic equipment responds the speech data；By
This is visible, in the present embodiment, when the voice assistant of multiple electronic equipments receives the speech data of user's transmission, and Ke Yicong
Speech data, which belongs in the electronic equipment of same vocal print, to be determined with user at a distance of nearest target electronic device, and controls its language
Sound assistant responds the speech data, manually operated without user, improves Consumer's Experience, and improves the accurate of data processing
Property.
Corresponding with a kind of above-mentioned voice data processing method, the embodiment of the invention also discloses a kind of language data process
System, illustrated individually below by embodiment：
One embodiment of the invention discloses a kind of voice data processing system, as shown in figure 5, the system includes：Service
Device 100, electronic equipment 201, electronic equipment 202 and electronic equipment 203；
Wherein, electronic equipment 201 and electronic equipment 202 belong to same group, and electronic equipment 203 is not belonging to electronic equipment
201 and electronic equipment 202 belonging to group, may belong to another group, any group can also be not belonging to.
Electronic equipment 201, electronic equipment 202 and electronic equipment 203 have been separately operable voice assistant, are helped when by voice
When hand collects speech data, server 100 can be sent it to.
In the present invention, voice data processing system includes multiple electronic equipments, and the present embodiment is only with three electronic equipments
Exemplified by.
Server 100, for the voice for obtaining the voice assistant for the multiple electronic equipments for belonging to same group while sending
Data, determine to control institute at a distance of nearest target electronic device with the sender of speech data from the multiple electronic equipment
The voice assistant for stating target electronic device responds the speech data.In the present embodiment, server 100 is set for obtaining electronics
The speech data sent simultaneously for the voice assistant of 201 and electronic equipment 202, and from electronic equipment 201 and electronic equipment 202
It is determined that the voice assistant of the target electronic device is controlled to ring at a distance of nearest target electronic device with the sender of speech data
Answer the speech data.
It is understood that the implication of " simultaneously " is synchronization, but due to the factors such as network delay be present, the present invention
In to may refer to " simultaneously " be the time difference in preset time, and preset time is especially short, such as 0.5 second, 1 second.
Optionally, server can determine its affiliated group by the identity of electronic equipment, have common identity
The electronic equipment of mark belongs to same group.The identity can be belonging to for characterizing multiple electronic equipments for user's setting
The mark of same holder, the specific implementation form present invention do not limit.
It should be noted that the identity of electronic equipment may refer to the identity for electronic equipment in itself, can also
It is referred to as the identity of the voice assistant of electronic equipment.
Wherein, the voice assistant of electronic equipment can carry identity when sending speech data to server, certainly
The identity of each electronic equipment can also be stored in the server in advance so that server carries out drawing for group in advance
Point.
Wherein, it is at a distance of most with the sender of speech data that at least one electronic equipment is determined from multiple electronic equipments
Near target electronic device.
Optionally, in one embodiment, electronic equipment is used for the category of the speech data gathered based on its voice assistant
Property information determine its distance between with the sender of speech data parameter；Server is used to receive the multiple electronic equipment point
The distance parameter not sent, determine that the minimum electronic equipment of distance parameter is target electronic device.
It is transmitted directly to service in speech data it should be noted that electronic equipment can carry the distance parameter
Device, or, distance parameter is individually sent to server.
The attribute information of speech data includes one or more of following parameter：Signal to noise ratio parameter, energy intensity.Electronics
Equipment is previously stored with the corresponding relation of different attribute informations and distance parameter, from the corresponding relation prestored search with
Distance parameter corresponding to the attribute information of speech data, and send it to server；Server receives electronic equipment transmission
Distance parameter after, be subordinated to and determine that the minimum electronic equipment of distance parameter is target in multiple electronic equipments of same group
Electronic equipment.
Optionally, in another embodiment, server is specifically used for the attribute information for obtaining speech data, determines that attribute is believed
Breath meets that the electronic equipment of preparatory condition is target electronic device.
The attribute information of speech data includes one or more of following parameter：Signal to noise ratio parameter, energy intensity.
Server it is determined that attribute information meets the electronic equipment of preparatory condition be target electronic device when, a kind of realization side
In formula, the attribute information for the speech data that server can send the voice assistant of multiple electronic equipments of same group is carried out
Contrast, determine that attribute information meets that the electronic equipment of preparatory condition be target electronic device, wherein, the preparatory condition for for
Determine the nearest condition of the distance between the sender of electronic equipment and speech data.In one embodiment, attribute information is worked as
For signal to noise ratio parameter when, preparatory condition be multiple speech datas in, signal to noise ratio optimal conditions；When attribute information is energy intensity
When, preparatory condition is the most strong condition of energy intensity in multiple speech datas.
Server it is determined that attribute information meets the electronic equipment of preparatory condition be target electronic device when, another kind realize
In mode, the attribute information for the speech data that server can send the voice assistant of multiple electronic equipments of same group is equal
Compared with a default attribute information, it is determined that the electronic equipment for meeting default attribute information is target electronic device.
As can be seen here, in the present embodiment, when the voice assistant of multiple electronic equipments receives the voice number of user's transmission
According to when, only can just respond the speech data at a distance of the voice assistant of nearest target electronic device with user, without with
Family is manually operated, improves Consumer's Experience.
Another embodiment of the present invention discloses a kind of voice data processing system, and in the present embodiment, server is additionally operable to
Judge whether the multiple electronic equipment is located at consolidated network；Accordingly, server determines and voice from multiple electronic equipments
The sender of data at a distance of nearest target electronic device, be specially subordinated in multiple electronic equipments of consolidated network determine with
The sender of speech data is at a distance of nearest target electronic device.
Wherein, server is by judging whether the plurality of electronic equipment is located at consolidated network to determine the plurality of electronic equipment
It is whether co-located, if located in consolidated network, determining that the plurality of electronic equipment is co-located, if located in not
With in network, determining that the plurality of electronic equipment is located at different positions.
Optionally, server can determine the plurality of electronic equipment based on the network address or network identity of electronic equipment
Whether it is located at consolidated network, there is same network address or the electronic equipment of identical network mark to be located at consolidated network, have not
The electronic equipment identified with network address or heterogeneous networks is located at heterogeneous networks.
In an alternative embodiment of the invention, server is additionally operable to control the electronic equipment for belonging to heterogeneous networks to respond it respectively
The speech data that voice assistant is sent.
As can be seen here, in the present invention, when the voice assistant of multiple electronic equipments receives the speech data of user's transmission
When, it can be subordinated in the electronic equipment of consolidated network and determine with user at a distance of nearest target electronic device, and control it
Voice assistant responds the speech data, manually operated without user, improves Consumer's Experience, and improves the accurate of data processing
Property.
Further embodiment of this invention discloses a kind of voice data processing system, and in the present embodiment, server is additionally operable to
Judge the voice assistant of the multiple electronic equipment while whether the speech data sent belongs to same vocal print, accordingly,
Server is determined with the sender of speech data from multiple electronic equipments at a distance of nearest target electronic device, specially from language
Sound data, which belong in multiple electronic equipments of same vocal print, to be determined to set at a distance of nearest target electronic with the sender of speech data
It is standby.
Wherein, server is by judging whether the plurality of electronic equipment belongs to same vocal print to determine the plurality of electronic equipment
The speech data that is gathered of voice assistant whether be what same sender sent, if belonged in same vocal print, determine that this is more
The speech data that the voice assistant of individual electronic equipment is gathered sends for same sender, if belonging to different vocal prints, really
The speech data that the voice assistant of fixed the plurality of electronic equipment is gathered sends for different senders.
In an alternative embodiment of the invention, server is additionally operable to the electronic equipment point that control voice data belong to different vocal prints
Hold your noise the speech data for answering its voice assistant to send.
As can be seen here, in the present embodiment, when the voice assistant of multiple electronic equipments receives the voice number of user's transmission
According to when, can belong to from speech data in the electronic equipment of same vocal print and determine to set at a distance of nearest target electronic with user
It is standby, and control its voice assistant to respond the speech data, it is manually operated without user, Consumer's Experience is improved, and improve number
According to the accuracy of processing.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be and other
The difference of embodiment, between each embodiment identical similar portion mutually referring to.For device disclosed in embodiment
For, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is said referring to method part
It is bright.
The foregoing description of the disclosed embodiments, professional and technical personnel in the field are enable to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (10)
- A kind of 1. voice data processing method, it is characterised in that including：Obtain the voice assistant for the multiple electronic equipments for belonging to same group while the speech data sent；Determine the sender with speech data at a distance of nearest target electronic device from the multiple electronic equipment；The voice assistant of the target electronic device is controlled to respond the speech data.
- 2. according to the method for claim 1, it is characterised in that also include：Judge whether the multiple electronic equipment is located at consolidated network；Accordingly, it is described to determine to set at a distance of nearest target electronic with the sender of speech data from the multiple electronic equipment It is standby, including：It is subordinated in multiple electronic equipments of consolidated network and determines to set at a distance of nearest target electronic with the sender of speech data It is standby.
- 3. according to the method for claim 1, it is characterised in that also include：Judge the voice assistant of the multiple electronic equipment while whether the speech data sent belongs to same vocal print；Accordingly, it is described to determine to set at a distance of nearest target electronic with the sender of speech data from the multiple electronic equipment It is standby, including：Belong to from speech data in multiple electronic equipments of same vocal print and determine the sender with speech data at a distance of nearest mesh Mark electronic equipment.
- 4. according to the method in claim 2 or 3, it is characterised in that also include：If it is not, the voice assistant of the multiple electronic equipment is controlled to respond the speech data respectively.
- 5. according to the method for claim 1, it is characterised in that determined from the multiple electronic equipment and speech data Sender at a distance of nearest target electronic device, including：Receive the distance parameter that the multiple electronic equipment is sent respectively；Wherein, the distance parameter is that electronic equipment is based on language The attribute informations of sound data determine its distance between with the sender of speech data；Determine that the minimum electronic equipment of distance parameter is target electronic device.
- 6. according to the method for claim 1, it is characterised in that determined from the multiple electronic equipment and speech data Sender at a distance of nearest target electronic device, including：Obtain the attribute information of the speech data；Determine that the attribute information meets that the electronic equipment of preparatory condition is target electronic device.
- A kind of 7. voice data processing system, it is characterised in that including：Multiple electronic equipments, have been separately operable voice assistant, for gathering speech data by the voice assistant；Server, for obtaining the voice assistant for the multiple electronic equipments for belonging to same group while the speech data of transmission, from Determine to control the target electricity at a distance of nearest target electronic device with the sender of speech data in the multiple electronic equipment The voice assistant of sub- equipment responds the speech data.
- 8. system according to claim 7, it is characterised in that the server is additionally operable to judge the multiple electronic equipment Whether consolidated network is located at, and specifically for being subordinated to the transmission determined in multiple electronic equipments of consolidated network with speech data Person is at a distance of nearest target electronic device.
- 9. system according to claim 7, it is characterised in that the server is additionally operable to judge the multiple electronic equipment The speech data that sends simultaneously of voice assistant whether belong to same vocal print, and specifically for belonging to same from speech data Determine the sender with speech data at a distance of nearest target electronic device in multiple electronic equipments of vocal print.
- 10. system according to claim 7, it is characterised in that the electronic equipment is used for based on the speech data Attribute information determine its distance between with the sender of the speech data parameter；The server is specifically used for receiving the distance parameter that the multiple electronic equipment is sent respectively, determines distance parameter minimum Electronic equipment be target electronic device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710703578.7A CN107452386B (en) | 2017-08-16 | 2017-08-16 | Voice data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710703578.7A CN107452386B (en) | 2017-08-16 | 2017-08-16 | Voice data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107452386A true CN107452386A (en) | 2017-12-08 |
| CN107452386B CN107452386B (en) | 2020-03-24 |
Family
ID=60492616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710703578.7A Active CN107452386B (en) | 2017-08-16 | 2017-08-16 | Voice data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107452386B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108597536A (en) * | 2018-03-20 | 2018-09-28 | 成都星环科技有限公司 | A kind of interactive system based on acoustic information positioning |
| CN108682414A (en) * | 2018-04-20 | 2018-10-19 | 深圳小祺智能科技有限公司 | Sound control method, voice system, equipment and storage medium |
| CN109243443A (en) * | 2018-09-28 | 2019-01-18 | 联想(北京)有限公司 | Sound control method, device and electronic equipment |
| CN109639961A (en) * | 2018-11-08 | 2019-04-16 | 联想(北京)有限公司 | Acquisition method and electronic equipment |
| CN110415694A (en) * | 2019-07-15 | 2019-11-05 | 深圳市易汇软件有限公司 | A kind of method that more intelligent sound boxes cooperate |
| CN110660389A (en) * | 2019-09-11 | 2020-01-07 | 北京小米移动软件有限公司 | Voice response method, device, system and equipment |
| CN110910880A (en) * | 2019-11-29 | 2020-03-24 | 广东美的厨房电器制造有限公司 | Voice control method, system, device and storage medium |
| CN111128150A (en) * | 2019-11-27 | 2020-05-08 | 云知声智能科技股份有限公司 | Method and device for awakening intelligent voice equipment |
| CN111354361A (en) * | 2018-12-21 | 2020-06-30 | 深圳市优必选科技有限公司 | Emotion communication method and system and robot |
| CN111614768A (en) * | 2020-05-22 | 2020-09-01 | 云知声智能科技股份有限公司 | Single awakening method, device and system |
| CN111614770A (en) * | 2020-05-22 | 2020-09-01 | 云知声智能科技股份有限公司 | Single awakening method, device and system |
| WO2020215736A1 (en) * | 2019-04-26 | 2020-10-29 | 广东美的白色家电技术创新中心有限公司 | Voice recognition devices and wake-up response method therefor, and computer storage medium |
| CN112289313A (en) * | 2019-07-01 | 2021-01-29 | 华为技术有限公司 | Voice control method, electronic equipment and system |
| WO2021025542A1 (en) * | 2019-08-08 | 2021-02-11 | Samsung Electronics Co., Ltd. | Method, system and device for sharing intelligence engine by multiple devices |
| CN112750439A (en) * | 2020-12-29 | 2021-05-04 | 恒玄科技(上海)股份有限公司 | Speech recognition method, electronic device and storage medium |
| CN114143133A (en) * | 2021-11-26 | 2022-03-04 | 深圳康佳电子科技有限公司 | Decentralized intelligent household appliance and voice management system thereof |
| WO2022179269A1 (en) * | 2021-02-26 | 2022-09-01 | 华为技术有限公司 | Voice interaction method and electronic device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105788599A (en) * | 2016-04-14 | 2016-07-20 | 北京小米移动软件有限公司 | Speech processing method, router and intelligent speech control system |
| CN106951209A (en) * | 2017-03-29 | 2017-07-14 | 联想(北京)有限公司 | A kind of control method, device and electronic equipment |
-
2017
- 2017-08-16 CN CN201710703578.7A patent/CN107452386B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105788599A (en) * | 2016-04-14 | 2016-07-20 | 北京小米移动软件有限公司 | Speech processing method, router and intelligent speech control system |
| CN106951209A (en) * | 2017-03-29 | 2017-07-14 | 联想(北京)有限公司 | A kind of control method, device and electronic equipment |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108597536A (en) * | 2018-03-20 | 2018-09-28 | 成都星环科技有限公司 | A kind of interactive system based on acoustic information positioning |
| CN108682414A (en) * | 2018-04-20 | 2018-10-19 | 深圳小祺智能科技有限公司 | Sound control method, voice system, equipment and storage medium |
| CN109243443A (en) * | 2018-09-28 | 2019-01-18 | 联想(北京)有限公司 | Sound control method, device and electronic equipment |
| CN109639961A (en) * | 2018-11-08 | 2019-04-16 | 联想(北京)有限公司 | Acquisition method and electronic equipment |
| CN111354361A (en) * | 2018-12-21 | 2020-06-30 | 深圳市优必选科技有限公司 | Emotion communication method and system and robot |
| WO2020215736A1 (en) * | 2019-04-26 | 2020-10-29 | 广东美的白色家电技术创新中心有限公司 | Voice recognition devices and wake-up response method therefor, and computer storage medium |
| CN112289313A (en) * | 2019-07-01 | 2021-01-29 | 华为技术有限公司 | Voice control method, electronic equipment and system |
| CN110415694A (en) * | 2019-07-15 | 2019-11-05 | 深圳市易汇软件有限公司 | A kind of method that more intelligent sound boxes cooperate |
| US11490240B2 (en) | 2019-08-08 | 2022-11-01 | Samsung Electronics Co., Ltd. | Method, system and device for sharing intelligence engine by multiple devices |
| WO2021025542A1 (en) * | 2019-08-08 | 2021-02-11 | Samsung Electronics Co., Ltd. | Method, system and device for sharing intelligence engine by multiple devices |
| CN110660389A (en) * | 2019-09-11 | 2020-01-07 | 北京小米移动软件有限公司 | Voice response method, device, system and equipment |
| CN111128150A (en) * | 2019-11-27 | 2020-05-08 | 云知声智能科技股份有限公司 | Method and device for awakening intelligent voice equipment |
| CN110910880B (en) * | 2019-11-29 | 2022-05-10 | 广东美的厨房电器制造有限公司 | Voice control method, system, device and storage medium |
| CN110910880A (en) * | 2019-11-29 | 2020-03-24 | 广东美的厨房电器制造有限公司 | Voice control method, system, device and storage medium |
| CN111614770A (en) * | 2020-05-22 | 2020-09-01 | 云知声智能科技股份有限公司 | Single awakening method, device and system |
| CN111614768A (en) * | 2020-05-22 | 2020-09-01 | 云知声智能科技股份有限公司 | Single awakening method, device and system |
| CN112750439A (en) * | 2020-12-29 | 2021-05-04 | 恒玄科技(上海)股份有限公司 | Speech recognition method, electronic device and storage medium |
| CN112750439B (en) * | 2020-12-29 | 2023-10-03 | 恒玄科技(上海)股份有限公司 | Speech recognition method, electronic device and storage medium |
| WO2022179269A1 (en) * | 2021-02-26 | 2022-09-01 | 华为技术有限公司 | Voice interaction method and electronic device |
| CN114143133A (en) * | 2021-11-26 | 2022-03-04 | 深圳康佳电子科技有限公司 | Decentralized intelligent household appliance and voice management system thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107452386B (en) | 2020-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107452386A (en) | A kind of voice data processing method and system | |
| CN105139506B (en) | Number obtaining method, device, server-side and system based on positioning mobile terminal | |
| CN103294460B (en) | User-interface application layout adjustment method, server device and terminal unit | |
| CN108259277B (en) | Mobile terminal communication information sharing method and system based on intelligent household equipment | |
| EP3817283B1 (en) | Data transmission control method and related apparatus | |
| CN106535149B (en) | Terminal automatic call forwarding method and system | |
| CN105872833A (en) | Video communication method and device, and smart television | |
| CN109508527A (en) | A kind of method that realizing that different terminals account is unified, terminal and server | |
| CN103905674A (en) | Device and method applied to dual-network communication of Internet and telecommunication network | |
| CN107707651A (en) | The data transmission system of new blower fan comprising peripheral hardware mobile monitoring controller | |
| CN108521889A (en) | Accidental access method and device, user equipment and base station | |
| CN106713682A (en) | Call transfer method and system | |
| CN103068077A (en) | Bimodule mobile terminal and communication method thereof | |
| CN110177368A (en) | A kind of call-establishing method and system, Video Communication Server | |
| CN109327381A (en) | Personnel are quickly added to the method and device of group and newly-built group | |
| CN105208231B (en) | A kind of voice broadcast method and related system based on IVR | |
| WO2009048260A3 (en) | Visual ars service system and method enabled by mobile terminal's call control function | |
| CN103281785A (en) | Method and device for regulating communication resource amount | |
| CN105577955A (en) | Communication method and electronic device | |
| KR101814324B1 (en) | Automatic calling synchronization system and method | |
| US20120002239A1 (en) | Menu display system, menu display method, and server device | |
| CN106301531B (en) | Private network communication method based on satellite digital Transmission system | |
| CN104469720B (en) | A kind of method and system of clawback incoming call | |
| CN105741050A (en) | Power grid dispatching method and device | |
| CN106303110A (en) | The method and system that a kind of call center generation visitor queues up |
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 |