CN107580237A - Operating method, device, system and the storage medium of TV - Google Patents
Operating method, device, system and the storage medium of TV Download PDFInfo
- Publication number
- CN107580237A CN107580237A CN201710793303.7A CN201710793303A CN107580237A CN 107580237 A CN107580237 A CN 107580237A CN 201710793303 A CN201710793303 A CN 201710793303A CN 107580237 A CN107580237 A CN 107580237A
- Authority
- CN
- China
- Prior art keywords
- vocal print
- cluster
- television set
- user
- phonetic order
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a kind of operating method of TV, the operating method of TV includes：When receiving the operation requests of television set transmission, operation requests are parsed, to extract the phonetic order of the device identification of television set, the vocal print feature of user and user；It is determined that vocal print cluster corresponding with device identification；It is determined that after vocal print cluster, the identity information of user is determined according to the sound-groove model in vocal print feature and vocal print cluster；According to response data corresponding to phonetic order and identity information generation, and response data is fed back into television set.The present invention also provides a kind of operation device of TV, system and storage medium.It is of the invention that vocal print cluster is determined according to the device identification of television set because of server, reduce the sound-groove model with the comparison of vocal print feature, avoid the interference pair determine subscriber identity information, improve the accuracy rate of user's identification, so that the expectation of the data fit user of server feedback, improves the experience of user.
Description
Technical field
The present invention relates to TV technology, more particularly to a kind of operating method of TV, device, system and storage to be situated between
Matter.
Background technology
Television set is after it can connect internet, and the video of television for play is more abundant, the application function of television set
Also gradually increase.
TV with voice remote controller is popularized very much, and it is corresponding that user performs according to phonetic order television set
Operation；And television set is the shared device of one family, i.e., television set includes multiple users, how accurate according to phonetic order
Identify user so that television set performs corresponding operation to be needed to solve the problems, such as lower TV industry.
In the prior art, the vocal print feature of television set extraction user speech instruction, according in vocal print feature and vocal print cluster
Sound-groove model matching degree identification user, because the sound-groove model of vocal print cluster is more, can to recognition result produce interference so that the knowledge
Other method accuracy rate is low, so that the data that television set obtains do not meet the expectation of user, reduces the experience of user.
The content of the invention
It is a primary object of the present invention to provide a kind of operating method of TV, device, system and storage medium, it is intended to solve
Certainly the accuracy rate of TV identification user is low so that the data that television set obtains do not meet the expectation of user, reduce the body of user
The problem of testing.
To achieve the above object, the present invention provides a kind of operating method of TV, the operating method of the TV include with
Lower step：
When receiving the operation requests of television set transmission, the operation requests are parsed, and please in the operation of the parsing
Seek device identification, the vocal print feature of user and the phonetic order of user of the middle extraction television set；
It is determined that vocal print cluster identity corresponding with the device identification, and according to corresponding to determining the vocal print cluster identity
Vocal print cluster；
It is determined that after the vocal print cluster, the vocal print feature and the sound-groove model in the vocal print cluster are compared
It is right, to determine the identity information of user, wherein, the vocal print cluster contains the sound-groove model of multiple users；
The response data according to corresponding to generating the phonetic order and the identity information, and the response data is anti-
It is fed to the television set.
Preferably, the sound-groove model according in the vocal print cluster determines subscriber identity information with the vocal print feature
The step of include：
The vocal print feature and the matching degree of each sound-groove model in the vocal print cluster are calculated, wherein, the vocal print mould
Type corresponds to the subscriber identity information；
Obtain subscriber identity information corresponding to the maximum sound-groove model of matching degree.
Preferably, described the step of calculating the matching degree of each sound-groove model in the vocal print feature and the vocal print cluster
Afterwards, in addition to：
Judge whether each matching degree is more than or equal to predetermined threshold value；
When there is the matching degree to be more than or equal to predetermined threshold value, the sound-groove model for obtaining matching degree maximum is performed
Step.
Preferably, the sound-groove model according in the vocal print cluster determines subscriber identity information with the vocal print feature
The step of after, in addition to：
Control authority corresponding to the subscriber identity information is obtained, and judges whether the phonetic order is in the control
Corresponding to authority in the range of control instruction；
When judging that the phonetic order is in the range of the control instruction of the control authority, perform described in the basis
Corresponding to phonetic order and the identity information generation the step of response data.
Preferably, the sound-groove model according in the vocal print cluster determines subscriber identity information with the vocal print feature
The step of after, in addition to：
Current point in time is obtained, and obtains control authority corresponding with the current point in time；
Control instruction scope corresponding with the control authority is obtained, and judges whether the phonetic order is in the control
Corresponding to authority processed in the range of control instruction；
When judging that the phonetic order is in the range of the control instruction of the control authority, perform described in the basis
Corresponding to phonetic order and the identity information generation the step of response data.
Preferably, it is described that the step of whether phonetic order is in the range of the control instruction of the control authority judged
Afterwards, in addition to：
When judging that the phonetic order is not in the range of the control instruction of the control authority, to the user identity
The default terminal of information association sends prompt message.
Preferably, the operating method of the TV, in addition to：
After the generation request for the vocal print cluster that the television set is sent is received, according to the generation acquisition request
The device identification of television set and pending vocal print cluster；
Generation vocal print cluster identity corresponding with the pending vocal print cluster；
The mapping relations of the device identification and the vocal print cluster identity are established, and preserve mapping relations, described
Pending vocal print cluster, the vocal print cluster identity and the device identification, to generate the vocal print cluster.
To achieve the above object, the present invention also provides a kind of operation device of TV, and the operation device of the TV includes
Memory, processor and the operation sequence for being stored in the TV that can be run on the memory and on the processor, it is described
The step of operating method of TV as described above is realized when the operation sequence of TV is by the computing device.
To achieve the above object, the present invention also provides a kind of operating system of TV, and the operating system of the TV includes
The operation device of television set, server and TV, wherein,
The server, for when receiving the operation requests of television set transmission, parsing the operation requests, and in institute
The phonetic order of the device identification that the television set is extracted in the operation requests of parsing, the vocal print feature of user and user is stated,
It is determined that vocal print cluster identity corresponding with the device identification, and the vocal print collection according to corresponding to determining the vocal print cluster identity
Group, it is determined that after the vocal print cluster, the vocal print feature is compared with the sound-groove model in the vocal print cluster, with true
Determine the identity information of user, wherein, the vocal print cluster contains the sound-groove model of multiple users, according to the phonetic order and
Response data corresponding to the identity information generation, and the response data is fed back into the television set；
The television set, for when receiving the phonetic order of user's transmission, user to be extracted according to the phonetic order
Vocal print feature, and obtain the device identification of television set, it is special according to the phonetic order, the device identification and the vocal print
Sign generation operation requests, and send the operation requests to the server.
To achieve the above object, the present invention also provides a kind of storage medium, and the behaviour of TV is stored with the storage medium
Make program, the operation sequence of the TV realizes the operating method of TV as described above when being executed by processor the step of.
Operating method, device, system and the storage medium of TV provided by the invention, server are receiving television set hair
During the operation requests sent, device identification, the phonetic order of user and the vocal print of user of television set are extracted in operation requests
Feature, the vocal print cluster according to corresponding to determining television devices mark, and it is special according to the sound-groove model in vocal print cluster and vocal print
Sign determines subscriber identity information, so that server number of responses according to corresponding to phonetic order and identity information generation
According to, and response data is fed back to television set；Because server according to the device identification of television set determines vocal print cluster, reduce with
The sound-groove model of the comparison of vocal print feature, the interference pair determine subscriber identity information is avoided, improves the accurate of user's identification
Rate so that the expectation of the data fit user of server feedback, improve the experience of user.
Brief description of the drawings
Fig. 1 is system architecture figure of the present invention；
Fig. 2 is the hardware architecture diagram of the server involved by the embodiment of the present invention；
Fig. 3 is the schematic flow sheet of the first embodiment of the operating method of TV of the present invention；
Fig. 4 is to determine user according to the sound-groove model in the vocal print cluster and the vocal print feature in step S20 in Fig. 3
The refinement schematic flow sheet of identity information；
Fig. 5 is the schematic flow sheet of the second embodiment of the operating method of TV of the present invention；
Fig. 6 is the schematic flow sheet of the 3rd embodiment of the operating method of TV of the present invention.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The primary solutions of the embodiment of the present invention are：When receiving the operation requests of television set transmission, described in parsing
Operation requests, and extract in the operation requests of the parsing device identification of the television set, the vocal print feature of user and
The phonetic order of user；It is determined that vocal print cluster identity corresponding with the device identification, and it is true according to the vocal print cluster identity
Vocal print cluster corresponding to fixed；It is determined that after the vocal print cluster, by the vocal print mould in the vocal print feature and the vocal print cluster
Type is compared, to determine the identity information of user, wherein, the vocal print cluster contains the sound-groove model of multiple users；According to
Response data corresponding to the phonetic order and identity information generation, and the response data is fed back into the TV
Machine.
Because in the prior art, television set extracts the vocal print feature of user speech instruction, according to vocal print feature and vocal print collection
Sound-groove model matching degree identification user in group, because the sound-groove model of vocal print cluster is more, interference can be produced to recognition result so that
The recognition methods accuracy rate is low, so that the data that television set obtains do not meet the expectation of user, reduces the experience of user.
The present invention provides a solution, because server according to the device identification of television set determines vocal print cluster, reduces
Sound-groove model with the comparison of vocal print feature, the interference pair determine subscriber identity information is avoided, improves user's identification
Accuracy rate so that the expectation of the data fit user of server feedback, improve the experience of user.
As shown in figure 1, the system architecture that the present embodiment method is related to includes server, television set.
The server, for when receiving the operation requests of television set transmission, parsing the operation requests, and in institute
The phonetic order of the device identification that the television set is extracted in the operation requests of parsing, the vocal print feature of user and user is stated,
It is determined that vocal print cluster identity corresponding with the device identification, and the vocal print collection according to corresponding to determining the vocal print cluster identity
Group, it is determined that after the vocal print cluster, the vocal print feature is compared with the sound-groove model in the vocal print cluster, with true
Determine the identity information of user, wherein, the vocal print cluster contains the sound-groove model of multiple users, according to the phonetic order and
Response data corresponding to the identity information generation, and the response data is fed back into the television set；
The television set, for when receiving the second phonetic order, the vocal print of user to be extracted according to the phonetic order
Feature, and obtain the device identification of television set；The first phonetic order corresponding with the second phonetic order is sent to the server,
So that server response data according to corresponding to first phonetic order to television set feedback, wherein, described the
One phonetic order contains the vocal print feature and the device identification.
As a kind of implementation, the hardware configuration of above-mentioned server can be as described in Figure 2.
Reference picture 2, the server can include：Processor 1001, such as CPU, memory 1002, communication bus 1003.
Wherein, communication bus 1003 is used to realize the connection communication in the server between each building block.Memory 1002 can be
High-speed RAM memory or stable memory (non-volatile memory), such as magnetic disk storage.Memory
The 1002 optional storage devices that can also be independently of aforementioned processor 1001.As shown in Fig. 2 stored as a kind of computer
The operation sequence of operating system, communication module and TV can be included in the memory 1002 of medium.
Processor 1001 can be used for calling and be stored in memory 1002 in the hardware involved by the server shown in Fig. 2
TV operation sequence, and perform following operate：
When receiving the operation requests of television set transmission, the operation requests are parsed, and please in the operation of the parsing
Seek device identification, the vocal print feature of user and the phonetic order of user of the middle extraction television set；
It is determined that vocal print cluster identity corresponding with the device identification, and according to corresponding to determining the vocal print cluster identity
Vocal print cluster；
It is determined that after the vocal print cluster, the vocal print feature and the sound-groove model in the vocal print cluster are compared
It is right, to determine the identity information of user, wherein, the vocal print cluster contains the sound-groove model of multiple users；
The response data according to corresponding to generating the phonetic order and the identity information, and the response data is anti-
It is fed to the television set.Further, in one embodiment, processor 1001 can be used for calling and be stored in memory 1002
TV operation sequence, and perform following operate：
The vocal print feature and the matching degree of each sound-groove model in the vocal print cluster are calculated, wherein, the vocal print mould
Type corresponds to the subscriber identity information；
Obtain subscriber identity information corresponding to the maximum sound-groove model of matching degree.
Further, in one embodiment, processor 1001 can be used for calling the TV stored in memory 1002
Operation sequence, and perform following operate：
Judge whether each matching degree is more than or equal to predetermined threshold value；
When there is the matching degree to be more than or equal to predetermined threshold value, the sound-groove model for obtaining matching degree maximum is performed
Step.
Further, in one embodiment, processor 1001 can be used for calling the TV stored in memory 1002
Operation sequence, and perform following operate：
Control authority corresponding to the subscriber identity information is obtained, and judges whether the phonetic order is in the control
Corresponding to authority in the range of control instruction；
When judging that the phonetic order is in the range of the control instruction of the control authority, perform described in the basis
Corresponding to phonetic order and the identity information generation the step of response data.
Further, in one embodiment, processor 1001 can be used for calling the TV stored in memory 1002
Operation sequence, and perform following operate：
Current point in time is obtained, and obtains control authority corresponding with the current point in time；
Control instruction scope corresponding with the control authority is obtained, and judges whether the phonetic order is in the control
Corresponding to authority processed in the range of control instruction；
When judging that the phonetic order is in the range of the control instruction of the control authority, perform described in the basis
Corresponding to phonetic order and the identity information generation the step of response data.
Further, in one embodiment, processor 1001 can be used for calling the TV stored in memory 1002
Operation sequence, and perform following operate：
When judging that the phonetic order is not in the range of the control instruction of the control authority, to the user identity
The default terminal of information association sends prompt message.
Further, in one embodiment, processor 1001 can be used for calling the TV stored in memory 1002
Operation sequence, and perform following operate：
After the generation request for the vocal print cluster that the television set is sent is received, according to the generation acquisition request
The device identification of television set and pending vocal print cluster；
Generation vocal print cluster identity corresponding with the pending vocal print cluster；
The mapping relations of the device identification and the vocal print cluster identity are established, and preserve mapping relations, described
Pending vocal print cluster, the vocal print cluster identity and the device identification, to generate the vocal print cluster
The present embodiment is according to such scheme, and server is when receiving the operation requests of television set transmission, in operation requests
Device identification, the phonetic order of user and the vocal print feature of user of middle extraction television set, are identified true according to television devices
Vocal print cluster corresponding to fixed, and subscriber identity information is determined according to the sound-groove model in vocal print cluster and vocal print feature, so that
Server response data according to corresponding to phonetic order and identity information generation is obtained, and response data is anti-to television set
Feedback；Because server according to the device identification of television set determines vocal print cluster, reduce the sound-groove model with the comparison of vocal print feature,
The interference pair determine subscriber identity information is avoided, improves the accuracy rate of user's identification so that the data symbols of server feedback
The expectation at family is shared, improves the experience of user.
Based on above-mentioned hardware architecture, the embodiment of the operating method of TV of the present invention is proposed.
Reference picture 2, Fig. 2 are the first embodiment of the operation of TV of the present invention, and the operation depending on TV comprises the following steps：
Step S10, when receiving the operation requests of television set transmission, the operation requests are parsed, and in the parsing
Operation requests in extract the phonetic order of the device identification of the television set, the vocal print feature of user and user；
In the present invention, television set is stored with unique facility information on the server, and the facility information of television set includes
The device identification of television set；Television set is provided with the reception device for receiving user speech, and reception device can be remote control；Television set
Voiceprint extraction module is inside additionally provided with, voiceprint extraction module can extract the vocal print feature in phonetic order.Received when television set
To user phonetic order when, obtain the device identification of television set, then according to phonetic order extract user vocal print feature, and
By phonetic order and vocal print feature and the device identification boil down to packet of television set, then by the operation requests containing packet
Sent to server, server parses operation requests to extract the device identification of television set, user when receiving operation requests
Vocal print feature and user phonetic order.
It should be noted that server is the individualized content that each television set associated with it is provided with TV user
Service, and television set is family expenses shared device, i.e., the personalized content services of each television set include and TV office
Each kinsfolk of connection；In order to be accurately that each kinsfolk provides personalized service, television set is provided with sound and receives dress
Put and (sound can be received in the case where television set is connected to power supply), sound receiver can receive each member's in family
Sound, and according to the keyword in kinsfolk's sound of reception to determine the relation of member in family, so as to be each family
Front yard member determines identity, such as, then television set defines identity corresponding to the sound when receiving some sound
It is that core acquisition is relevant with the sound using the sound of " son " during each member's sound in lasting reception family for son
The keyword (such as " wife ", " daughter ", " mother ") of system, after each keyword is obtained, television set can found a family pass
It is net, and by the SoundRec of reception in corresponding kinsfolk, the then sound according to corresponding to being established the sound of kinsfolk
Line model, and sound-groove model is corresponding with corresponding subscriber identity information to establish vocal print cluster.
The identity information of kinsfolk is determined in television set, television set can record user corresponding to each identity information
Television-viewing operates, for example records the video type of user viewing, watches the period of video, and electricity during viewing video
Depending on volume, TV brightness, and history viewing record of each television video etc., television set is by these content records
Get off and send to server so that server conclude the user TV operation custom, hobby video type with to this
User provides personalized service.Television set can be spaced certain time length and upload the above to server, so that server is real-time more
The personalized service of new user.
Step S20, it is determined that vocal print cluster identity corresponding with the device identification, and it is true according to the vocal print cluster identity
Vocal print cluster corresponding to fixed；
Step S30, it is determined that after the vocal print cluster, by the sound-groove model in the vocal print feature and the vocal print cluster
It is compared, to determine the identity information of user, wherein, the vocal print cluster contains the sound-groove model of multiple users；
After television set establishes vocal print cluster, vocal print cluster, television devices mark can be compressed into packet, and to clothes
Business device sends the generation request of the vocal print cluster containing packet, and now server can obtain device identification and the sound of television set
Line cluster, and for vocal print cluster ID (vocal print cluster identity) corresponding to the generation of vocal print cluster, then establish television equipment mark
With the mapping relations of vocal print cluster identity, and television devices are identified, vocal print cluster identity, vocal print cluster and mapping relations
Preserve, while personalized service associate with vocal print cluster, it is possible to understand that think, television set is on the server all with uniquely
Vocal print cluster, i.e. server contains multiple vocal print clusters.Need to illustrate when, television set can be spaced certain duration and upload
New vocal print cluster (the mainly renewal of sound-groove model), so as to enable the server to improve the accuracy of identification user.
After corresponding vocal print cluster is found according to the device identification of television set when server, according to vocal print spy feature with
Each vocal print module in vocal print cluster compares matching so that it is determined that the identity information of user, specifically refer to Fig. 4, and Fig. 4 is root
It is described according to the refined flow chart that subscriber identity information is determined according to the sound-groove model in the vocal print cluster and the vocal print feature
Step S20 includes：
Step S21, the vocal print feature and the matching degree of each sound-groove model in the vocal print cluster are calculated, wherein, institute
State sound-groove model and correspond to the subscriber identity information；
Step S22, obtain subscriber identity information corresponding to the maximum sound-groove model of matching degree；
Sound-groove model containing TV user corresponding to television set in vocal print cluster, and these TV users are all some
The sound-groove model quantity contained in the kinsfolk of family, i.e. vocal print cluster is few (in general family has 5-10 people) so that sound
Line feature and the calculation times of sound-groove model are few, so as to reduce the operation time of server, avoid because calculating excessive interference
The problem of accuracy rate of user's identification.
It should be noted that because the phonetic order of television set transmission may not be the kinsfolk (visitor in the vocal print cluster
People), so TV user can not be determined with subscriber identity information corresponding to the maximum sound-groove model of matching degree, so
Need to set matching degree one predetermined threshold value (predetermined threshold value can be any appropriate numerical value, such as matching degree 80%),
Have and be more than the predetermined threshold value in matching degree, step S22 could be performed, when all matching degrees are respectively less than predetermined threshold value, now
Server can assert that the user is visitor, and server can not provide personalized service corresponding with the visitor, for this feelings
Condition, conventional service can be set to be selected for visitor.
Step S40, according to response data corresponding to the phonetic order and identity information generation, and by the sound
Data feedback is answered to the television set；
In the present invention, phonetic order can be the instruction to television set, for example volume tunes up, shut down or timing, also may be used
To be video recommendations instruction, for example see a film, see animation, TV for not watched of viewing last time etc., can with query statement, than
Such as check weather tomorrow, inquiry quotations on the stock market；These contents have the personalized service in the server with the user-association
Described in interior；I.e. after server determines the identity information of user, personalized service corresponding with the user is searched, then basis
Phonetic order obtain corresponding to data, (data are pre-processed, such as server after generating response data further according to data
The form for the data that the format conversion of data can be played into television set), the response data is fed back into television set.
In the technical scheme that the present embodiment provides, server is operating when receiving the operation requests of television set transmission
Device identification, the phonetic order of user and the vocal print feature of user of television set are extracted in request, according to television devices mark
Know vocal print cluster corresponding to determining, and subscriber identity information is determined according to the sound-groove model in vocal print cluster and vocal print feature, from
And cause server response data according to corresponding to phonetic order and identity information generation, and by response data to TV
Machine feeds back；Because server according to the device identification of television set determines vocal print cluster, reduce the vocal print with the comparison of vocal print feature
Model, the interference pair determine subscriber identity information is avoided, improve the accuracy rate of user's identification so that the number of server feedback
According to the expectation for meeting user, the experience of user is improved.
Reference picture 5, Fig. 5 is the second embodiment of the operating method of TV of the present invention, based on above-described embodiment, the step
After S30, in addition to：
Step S50, control authority corresponding to the subscriber identity information is obtained, and judge whether the phonetic order is in
In the range of the control instruction of the control authority；
Step S60, when judging that the phonetic order is in the range of the control instruction of the control authority, described in execution
According to corresponding to generating the phonetic order and the identity information the step of response data；
After server determines the identity of user, server can read corresponding to the user that (user can for control authority
The authority of each kinsfolk is independently set, and is stored in server), whether server now judges phonetic order in control
In the range of the control instruction of authority, for example the user is children, then the control authority of the children can only watch animation, it is impossible to see
See violence video, it is impossible to play game, if the phonetic order that children send is viewing animation, now server obtains the dynamic of the children
Viewing record is drawn, so that the children can watch animation；I.e. it is anti-to obtain response data corresponding with phonetic order for server
It is fed to television set.If phonetic order is not in the range of the control instruction of control authority, the prompting letter of generation insufficient permission
Breath, and feed back to television set.
In the technical scheme that the present embodiment provides, server determines whether the use it is determined that after the identity information of user
Whether the phonetic order at family is in corresponding to user in the range of the control instruction of control authority, is referred to deciding whether to obtain with voice
Data corresponding to order, so that the operating method of television set is more intelligent.
Reference picture 6, Fig. 6 is the 3rd embodiment of the operating method of TV of the present invention, based on first embodiment, the step
After S30, in addition to：
Step S70, current point in time is obtained, and obtain control authority corresponding with the current point in time；
Step S80, control instruction scope corresponding with the control authority is obtained, and judge whether the phonetic order is located
In corresponding to the control authority in the range of control instruction；
Step S90, when judging that the phonetic order is in the range of the control instruction of the control authority, described in execution
According to corresponding to generating the phonetic order and the identity information the step of response data.
The control authority of user can associate with time point, such as, father and mother set children's working day to play game, still
Allow the certain time period (such as 3 points to 5 points of afternoon) at weekend can play, i.e., the control authority of children can be according to current time
The point residing period it is appropriate relax control instruction scope.
It should be noted that when phonetic order is not in the range of the control instruction of control authority, now server meeting
The phonetic order and the user profile sent to default terminal, can with understanding think that server can set each
Television set main users (such as in vocal print cluster be " mother " identity), this preset terminal receive phonetic order with
And during user profile, user corresponding to the default terminal can learn concrete operations of the user corresponding to phonetic order to television set
Item, server can set default terminal to be directed to the response duration (preset duration) of prompt message, if server is not when default
It is long to receive default terminal and send when allowing to perform the information of the first instruction, then do not perform generation number of responses corresponding with phonetic order
According to conversely, obtaining response data corresponding with phonetic order.
In the technical scheme that the present embodiment provides, server determines whether the use it is determined that after the identity information of user
Whether the phonetic order at family is in corresponding to user in the range of the control instruction of control authority, is referred to deciding whether to obtain with voice
Data corresponding to order, so that the operating method of television set is more intelligent.
The present invention also provides a kind of operation device of TV, the operation device of the TV include memory, processor and
It is stored in the operation sequence for the TV that can be run on the memory and on the processor, the operation sequence quilt of the TV
The step of operating method that the TV described in example is performed as described above is realized during the computing device.
The present invention also provides a kind of operating system of TV, the operating system of the TV include television set, server and
The operating method of TV, wherein,
The server, for when receiving the operation requests of television set transmission, parsing the operation requests, and in institute
The phonetic order of the device identification that the television set is extracted in the operation requests of parsing, the vocal print feature of user and user is stated,
It is determined that vocal print cluster identity corresponding with the device identification, and the vocal print collection according to corresponding to determining the vocal print cluster identity
Group, it is determined that after the vocal print cluster, the vocal print feature is compared with the sound-groove model in the vocal print cluster, with true
Determine the identity information of user, wherein, the vocal print cluster contains the sound-groove model of multiple users, according to the phonetic order and
Response data corresponding to the identity information generation, and the response data is fed back into the television set；
The television set, for when receiving the phonetic order of user's transmission, user to be extracted according to the phonetic order
Vocal print feature, and obtain the device identification of television set, it is special according to the phonetic order, the device identification and the vocal print
Sign generation operation requests, and send the operation requests to the server.
The present invention also provides a kind of storage medium, and the operation sequence of TV, the TV are stored with the storage medium
Operation sequence each step of the operating method that the TV described in example is performed as described above is realized when being executed by processor.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or device including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, method, article or device institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Other identical element also be present in the process of key element, method, article or device.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions to cause a station terminal equipment (can be mobile phone,
Computer, server, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of operating method of TV, it is characterised in that the operating method of the TV comprises the following steps：
When receiving the operation requests of television set transmission, the operation requests are parsed, and in the operation requests of the parsing
Extract the phonetic order of the device identification of the television set, the vocal print feature of user and user；
It is determined that vocal print cluster identity corresponding with the device identification, and the vocal print according to corresponding to determining the vocal print cluster identity
Cluster；
It is determined that after the vocal print cluster, the vocal print feature is compared with the sound-groove model in the vocal print cluster, with
The identity information of user is determined, wherein, the vocal print cluster contains the sound-groove model of multiple users；
According to response data corresponding to the phonetic order and identity information generation, and the response data is fed back to
The television set.
2. the operating method of TV as claimed in claim 1, it is characterised in that described by the vocal print feature and the vocal print
Sound-groove model in cluster is compared, to include the step of determining the identity information of user：
The vocal print feature and the matching degree of each sound-groove model in the vocal print cluster are calculated, wherein, the sound-groove model pair
Answer the subscriber identity information；
Obtain subscriber identity information corresponding to the maximum sound-groove model of matching degree.
3. the operating method of TV as claimed in claim 2, it is characterised in that described to calculate the vocal print feature and the sound
In line cluster the step of the matching degree of each sound-groove model after, in addition to：
Judge whether each matching degree is more than or equal to predetermined threshold value；
When there is the matching degree to be more than or equal to predetermined threshold value, the step for obtaining the maximum sound-groove model of matching degree is performed
Suddenly.
4. the operating method of TV as claimed in claim 1, it is characterised in that the vocal print according in the vocal print cluster
After the step of model determines subscriber identity information with the vocal print feature, in addition to：
Control authority corresponding to the subscriber identity information is obtained, and judges whether the phonetic order is in the control authority
In the range of corresponding control instruction；
When judging that the phonetic order is in the range of the control instruction of the control authority, perform described according to the voice
Corresponding to instruction and the identity information generation the step of response data.
5. the operating method of TV as claimed in claim 1, it is characterised in that the vocal print according in the vocal print cluster
After the step of model determines subscriber identity information with the vocal print feature, in addition to：
Current point in time is obtained, and obtains control authority corresponding with the current point in time；
Control instruction scope corresponding with the control authority is obtained, and judges whether the phonetic order is in the control
Corresponding to limit in the range of control instruction；
When judging that the phonetic order is in the range of the control instruction of the control authority, perform described according to the voice
Corresponding to instruction and the identity information generation the step of response data.
6. the operating method of the TV as described in claim 4 or 5, it is characterised in that described whether to judge the phonetic order
After the step of in the range of control instruction in the control authority, in addition to：
When judging that the phonetic order is not in the range of the control instruction of the control authority, to the subscriber identity information
The default terminal of association sends prompt message.
7. the operating method of the TV as described in claim any one of 1-5, it is characterised in that the operating method of the TV,
Also include：
After the generation request for the vocal print cluster that the television set is sent is received, according to TV described in the generation acquisition request
The device identification of machine and pending vocal print cluster；
Generation vocal print cluster identity corresponding with the pending vocal print cluster；
The mapping relations of the device identification and the vocal print cluster identity are established, and preserves the mapping relations, described wait to locate
Vocal print cluster, the vocal print cluster identity and the device identification are managed, to generate the vocal print cluster.
8. a kind of operation device of TV, it is characterised in that the operation device of the TV includes memory, processor and storage
On the memory and the operation sequence of TV that can run on the processor, the operation sequence of the TV are described
The step of operating method of the TV as described in claim any one of 1-7 is realized during computing device.
9. a kind of operating system of TV, it is characterised in that the operating system of the TV includes television set, server and TV
Operation device, wherein,
The server, for when receiving the operation requests of television set transmission, parsing the operation requests, and in the solution
The phonetic order of the device identification of the television set, the vocal print feature of user and user is extracted in the operation requests of analysis, it is determined that
Vocal print cluster identity corresponding with the device identification, and the vocal print cluster according to corresponding to determining the vocal print cluster identity,
After determining the vocal print cluster, the vocal print feature is compared with the sound-groove model in the vocal print cluster, to determine to use
The identity information at family, wherein, the vocal print cluster contains the sound-groove model of multiple users, according to the phonetic order and described
Response data corresponding to identity information generation, and the response data is fed back into the television set；
The television set, for when receiving the phonetic order of user's transmission, the sound of user to be extracted according to the phonetic order
Line feature, and the device identification of television set is obtained, given birth to according to the phonetic order, the device identification and the vocal print feature
The operation requests are sent into operation requests, and to the server.
A kind of 10. storage medium, it is characterised in that the operation sequence of TV is stored with the storage medium, the TV
The step of operating method of the TV as any one of claim 1 to 7 is realized when operation sequence is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710793303.7A CN107580237A (en) | 2017-09-05 | 2017-09-05 | Operating method, device, system and the storage medium of TV |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710793303.7A CN107580237A (en) | 2017-09-05 | 2017-09-05 | Operating method, device, system and the storage medium of TV |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107580237A true CN107580237A (en) | 2018-01-12 |
Family
ID=61029957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710793303.7A Pending CN107580237A (en) | 2017-09-05 | 2017-09-05 | Operating method, device, system and the storage medium of TV |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107580237A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109524013A (en) * | 2018-12-18 | 2019-03-26 | 北京猎户星空科技有限公司 | A kind of method of speech processing, device, medium and smart machine |
| CN109729400A (en) * | 2018-06-27 | 2019-05-07 | 平安科技（深圳）有限公司 | Apparatus control method, device, equipment and storage medium based on sound |
| CN109799719A (en) * | 2019-01-31 | 2019-05-24 | 广东美的制冷设备有限公司 | Control method, server, household appliance and the storage medium of household appliance |
| WO2019141028A1 (en) * | 2018-01-22 | 2019-07-25 | 珠海格力电器股份有限公司 | Control method, device and system for electrical device |
| CN110324711A (en) * | 2019-05-22 | 2019-10-11 | 苏州乐轩科技有限公司 | TV functions management method based on recognition of face |
| CN110719512A (en) * | 2019-09-23 | 2020-01-21 | 中移（杭州）信息技术有限公司 | Intelligent remote controller control method and device, intelligent remote controller and storage medium |
| CN111081249A (en) * | 2019-12-30 | 2020-04-28 | 腾讯科技（深圳）有限公司 | Mode selection method, device and computer readable storage medium |
| CN111161741A (en) * | 2019-12-19 | 2020-05-15 | 五八有限公司 | Personalized information identification method and device, electronic equipment and storage medium |
| WO2020135241A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳Tcl新技术有限公司 | Voice-based data transmission control method, smart television and storage medium |
| CN111613217A (en) * | 2020-04-02 | 2020-09-01 | 深圳创维－Rgb电子有限公司 | Equipment recommendation method and device, electronic equipment and readable storage medium |
| CN111641875A (en) * | 2020-05-21 | 2020-09-08 | 广州欢网科技有限责任公司 | Method, device and system for analyzing family members by smart television |
| CN112312181A (en) * | 2019-07-26 | 2021-02-02 | 深圳Tcl新技术有限公司 | Smart television voice recognition method, system and readable storage medium |
| CN112423063A (en) * | 2020-11-03 | 2021-02-26 | 深圳Tcl新技术有限公司 | Automatic setting method and device for smart television and storage medium |
| CN112820302A (en) * | 2021-01-28 | 2021-05-18 | Oppo广东移动通信有限公司 | Voiceprint recognition method and device, electronic equipment and readable storage medium |
| CN114598932A (en) * | 2020-12-04 | 2022-06-07 | 深圳Tcl新技术有限公司 | Program recommendation method, terminal and storage medium |
| CN114724566A (en) * | 2022-04-18 | 2022-07-08 | 中国第一汽车股份有限公司 | Voice processing method, device, storage medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102098584A (en) * | 2009-12-11 | 2011-06-15 | Tcl集团股份有限公司 | Monitoring method of network television program |
| CN102142254A (en) * | 2011-03-25 | 2011-08-03 | 北京得意音通技术有限责任公司 | Voiceprint identification and voice identification-based recording and faking resistant identity confirmation method |
| CN102662961A (en) * | 2012-03-08 | 2012-09-12 | 北京百舜华年文化传播有限公司 | Method, apparatus and terminal unit for matching semantics with image |
| US20140258324A1 (en) * | 2013-03-06 | 2014-09-11 | Nuance Communications, Inc. | Task assistant utilizing context for improved interaction |
| CN105049882A (en) * | 2015-08-28 | 2015-11-11 | 北京奇艺世纪科技有限公司 | Method and device for video recommendation |
| CN105791935A (en) * | 2016-05-03 | 2016-07-20 | 乐视控股（北京）有限公司 | Television control method and apparatus thereof |
-
2017
- 2017-09-05 CN CN201710793303.7A patent/CN107580237A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102098584A (en) * | 2009-12-11 | 2011-06-15 | Tcl集团股份有限公司 | Monitoring method of network television program |
| CN102142254A (en) * | 2011-03-25 | 2011-08-03 | 北京得意音通技术有限责任公司 | Voiceprint identification and voice identification-based recording and faking resistant identity confirmation method |
| CN102662961A (en) * | 2012-03-08 | 2012-09-12 | 北京百舜华年文化传播有限公司 | Method, apparatus and terminal unit for matching semantics with image |
| US20140258324A1 (en) * | 2013-03-06 | 2014-09-11 | Nuance Communications, Inc. | Task assistant utilizing context for improved interaction |
| CN105049882A (en) * | 2015-08-28 | 2015-11-11 | 北京奇艺世纪科技有限公司 | Method and device for video recommendation |
| CN105791935A (en) * | 2016-05-03 | 2016-07-20 | 乐视控股（北京）有限公司 | Television control method and apparatus thereof |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019141028A1 (en) * | 2018-01-22 | 2019-07-25 | 珠海格力电器股份有限公司 | Control method, device and system for electrical device |
| CN109729400A (en) * | 2018-06-27 | 2019-05-07 | 平安科技（深圳）有限公司 | Apparatus control method, device, equipment and storage medium based on sound |
| CN109524013A (en) * | 2018-12-18 | 2019-03-26 | 北京猎户星空科技有限公司 | A kind of method of speech processing, device, medium and smart machine |
| CN109524013B (en) * | 2018-12-18 | 2022-07-22 | 北京猎户星空科技有限公司 | Voice processing method, device, medium and intelligent equipment |
| CN111385624A (en) * | 2018-12-29 | 2020-07-07 | 深圳Tcl新技术有限公司 | Voice-based data transmission control method, smart television and storage medium |
| WO2020135241A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳Tcl新技术有限公司 | Voice-based data transmission control method, smart television and storage medium |
| CN111385624B (en) * | 2018-12-29 | 2021-10-01 | 深圳Tcl新技术有限公司 | Voice-based data transmission control method, smart television and storage medium |
| CN109799719B (en) * | 2019-01-31 | 2021-01-08 | 广东美的制冷设备有限公司 | Control method of household appliance, server, household appliance and storage medium |
| CN109799719A (en) * | 2019-01-31 | 2019-05-24 | 广东美的制冷设备有限公司 | Control method, server, household appliance and the storage medium of household appliance |
| CN110324711A (en) * | 2019-05-22 | 2019-10-11 | 苏州乐轩科技有限公司 | TV functions management method based on recognition of face |
| CN112312181A (en) * | 2019-07-26 | 2021-02-02 | 深圳Tcl新技术有限公司 | Smart television voice recognition method, system and readable storage medium |
| CN110719512A (en) * | 2019-09-23 | 2020-01-21 | 中移（杭州）信息技术有限公司 | Intelligent remote controller control method and device, intelligent remote controller and storage medium |
| CN111161741A (en) * | 2019-12-19 | 2020-05-15 | 五八有限公司 | Personalized information identification method and device, electronic equipment and storage medium |
| CN111161741B (en) * | 2019-12-19 | 2023-06-27 | 五八有限公司 | Personalized information identification method and device, electronic equipment and storage medium |
| CN111081249A (en) * | 2019-12-30 | 2020-04-28 | 腾讯科技（深圳）有限公司 | Mode selection method, device and computer readable storage medium |
| CN111613217A (en) * | 2020-04-02 | 2020-09-01 | 深圳创维－Rgb电子有限公司 | Equipment recommendation method and device, electronic equipment and readable storage medium |
| CN111641875A (en) * | 2020-05-21 | 2020-09-08 | 广州欢网科技有限责任公司 | Method, device and system for analyzing family members by smart television |
| CN112423063A (en) * | 2020-11-03 | 2021-02-26 | 深圳Tcl新技术有限公司 | Automatic setting method and device for smart television and storage medium |
| CN114598932A (en) * | 2020-12-04 | 2022-06-07 | 深圳Tcl新技术有限公司 | Program recommendation method, terminal and storage medium |
| CN112820302A (en) * | 2021-01-28 | 2021-05-18 | Oppo广东移动通信有限公司 | Voiceprint recognition method and device, electronic equipment and readable storage medium |
| CN112820302B (en) * | 2021-01-28 | 2024-04-12 | Oppo广东移动通信有限公司 | Voiceprint recognition method, voiceprint recognition device, electronic equipment and readable storage medium |
| CN114724566A (en) * | 2022-04-18 | 2022-07-08 | 中国第一汽车股份有限公司 | Voice processing method, device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107580237A (en) | Operating method, device, system and the storage medium of TV | |
| US11189263B2 (en) | Voice data processing method, voice interaction device, and storage medium for binding user identity with user voice model | |
| CN108900923B (en) | Method and device for recommending live broadcast template | |
| US10650816B2 (en) | Performing tasks and returning audio and visual feedbacks based on voice command | |
| CN108683574B (en) | Equipment control method, server and intelligent home system | |
| CN109308357B (en) | Method, device and equipment for obtaining answer information | |
| WO2018036555A1 (en) | Session processing method and apparatus | |
| US10284705B2 (en) | Method and apparatus for controlling smart device, and computer storage medium | |
| CN105654950A (en) | Self-adaptive voice feedback method and device | |
| US20150310855A1 (en) | Voice recognition device and method of controlling same | |
| CN110164415A (en) | A kind of recommended method based on speech recognition, device and medium | |
| CN107655154A (en) | Terminal control method, air conditioner and computer-readable recording medium | |
| CN104078045A (en) | Identifying method and electronic device | |
| EP2747464A1 (en) | Sent message playing method, system and related device | |
| CN106559694A (en) | A kind of method and device that user's admission scene is rendered for online direct broadcasting room | |
| CN111222044A (en) | Information recommendation method and device based on emotion perception and storage medium | |
| CN112185362A (en) | Voice processing method and device for user personalized service | |
| CN110909241B (en) | Information recommendation method, user identification recommendation method, device and equipment | |
| CN110147481B (en) | Media content pushing method and device and storage medium | |
| CN106878449B (en) | Apparatus control method and device | |
| CN103634321B (en) | Voice recognition result display method and device | |
| CN115273828A (en) | Training method and device of voice intention recognition model and electronic equipment | |
| CN112820265B (en) | Speech synthesis model training method and related device | |
| CN111552794B (en) | Prompt generation method, device, equipment and storage medium | |
| CN109391537A (en) | A kind of information processing method, device and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180112 |