Summary of the invention
The embodiment of the present invention provides a kind of program commending method and device, it is possible to solves to lose time in correlation technique, and uses
Bad problem is experienced during the viewing program of family.
First aspect according to embodiments of the present invention, it is provided that a kind of program commending method, including:
Receive the voice messaging of user's input;
Voiceprint is extracted from described voice messaging;
Resolve described voiceprint and obtain the age bracket of described user;
The program matched with described age bracket is defined as program to be recommended;
Show described program to be recommended.
Preferably, after extracting voiceprint from described voice messaging, described method also includes:
Range data and the tone data of described user is obtained from described voiceprint;
The eigenvalue of described user it is calculated according to described range data and described tone data;
Judge whether to store the program identification of playing content corresponding with described eigenvalue;
If storage has the program identification of playing content corresponding with described eigenvalue, show the joint that described program identification is corresponding
Mesh;
If not storing the program identification of playing content corresponding with described eigenvalue, performing to resolve described voiceprint and obtaining
Step to the age bracket of described user.
Preferably, after the described program to be recommended of described display, described method also includes:
Receive the first search voice of user's input;
Identify the Word message that described first search voice is corresponding;
Read programme type identification included in described Word message;
From described program to be recommended, screening meets the program of described programme type identification as target program;
Show described target program.
Preferably, after the described program to be recommended of described display, described method also includes:
Receive the second search voice of user's input;
Identify the Word message that described second search voice is corresponding;
Read program key word included in described Word message;
Program corresponding for described program key word is defined as appointed program;
Show described appointed program.
Preferably, after the described voice messaging receiving user's input, described method also includes:
Identify the Word message that described voice messaging is corresponding;
When described Word message includes start mark, perform power-on operation.
Second aspect, the embodiment of the present invention additionally provides a kind of program recommendation apparatus, and described device includes:
First receiver module, for receiving the voice messaging of user's input;
Extraction module, for extracting voiceprint from described voice messaging;
Parsing module, obtains the age bracket of described user for resolving described voiceprint;
First determines module, for the program matched with described age bracket is defined as program to be recommended;
First display module, is used for showing described program to be recommended.
Preferably, described device also includes: acquisition module, computing module, judge module and the second display module, wherein,
Described acquisition module, for obtaining range data and the tone data of described user from described voiceprint;
Described computing module, for being calculated the feature of described user according to described range data and described tone data
Value;
Described judge module, for judging whether to store the program identification of playing content corresponding with described eigenvalue;
Described second display module, is used for when storage has the program identification of playing content corresponding with described eigenvalue,
Show the program that described program identification is corresponding;
Described parsing module, is additionally operable to when not storing the program identification of playing content corresponding with described eigenvalue, solves
Analyse described voiceprint and obtain the age bracket of described user.
Preferably, described device also includes: the second receiver module, the first identification module, the first read module, screening module
With the 3rd display module, wherein,
Described second receiver module, for receiving the first search voice of user's input;
Described first identification module, for identifying the Word message that described first search voice is corresponding;
Described first read module, for reading programme type identification included in described Word message;
Described screening module, meets the program of described programme type identification as mesh for screening from described program to be recommended
Mark program;
Described 3rd display module, is used for showing described target program.
Preferably, described device also includes: the 3rd receiver module, the second identification module, the second read module, second determine
Module and the 4th display module, wherein,
Described 3rd receiver module, for receiving the second search voice of user's input;
Described second identification module, for identifying the Word message that described second search voice is corresponding;
Described second read module, for reading program key word included in described Word message;
Described second determines module, for program corresponding for described program key word is defined as appointed program;
Described 4th display module, is used for showing described appointed program.
Preferably, described device also includes: the 3rd identification module and execution module, wherein,
Described 3rd identification module, for identifying the Word message that described voice messaging is corresponding;
Described execution module, for when described Word message includes start mark, performing power-on operation.
Compared with prior art, the technical scheme that the present embodiment provides has the following advantages and feature:
In the scheme that the embodiment of the present invention provides, intelligent television can be that user recommends program according to the voice of user, tool
Body, intelligent television receives the voice messaging of user's input, then, extracts voiceprint, go forward side by side from described voice messaging
One step, resolves described voiceprint and obtains the age bracket of described user.Due to the user of different age group, it is suitable for and likes
Program also differs, and therefore, the program matched with described age bracket is defined as program to be recommended by this programme, and shows institute
State program to be recommended.As can be seen here, the technical scheme of the embodiment of the present invention, it is possible to according to the voice of different user input, for phase
Answer user's being customized program to recommend, thus can not only automatically recommend program, and can shorten user search program time
Between, and then user can be improved watch the experience of program.
Detailed description of the invention
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
Description, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments.Base
Embodiment in the present invention, it is all that those of ordinary skill in the art are obtained under not making creative work premise
Other embodiments, broadly fall into the scope of protection of the invention.
The method flow diagram of a kind of program commending method that Fig. 1 provides for the embodiment of the present invention.Program shown in Fig. 1 is recommended
Method can be that user recommends program according to the voice of user, thus improve user and watch the experience of program.The method bag
Include following steps.
Step S101, the voice messaging of reception user's input.
Wherein, in correlation technique, intelligent television itself and remote controller thereof are provided with speech reception module, and user can be led to
Cross the speech reception module of remote controller or intelligent television to intelligent television input voice information.In the embodiment of this programme,
Intelligent television, after receiving the voice messaging of user's input, can perform corresponding behaviour according to the order that voice messaging is comprised
Make, concrete, description as described below.It should be noted that the premise that intelligent television is able to receive that voice messaging is, intelligence
Power-up state can be in by TV.
It should be noted that in the technical scheme of the embodiment of the present invention, intelligent television, can after receiving voice messaging
To calculate the characteristic vector of each pronunciation in voice messaging respectively, it is then possible to the characteristic vector that will identify that and template
Characteristic vector template in storehouse carries out similarity-rough set, and using defeated as recognition result for characteristic vector template the highest for similarity
Go out, thus identify the Word message that voice messaging is corresponding, and determined the mark of order by the content of Word message, enter
And the corresponding command can be performed according to command id.Wherein, speech recognition technology is skill well-known to those skilled in the art
Art, the embodiment of the present invention the most no longer describes in detail.
Based on foregoing description, intelligent television can pre-build the corresponding relation of command id and pending operation, thus
After Word message reads command id, it is possible to automatically perform corresponding operating.Concrete, if intelligent television is currently located
Can include start mark in off-mode, Word message, intelligent television can trigger start automatically according to start mark
Module, performs power-on operation;Accordingly, after intelligent television start, when user's defeated shutdown voice, Word message includes
During shutdown mark, intelligent television can trigger shutdown module automatically according to shutdown mark, performs power-off operation.
Such as, when, after the voice messaging of user's input " super television startup ", intelligent television can be by speech recognition
Voice messaging is converted to Word message " super television startup " by mode such that it is able to identifies start mark word and " starts shooting ",
And then, " start shooting " according to word and the corresponding relation of power-on operation, call starting module, perform power-on operation;For another example,
When, after the voice messaging of user's input " super television shutdown ", intelligent television can be by voice by the way of speech recognition
Information is converted to Word message " super television shutdown " such that it is able to identifies shutdown mark word and " shuts down ", and then,
" shut down " according to word and the corresponding relation of power-off operation, call shutdown module, perform power-off operation.
Step S102, from described voice messaging extract voiceprint.
Wherein, voiceprint is as the sound wave spectrum of speaker, it is possible to embody the wavelength of speaker's sound, frequency, intensity
With the information such as rhythm, therefore, by the voiceprint of speaker is analyzed, it is possible to detect speaker sex,
The features such as age and life area.Based on this, this programme can extract voiceprint from the voice messaging of user's input,
And then the feature of user can be determined by voiceprint.It should be noted that in the present embodiment, the feature of user is permissible
Including age bracket and the sex of user of user, the embodiment of the present invention is without limitation.
Concrete, sound is generally propagated by the way of sound wave, therefore, and intelligent television received speech information essence
On be the sound wave of user speech, after the sound wave receiving user speech, the change of sound wave can be changed by intelligent television
Become the change of the intensity of the signal of telecommunication, wavelength, frequency and rhythm etc., and characterize the intensity of the signal of telecommunication, wavelength, frequency and joint
The change wave spectrogram played etc., is vocal print figure, and the information that vocal print figure is embodied is voiceprint.Wherein it is desired to explanation
, extract the method for voiceprint and technology that process is well known to the skilled person, the embodiment of the present invention this
Place is no longer described in detail.
Step S103, resolve described voiceprint and obtain the age bracket of described user.
Wherein, according to the description of above-described embodiment, voiceprint can characterize the individual characteristics of user, therefore,
After the voiceprint of the voice messaging extracting user's input, the range data of user can be obtained by resolving voiceprint
And tone data, and owing to the sound of the user of different age group takes on a different character, therefore, the use of different age group
The range data at family and tone data, after preset algorithm computing, can obtain different eigenvalues, and according to described spy
Value indicative can determine age of user section.
It should be noted that range data specifically can include pitch and the duration of a sound, tone data specifically can include loudness of a sound and
Tone color, and pitch, the duration of a sound, loudness of a sound and tone color can directly obtain from voiceprint.Additionally, technical staff can be pre-
First gather the pitch of the speaker of known age bracket, the duration of a sound, loudness of a sound and tone color, and be trained such that it is able to used
The algorithm model of family eigenvalue, and different age group characteristic of correspondence value scope.Therefore, in this programme, intelligent television
Algorithm model can be directly inputted and is calculated the feature of user after the range data obtaining user and tone data
Value.
Additionally, due to the purpose of this programme is to recommend program by the feature of user, therefore, it can by age bracket according to
Video frequency program is suitable for the crowd of viewing and divides, and such as, video frequency program can be divided into according to the crowd of applicable viewing always
Year class program, middle age class program, young class program and juvenile's class program, then, age bracket can be divided into by this programme
Old age, middle age, young and juvenile four sections.Certainly, above are only the preferred exemplary of the present invention, the skill of the embodiment of the present invention
Art scheme is not limited to this.
Step S104, the program matched with described age bracket is defined as program to be recommended.
Wherein it is desired to explanation, for the ease of management video frequency program, each setting of the programs has attribute tags, described genus
Property label can include the letter such as programm name, programme type identification, collection number, duration, viewing number of times and applicable age bracket
Breath, therefore, after determining age of user section, intelligent television can travel through the applicable age bracket of each program, and will be with
The program that the age bracket of user matches determines program to be recommended.
Such as, user is the child of 10 years old, after intelligent television receives the voice messaging of user's input, identifies user
Age bracket belong to juvenile, therefore, it can being suitable for age bracket in attribute information is that the program of juvenile is defined as joint to be recommended
Mesh, such as, program to be recommended can include that liking sheep sheep works together and big with ash too wolf, happy celestial body, tree of knowledge, dream star
The programs such as windmill.
Certainly, when the voice messaging of user's input does not comprises any programme information, the technical scheme of the embodiment of the present invention,
The condition can recommended using the age bracket of user as program, such as, current intelligent television is in off-mode, and user is defeated
The voice messaging entered is " super television startup ", owing to not comprising any programme information, therefore, Intelligent electric in voice messaging
Obtain the age bracket of user depending on voice messaging " super television startup " can be passed through, thus be user by age of user section
Recommend program.And when the voice messaging of user's input includes programme information, intelligent television can also be further according to program
Information is that user recommends program.
Furthermore, it is necessary to explanation, the quantity of program to be recommended may have multiple, therefore, in the present embodiment, and Intelligent electric
After apparent determines program to be recommended, further, it is also possible to by program to be recommended according to viewing number of times order from more to less
It is sequentially arranged, thus by program preferential recommendation the highest for temperature to user, to improve Consumer's Experience.
Step S105, show described program to be recommended.
Wherein, when intelligent television determines program to be recommended, and after program to be recommended being sorted according to viewing number of times, can be by
Program to be recommended is shown, in order to user selects to watch the program oneself liked according to default order.
It should be noted that in order to improve Consumer's Experience further, intelligent television is after powering, it is also possible to continue to use
The program searching voice of family input, it is possible to recommend program to user according to the content of program searching voice.Concrete, when
After intelligent television obtains program to be recommended according to the screening of age of user section, if user's input comprises the joint of programme type identification
Mesh search voice, in embodiments of the present invention, the referred to as first search voice.Intelligent television can also identify the first search phrase
The Word message that sound is corresponding, and read the programme type identification that corresponding Word message is comprised, then, further, can
To screen the program being consistent with programme type identification from program to be recommended, the program screened is defined as target program,
And show described target program.
Such as, user is the child of 10 years old, when intelligent television is after user recommends some row programs according to age bracket, uses
Family input voice " super TV, I to watch animated films ", then, intelligent television will screen animation from the program recommended
Sheet, for example, it is possible to include liking sheep sheep and ash too wolf, RNB and major part son father microcephaly etc., and will be screened
Cartoon is shown to user.
Additionally, user can also input the voice messaging comprising program key word, in embodiments of the present invention, referred to as second
Search voice.Same, intelligent television, after receiving the second search voice, can identify that the second search voice is corresponding
Word message, and from corresponding Word message, read program key word, it is then possible to by program corresponding for program key word
It is defined as appointed program, and shows this appointed program.Such as, after intelligent television shows program to be recommended, user's input is " super
TV, I to see happy celestial body ", then, intelligent television after identifying program key word " happy celestial body ", search attribute
Information includes the program of program key word " happy celestial body ", and display searches program.
It is pointed out that owing to program to be recommended obtains according to the age bracket screening of user, and the program that user wants viewing can
Can be not included in program to be recommended, such as, the program key word of user's input of 10 years old is " Song of Joy ", and TV play is " joyous
Happy song " it is not included in program to be recommended, therefore, intelligent television, can be in program database after identifying program key word
In directly search the program comprising program key word.
As can be seen here, in the embodiment shown in fig. 1, intelligent television can determine use according to the voice of different user input
The age bracket at family, and be that relative users being customized program is recommended according to age bracket, thus can not only automatically recommend program,
And user can be shortened and search joint object time, and then user can be improved watch the experience of program.
Certainly, above-described embodiment is one embodiment of the present invention, in order to make those skilled in the art clearer, complete
The technical scheme of the understanding embodiment of the present invention in face, is carried out the technical scheme of the embodiment of the present invention from another angle below
Describe.
Refer to the method flow diagram of the another kind of program commending method that Fig. 2, Fig. 2 provide for the embodiment of the present invention, wherein,
Embodiment shown in Fig. 2 is the embodiment of another angle based on Fig. 1 embodiment, so the content identical with Fig. 1
Can be found in the embodiment shown in Fig. 1.Based on the embodiment shown in Fig. 1, the embodiment shown in Fig. 2 after step s 102,
Can also comprise the following steps:
Step S106, the range data obtaining described user from described voiceprint and tone data.
Wherein, description based on above-described embodiment understands, and voiceprint can be from sides such as intensity, wavelength, frequency and rhythm
Face express user voice messaging, and according to intensity, wavelength, frequency and rhythm can obtain the pitch of user, the duration of a sound,
The data such as loudness of a sound and tone color such that it is able to obtain range data and the tone data of user further.
Step S107, it is calculated the eigenvalue of described user according to described range data and described tone data.
Wherein, concrete, the range data of user and tone data can be inputted in the algorithm model preset, be calculated
The eigenvalue of user.
It should be noted that owing to everyone sound all distinguishes the sound with other people, therefore, sound has with speaker
Having unique corresponding relation, therefore, the eigenvalue of user can uniquely characterize this user.
Step S108, judge whether to store the program identification of playing content corresponding with described eigenvalue, if storage have with
The program identification playing content that eigenvalue is corresponding, performs step S109;If not storing the broadcasting content corresponding with eigenvalue
Program identification, perform step S103.
Step S109, show the program that described program identification is corresponding.
Wherein, in the present embodiment, obtain the voice messaging of user during intelligent television start, and can be calculated this
The eigenvalue of user, owing to eigenvalue can uniquely characterize this user, therefore, in order to improve Consumer's Experience further, this
In embodiment, respectively each eigenvalue can be defined as a user, and corresponding this user of storage play in part
Hold the program identification corresponding to program, after intelligent television is calculated the eigenvalue of this user, can by with eigenvalue
The program corresponding to program identification of corresponding storage recommends user, thus searches program without the user effort time.
Such as, during this start of user A, intelligent television calculates and stores the eigenvalue A001 of user A, character pair
The content that value A001 intelligent television was play last time includes variety show " wonderful work says the second phase third quarter " and TV play " Mi
Pass the 11st collection, the 12nd collection and the 13rd collection the moon ", therefore, intelligent television is by variety show " wonderful work says the third quarter "
Storage corresponding with eigenvalue A001 with the program identification of TV play " the Mi month passes ", when intelligent television, this is calculated feature
During value A001, directly display variety show corresponding to the program identification stored " wonderful work says the third quarter " and TV play " Mi
The moon passes ".
If additionally, intelligent television does not find this feature value, or, corresponding this feature value does not store any program
Mark, then resolve the age bracket obtaining user, and be that user recommends program according to age bracket according to user's characteristic of correspondence value,
Concrete, referring to the description of above-described embodiment, here is omitted for the present embodiment.Certainly, in the present embodiment, Yong Hudian
After hitting the arbitrary programme content of broadcasting, intelligent television stores corresponding with eigenvalue for corresponding for the content play program identification,
So that during start next time, directly recommending its program interested for this user.
Such as, user B uses intelligent television for the first time, now, does not stores the eigenvalue B002 of user B in intelligent television,
And do not store the program identification corresponding with eigenvalue B002, then, intelligent television storage B002, and this is play
Variety show " the ultimate challenge second season " and program identification corresponding to TV play " Song of Joy ", as eigenvalue B002
Corresponding program identification stores, when user B starts shooting next time, by variety show " the ultimate challenge second season " and
User B is recommended in TV play " Song of Joy ".
It should be noted that TV programme are usually provided with collection number, after finishing, user may will not review
This program, additionally, when certain program just broadcasts, user may watch, but this program user may will not feel emerging
Interest, will not watch later, and therefore, what intelligent television also can record that program corresponding to each program identification do not play continues
Duration, the duration do not play when certain program reaches certain value, such as, and week age, then delete the joint of this program
Target is known.
As can be seen here, the technical scheme of the embodiment of the present invention, intelligent television can be that user recommends joint according to the voice of user
Mesh, concrete, intelligent television receives the voice messaging of user's input, then, extracts voiceprint from described voice messaging,
And further, resolve described voiceprint and obtain the age bracket of described user.Due to the user of different age group, it is suitable for and happiness
Joyous program also differs, and therefore, the program matched with described age bracket is defined as program to be recommended by this programme, and shows
Show described program to be recommended.As can be seen here, the technical scheme of the embodiment of the present invention, it is possible to according to the voice of different user input,
Recommend for relative users being customized program, thus can not only automatically recommend program, and user can be shortened and search program
Time, and then user can be improved watch the experience of program.
Corresponding with above-mentioned implementation method, the embodiment of the present invention additionally provides a kind of program recommendation apparatus.Refer to Fig. 3,
The schematic diagram of a kind of program recommendation apparatus that Fig. 3 provides for the embodiment of the present invention.This device includes the first receiver module 11, carries
Delivery block 12, parsing module 13, first determine module 14 and the first display module 15, wherein:
First receiver module 11, for receiving the voice messaging of user's input.
Extraction module 12, for extracting voiceprint from described voice messaging.
Parsing module 13, obtains the age bracket of described user for resolving described voiceprint.
First determines module 14, for the program matched with described age bracket is defined as program to be recommended.
First display module 15, is used for showing described program to be recommended.
Additionally, the device that the embodiment of the present invention provides can also include with lower module: acquisition module, computing module, judgement
Module and the second display module, wherein,
Described acquisition module, for obtaining range data and the tone data of described user from described voiceprint.
Described computing module, for being calculated the feature of described user according to described range data and described tone data
Value.
Described judge module, for judging whether to store the program identification of playing content corresponding with described eigenvalue.
Described second display module, is used for when storage has the program identification of playing content corresponding with described eigenvalue,
Show the program that described program identification is corresponding;When not storing the program identification of playing content corresponding with described eigenvalue,
Trigger parsing module 13.
On the basis of above-described embodiment, described device also includes, the second receiver module, the first identification module, the first reading
Module, screening module and the 3rd display module, wherein,
Described second receiver module, for receiving the first search voice of user's input.
Described first identification module, for identifying the Word message that described first search voice is corresponding.
Described first read module, for reading programme type identification included in described Word message.
Described screening module, meets the program of described programme type identification as mesh for screening from described program to be recommended
Mark program.
Described 3rd display module, is used for showing described target program.
On the basis of above-described embodiment, in another embodiment, described device also includes: the 3rd receiver module,
Two identification modules, the second read module, second determine module and the 4th display module, wherein,
Described 3rd receiver module, for receiving the second search voice of user's input.
Described second identification module, for identifying the Word message that described second search voice is corresponding.
Described second read module, for reading program key word included in described Word message.
Described second determines module, for program corresponding for described program key word is defined as appointed program.
Described 4th display module, is used for showing described appointed program.
In another embodiment, described device also includes: the 3rd identification module and execution module, wherein,
Described 3rd identification module, for identifying the Word message that described voice messaging is corresponding.
Described execution module, for when described Word message includes start mark, performing power-on operation.
About the device in above-described embodiment, wherein modules performs the concrete mode of operation in relevant the method
Embodiment is described in detail, explanation will be not set forth in detail herein.
Summary, in the scheme that the embodiment of the present invention provides, intelligent television can be that user pushes away according to the voice of user
Recommending program, concrete, intelligent television receives the voice messaging of user's input, then, extracts vocal print from described voice messaging
Information, and further, resolve described voiceprint and obtain the age bracket of described user.Due to the user of different age group, suitable
Closing and the program liked also differs, therefore, the program matched with described age bracket is defined as program to be recommended by this programme,
And show described program to be recommended.As can be seen here, the technical scheme of the embodiment of the present invention, it is possible to according to the language of different user input
Sound, recommends for relative users being customized program, thus can not only automatically recommend program, and can shorten user's lookup
Joint object time, and then user can be improved watch the experience of program.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art, in the technical scope that the invention discloses, can readily occur in change or replace, answering
Contain within protection scope of the present invention.Therefore, protection scope of the present invention should be described with scope of the claims
It is as the criterion.