CN103984415B - A kind of information processing method and electronic equipment - Google Patents
A kind of information processing method and electronic equipment Download PDFInfo
- Publication number
- CN103984415B CN103984415B CN201410211567.3A CN201410211567A CN103984415B CN 103984415 B CN103984415 B CN 103984415B CN 201410211567 A CN201410211567 A CN 201410211567A CN 103984415 B CN103984415 B CN 103984415B
- Authority
- CN
- China
- Prior art keywords
- data
- image
- input voice
- module
- identity
- 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.)
- Active
Links
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of information processing method and electronic equipment, the technical problem for solving the personal pronoun that electronic equipment can not correctly in voice command recognition.This method is applied in electronic equipment, and methods described includes:Obtain input voice;The input voice is recognized by speech recognition engine;When identifying that the input voice includes personal pronoun, the first data are obtained;The referents that the personal pronoun is referred to are determined based on first data;Perform operational order based on the referents, wherein, the operational order for it is described the input voice is recognized by speech recognition engine after, the corresponding instruction of the input voice that the speech recognition engine is identified.
Description
Technical field
The present invention relates to electronic technology field, more particularly to a kind of information processing method and electronic equipment.
Background technology
At present, the intelligent electronic device such as tablet personal computer, smart mobile phone, intelligent watch can recognize and perform user
Voice command, enrich the interactive mode of user and electronic equipment, bring advantage to the user.
But present inventor has found that above-mentioned prior art at least has following technical problem:
In the voice command that electronic equipment is obtained, personal pronoun may be included, and electronic equipment is difficult to determine the person
The referents that pronoun is referred to, causing the voice command of user can not be executed correctly.
The content of the invention
The application provides a kind of information processing method and electronic equipment, for solving there is electronic equipment in the prior art not
The technical problem of personal pronoun that can be in correct voice command recognition, realizes the identification of lifting electronic equipment, performs voice command
Ability, and then improve the usage experience of user.
On the one hand the embodiment of the present application provides a kind of information processing method, applied in electronic equipment, methods described bag
Include:Obtain input voice;The input voice is recognized by speech recognition engine;Identify it is described input voice include people
When claiming pronoun, the first data are obtained, including:Identifying that the input voice includes personal pronoun and the personal pronoun belongs to
When Equations of The Second Kind personal pronoun, start image capture module, to cause described image acquisition module to be in running status;By institute
Image capture module collection N pictures are stated, N is positive integer;Determine that there is a directionality to point to gesture by the N pictures;
Described image acquisition module is based on directionality sensing gesture the first image of acquisition and is used as first data;Based on described
One data determine the referents that the personal pronoun is referred to;Operational order is performed based on the referents, wherein, it is described
Operational order for it is described the input voice is recognized by speech recognition engine after, the institute that the speech recognition engine is identified
State the corresponding instruction of input voice.
Optionally, it is described determine the referents that the personal pronoun is referred to based on first data before, institute
Stating method also includes:When identifying that the input voice includes the personal pronoun, identity identification module is loaded, with
So that the identity identification module is in running status;It is described to determine that the personal pronoun is signified based on first data
The referents in generation, including:First data are identified by the identity identification module, described first is determined
Data the first identity of correspondence;The pointing object that first identity is referred to as the personal pronoun.
Optionally, the identity identification module includes face recognition module, described to identify the input voice
When including personal pronoun, the first data are obtained, including:When identifying that the input voice includes the personal pronoun,
Load image acquisition module, to cause described image acquisition module to be in running status;Obtained by described image acquisition module
First image includes who object as first data, described first image;It is described that mould is recognized by the identity
First data are identified block, determine the first identity of the first data correspondence, including:Known by the face
Described first image is identified other module, produces recognition result, and the recognition result is described in described first image
Corresponding first identity of who object.
Optionally, the identity identification module includes voiceprint identification module, described to identify the input voice
When including personal pronoun, the first data are obtained, including:Identify it is described input voice include first kind personal pronoun
When, voiceprint extraction module is loaded, to cause the voiceprint extraction module to be in running status;By the voiceprint extraction module from
Voice print database is extracted in the input voice and is used as first data;It is described by the identity identification module to described
First data are identified, and determine the first identity of the first data correspondence, including:Pass through the voiceprint identification module pair
The voice print database is identified, and determines the voice print database correspondence first identity.
Optionally, it is described to obtain the first data when identifying that the input voice includes personal pronoun, including:
Identify that the input voice includes the input voice pair that the personal pronoun and the speech recognition engine are identified
When the instruction answered is that picture searching is instructed, load image acquisition module, to cause described image acquisition module to be in running status;
First image is obtained by described image acquisition module and is used as first data, described first image includes who object;Institute
State and determine the referents that the personal pronoun is referred to based on first data, including:Described first image is defined as
The referents that the personal pronoun is referred to;It is described to perform operational order based on the referents, including:Extract institute
State the signature identification in the first image;The signature identification and picture database are compared, from the picture database
It is determined that meeting the M pictures of the signature identification, M is natural number.
On the other hand the embodiment of the present application provides a kind of electronic equipment, including:Phonetic acquisition unit, for obtaining input language
Sound;Voice recognition unit, for recognizing the input voice by speech recognition engine;Data acquiring unit, in identification
Go out the input voice when including personal pronoun, obtain the first data, wherein, the data acquiring unit includes the 3rd image
Obtaining unit, for identifying that the input voice includes personal pronoun and the personal pronoun belongs to Equations of The Second Kind person generation
During word, start image capture module, to cause described image acquisition module to be in running status;And mould is gathered by described image
Block gathers N pictures, determines that there is a directionality to point to gesture, and control described image collection mould by the N pictures
Block is based on the directionality and points to gesture the first image of acquisition as first data, and N is positive integer;Determining unit, is used for
The referents that the personal pronoun is referred to are determined based on first data;Instruction execution unit, for being referred to based on described
Perform operational order for object, wherein, the operational order for it is described by speech recognition engine recognize the input voice it
Afterwards, the corresponding instruction of the input voice that the speech recognition engine is identified.
Optionally, the electronic equipment also includes:First loading unit, for identify it is described input voice include
During the personal pronoun, identity identification module is loaded, to cause the identity identification module to be in running status;Institute
Stating determining unit includes identity determining unit, for being carried out by the identity identification module to first data
Identification, determines the first identity of the first data correspondence, signified using first identity as the personal pronoun
The pointing object in generation.
Optionally, the identity identification module includes face recognition module;The data acquiring unit includes first
Image acquiring unit, for identify it is described input voice include the personal pronoun when, load image acquisition module, with
So that described image acquisition module is in running status;And the first image is obtained by described image acquisition module be used as described the
One data, described first image includes who object;The identity determining unit includes the first determination subelement, for leading to
Cross the face recognition module described first image is identified, produce recognition result, the recognition result is described first
Corresponding first identity of the who object in image, it is signified using first identity as the personal pronoun
The pointing object in generation.
Optionally, the identity identification module includes voiceprint identification module;The data acquiring unit includes vocal print
Obtaining unit, for when identifying that the input voice includes the personal pronoun, voiceprint extraction module being loaded, to cause
The voiceprint extraction module is in running status;And vocal print number is extracted from the input voice by the voiceprint extraction module
According to being used as first data;The identity determining unit includes the second determination subelement, for being known by the vocal print
The voice print database is identified other module, the voice print database correspondence first identity is determined, by described first
The pointing object that identity is referred to as the personal pronoun.
Optionally, the data acquiring unit includes the second image acquiring unit, for identifying the input voice
It is picture searching to include the corresponding instruction of the input voice that the personal pronoun and the speech recognition engine identify
During instruction, load image acquisition module, to cause described image acquisition module to be in running status;And gathered by described image
Module obtains the first image as first data, and described first image includes who object;The determining unit is specifically used
In described first image is defined as into the referents that the personal pronoun is referred to;The instruction execution unit is specifically used
In extracting the signature identification in described first image, the signature identification and picture database are compared, from the picture
Determination meets the M pictures of the signature identification in database, and M is natural number.
The one or more technical schemes provided in the embodiment of the present application, have at least the following technical effects or advantages:
In the embodiment of the present application, when can include personal pronoun in input voice is identified, by obtaining the first data
To determine the referents of personal pronoun reference, input voice correspondence can be correctly performed according to the referents determined
Operational order.And then the technical problem for the personal pronoun that electronic equipment can not correctly in voice command recognition is solved, lifting is electric
Sub- equipment identification, the ability for performing voice command, improve the usage experience of user.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of information processing method in the embodiment of the present application;
Fig. 2 is a kind of refinement schematic flow sheet of step 104 in the embodiment of the present application;
Fig. 3 is a kind of refinement schematic flow sheet of step 103 in the embodiment of the present application;
Fig. 4 is the corresponding schematic flow sheet of example one in the embodiment of the present application;
Fig. 5 is the corresponding schematic flow sheet of example two in the embodiment of the present application;
Fig. 6 is the corresponding schematic flow sheet of example three in the embodiment of the present application;
Fig. 7 is the functional block diagram of electronic equipment in the embodiment of the present application.
Embodiment
The application provides a kind of information processing method and electronic equipment, for solving there is electronic equipment in the prior art not
The technical problem of personal pronoun that can be in correct voice command recognition, realizes the identification of lifting electronic equipment, performs voice command
Ability, and then improve the usage experience of user.
In the embodiment of the present application, electronic equipment can be smart mobile phone, intelligent watch, tablet personal computer, intelligent television, intelligence
The smart machines such as refrigerator, intelligent automobile, electronic equipment obtains the when the input voice for identifying user includes personal pronoun
One data determine referents that the personal pronoun is referred to, and then cause electronic equipment according to the referents determined just
Really perform the corresponding operational order of input voice.Wherein, the first data can be the image gathered by image capture module,
It can be the biological attribute data of user.The embodiment of the present application technical scheme, which solves electronic equipment, can not correctly recognize that voice is ordered
The technical problem of personal pronoun in order, the identification of lifting electronic equipment, the ability for performing voice command, improves the use of user
Experience.
Technical scheme is described in detail below by accompanying drawing and specific embodiment, it should be understood that the application
Specific features in embodiment and embodiment are the detailed description to technical scheme, rather than to present techniques
The restriction of scheme, in the case where not conflicting, the technical characteristic in the embodiment of the present application and embodiment can be mutually combined.
The information processing method applied to electronic equipment provided referring to Fig. 1, the embodiment of the present application, comprises the following steps:
Step 101:Obtain input voice.
Specifically, electronic equipment can obtain the input voice of user by voice typing unit.
Step 102:Pass through speech recognition engine identified input voice.
Specifically, speech recognition engine can be the local speech recognition engine of electronic equipment or high in the clouds
Speech recognition engine, electronic equipment can call high in the clouds speech recognition engine to carry out voice knowledge by accessing cloud server
Not.
Step 103:When identifying that input voice includes personal pronoun, the first data are obtained.
Specifically, the first data can be to include the view data of who object, or the biological characteristic of user
Data, such as voice print database, finger print data, iris data.
Step 104:The referents that personal pronoun is referred to are determined based on the first data.
Specifically, step 104 includes two kinds of implementations:
Mode 1, the corresponding identity of the first data is determined by identity identification module, and the identity is people
Claim the referents of pronoun.
Mode 2, it is referents in itself to determine the first data.For example, in the corresponding instruction of input voice identified
, can be according to the view data of acquisition (that is, the to make electronic equipment retrieval with the referents of personal pronoun during corresponding image
One data) carry out matching and comparing with the picture in picture library, and then picture corresponding with view data is retrieved, now picture number
According to as referents;In another example, it is electronic equipment is retrieved and personal pronoun in the corresponding instruction of input voice identified
Referents corresponding voice document when, can be according to the voice print database (that is, the first data) and language of the input voice of acquisition
Voice document in sound storehouse carries out matching comparison, and then retrieves voice document corresponding with voice print database, now voice print database
As referents.
Step 105:Operational order is performed based on referents, wherein, operational order is to be recognized by speech recognition engine
Input after voice, the corresponding instruction of input voice that speech recognition engine is identified.
Specifically, after operational order is speech recognition engine identified input voice, electronic equipment is according to identifying
Input the instruction of speech production.Appointing after step 102, before step 105, can occur for the generating process of the operational order
One moment, the embodiment of the present application is refused this to limit.
Operational order at least includes following several types:First, making electronic equipment retrieve the reference with the personal pronoun
The corresponding a certain class file of object or a certain class file folder;Second, making electronic equipment corresponding with the referents of the personal pronoun
Terminal communicated, for example, input voice be " sending the pictures to him " when, operational order is:Make electronic equipment ought
The photo of preceding display is sent to " he " corresponding referents;Third, making electronic equipment log in the reference pair with the personal pronoun
As corresponding local account or network account.
In the embodiment of the present application above-mentioned technical proposal, when can include personal pronoun in input voice is identified, pass through
Obtain the first data to determine the referents of personal pronoun reference, can correctly be performed according to the referents determined
Input the corresponding operational order of voice.And then solve the technology for the personal pronoun that electronic equipment can not correctly in voice command recognition
Problem, the identification of lifting electronic equipment, the ability for performing voice command, improves the usage experience of user.
Further, before step 104, information processing method also includes:Identifying that inputting voice includes personal pronoun
When, identity identification module is loaded, to cause identity identification module to be in running status;
Step 104:The referents that personal pronoun is referred to are determined based on the first data, referring to Fig. 2, including following step
Suddenly:
Step 1041:The first data are identified by identity identification module, the first data correspondence first is determined
Identity;
Step 1042:The pointing object that first identity is referred to as personal pronoun.
Specifically, identity, to characterize the mark of user identity, can be the name of user, identification card number, network
Account (such as WeChat ID, No. qq) etc..Identity identification module is process chip or single-chip microcomputer, the identity identification module
The first identity of correspondence of the first data is capable of determining that, first identity is the referents of personal pronoun.
In the embodiment of the present application, identity identification module determines that the mode of the corresponding identity of the first data is:Body
First data are compared part mark identification module with the data in corresponding property data base, each in this feature database
Characteristic corresponds to an identity.Therefore, the first data and a characteristic phase in property data base are being determined
Timing, you can it is the corresponding identity of this feature data to determine the corresponding identity of the first data.
Wherein, property data base can be local in electronic equipment, can also be stored in the service that electronic equipment has access to
On device.And determine that the mode in property data base with the first data character pair data is:By the first data and character pair number
It is compared according to the characteristic in storehouse, determines the characteristic for being more than given threshold with the first Data Matching rate, this feature
The corresponding personal identification of data is the corresponding personal identification of personal pronoun;If being more than given threshold with the first Data Matching rate
Characteristic it is not unique, it is determined that the corresponding personal identification of matching rate highest characteristic be the corresponding individual of personal pronoun
Identity.
Further, according to the difference of the first data type, the corresponding body of the first data is determined by identity module
The technical scheme of part mark at least includes following several situations:
Situation 1, the first data are image, and identity identification module determines correspondence identity according to image.
Specifically, identity identification module includes face recognition module;Step 103 comprises the following steps:
When identifying that input voice includes personal pronoun, load image acquisition module, to cause image capture module
In running status;
First image is obtained by image capture module and is used as the first data, the first image includes who object;
Step 1041 comprises the following steps:The first image is identified by face recognition module, recognition result is produced,
Recognition result is corresponding first identity of who object in the first image.
Specifically, image capture module can be the camera on electronic equipment, and the first image can be IMAQ
The picture that module is obtained, or video file.Face recognition module extracts face characteristic from the first image, by the people
Face feature is compared with the face characteristic data in facial feature database, and each face is special in the facial feature database
Levy data one identity of correspondence, thus it is determined that a people in the face characteristic correspondence face characteristic transmission of data storehouse of the first image
During face characteristic, it can correspond to and determine the corresponding identity of the first image.
Situation 2, the first data are the voice print database of input voice, and identity identification module is according to voice print database determination pair
Answer identity.
Specifically, step 103 comprises the following steps:When identifying that input voice includes personal pronoun, vocal print is loaded
Extraction module, to cause voiceprint extraction module to be in running status;Vocal print is extracted from input voice by voiceprint extraction module
Data are used as the first data;
Step 1041 comprises the following steps:Voice print database is identified by voiceprint identification module, voice print database is determined
The first identity of correspondence.
Specifically, first kind personal pronoun correspondence first person pronoun, such as " I ", " I ", " My ".When detecting
During one class personal pronoun, it may be determined that the referents of the personal pronoun are user corresponding with input voice, thus can root
The identity of the user is determined according to the voice print database of the input voice.
Voiceprint extraction module is a speech processing module, can be extracted according to certain mathematical modeling from input voice
Voice print database.The voice print database is compared voiceprint identification module with the vocal print feature data in vocal print feature database, should
One identity of each vocal print feature data correspondence in vocal print feature database, thus it is determined that the voice print database is at the sound
In line property data base during a vocal print feature data, it can correspond to and determine the corresponding identity of voice print database.
Situation 3, in addition to voice print database, when electronic equipment can identify that input voice includes personal pronoun again,
The other biological characteristics such as fingerprint, the iris of user are gathered by corresponding data acquisition unit and are used as the first data.Body
Part mark identification module can determine corresponding identity according to biological attribute datas such as fingerprint, irises.
Further, step 103 comprises the following steps:Identifying that input voice includes personal pronoun and speech recognition is drawn
When holding up the corresponding instruction of the input voice identified for picture searching instruction, load image acquisition module, to cause IMAQ
Module is in running status;
First image is obtained by image capture module and is used as the first data, the first image includes who object;
Step 104 comprises the following steps:First image is defined as the referents that personal pronoun is referred to;
Step 105 comprises the following steps:
Extract the signature identification in the first image;
Signature identification is compared with picture database, determines to meet M figures of signature identification from picture database
Piece, M is natural number.
Specifically, picture searching instruction is the instruction for making electronic equipment search out picture corresponding with personal pronoun.
When operational order is that picture searching is instructed, can be gathered by image capture module includes the first image of correspondence who object,
Then extract signature identification from first image, this feature mark can for who object face characteristic or
Apparel characteristic, hair style feature etc..Then this feature mark is compared with all pictures in the picture database of electronic equipment,
Determine and identify the M matched image in picture database with this feature.
In actual conditions, when determining that operational order instructs for picture searching, it would however also be possible to employ the skill in aforementioned circumstances 1
Art scheme, first passes through face recognition module and identifies the corresponding identity of the first image, and then retrieve in picture library with being somebody's turn to do
The corresponding picture of identity.If however, when face recognition module recognizes the identity failure of the first image, can transfer
Using the technical scheme for directly comparing the image in the first image and picture library.
In addition, above-mentioned technical proposal is equally applicable to operational order to make electronic equipment search out and first kind personal pronoun
The situation of corresponding voice document, can now extract voice print database by voiceprint extraction module from input voice, and will
The voice print database with the voice document in sound bank match comparing, and then can determine what is matched with the voice print database
Voice document.
Further, in the embodiment of the present application, the first image corresponding with personal pronoun is obtained extremely by image capture module
Include following two modes less:
Mode one, when it is first kind personal pronoun to identify the personal pronoun, the personal pronoun corresponds to active user,
The image of active user is directly obtained by image capture module (for example, front camera).
Mode two, referring to Fig. 3, step 103 comprises the following steps:
Step 1031:Identifying that input voice includes personal pronoun and personal pronoun belongs to Equations of The Second Kind personal pronoun
When, start image capture module, to cause image capture module to be in running status;
Step 1032:N pictures are gathered by image capture module, N is positive integer;
Step 1033:Determine that there is a directionality to point to gesture by N pictures;
Step 1034:Image capture module is based on directionality sensing gesture the first image of acquisition and is used as the first data.
Specifically, Equations of The Second Kind personal pronoun is non-first person pronoun, and correspondence is different from other individuals of active user,
Such as " he ", " her " etc..When identifying input voice Equations of The Second Kind personal pronoun, electronic equipment is set to obtain the person generation
The corresponding view data of word, can first pass through image capture module obtain be capable of determining that a directionality point to one of gesture or
Multiple images (can also be video file), for example, shoot the gestures direction of user, or shoot user by front camera
Visual focus direction, or shoot the finger of user or the moving direction of arm, and then can determine that finger according to these images
To the directive property direction of the personal pronoun.
After determining that directionality points to gesture, the image capture module of control electronics is pointing to hand with directionality
The corresponding collection position of gesture is acquired, you can obtain the first image for including personal pronoun correspondence individual.It is specific to wrap again
Include two ways:Completed first, pointing to gesture control image acquisition units according to directionality and moving to corresponding collection position
Collection;Second, electronic equipment includes multiple images acquisition module, or image capture module has multiple acquisition windows, controls
Corresponding with directionality sensing gesture image capture module or acquisition window complete IMAQ.
Further, Equations of The Second Kind personal pronoun can also include appellation pronoun in the embodiment of the present application, and such as Mr. Liu, beam is old
Teacher, (opening) manager etc..Electronic equipment is likely to be that the corresponding finger of these appellation pronouns can not be determined from analysis voice content
For object (or can only determine appellation pronoun may corresponding multiple referents, but can not determine it is unique, correct that
Individual referents), in this case, it can use and be applied to Equations of The Second Kind personal pronoun in the above-mentioned all technical schemes of the application
Technical scheme, no longer illustrates one by one herein.
Further,, can be according to upper when including two or more personal pronouns in inputting voice in the embodiment of the present application
The repetition and/or combination for stating technical scheme are handled.For example, included in input voice " I and she ... " when, it can pass through
The voice print database of voiceprint identification module identified input voice determines the referents of " I ", or by being obtained in step 1031
N images determine the referents of " I ", then after step 1032,1033 acquisitions image corresponding with " she " is performed, root
The referents of " she " are determined according to the image.
Technical scheme is explained below by instantiation:
Example one, referring to Fig. 4, comprises the following steps:
Step 201:Electronic equipment obtains the input voice of user:" photo for searching for me ";
Step 202:Pass through speech recognition engine identified input voice;
Step 203:Identify in input voice and include first kind personal pronoun " I ", load voiceprint extraction module, pass through
Voiceprint extraction module extracts voice print database from input voice;
Step 204:Voiceprint identification module identifies the vocal print by the way that the vocal print parameter and vocal print feature database are compared
The corresponding identity of parameter is " Li Ming ";
Step 205:It is determined that " Li Ming " is the referents of " I ";
Step 206:The corresponding execute instruction of input voice is performed, the photograph associated with " Li Ming " is searched out from picture library
Piece.Wherein, the generation of execute instruction can occur after step 202, any moment before step 206;" Li Ming " is with shining
The interrelational form of piece includes:" Li Ming " is included in the name of photo, or " Li Ming " is added with the attribute list of photo, etc.
Deng.
Example two, referring to Fig. 5, comprises the following steps:
Step 207 is performed after above-mentioned steps 202:Identify and first kind personal pronoun " I ", loading are included in input voice
Picture recognition module, obtains the first image for including active user;
Step 208:It is the referents of " I " to determine first image;
Step 209:The corresponding execute instruction of input voice is performed, face characteristic, and the people are extracted from the first image
Face feature and the face characteristic of every photo in picture library are compared, and search out the photo that face characteristic matches;Wherein, hold
The generation of row instruction can occur after step 202, any moment before step 209.
Example three, referring to Fig. 6, comprises the following steps:
Step 301:Electronic equipment obtains the input voice of user when playing the local music:" song is sent to Lee
Sir ";
Step 302:Pass through speech recognition engine identified input voice;
Step 303:Identify in input voice and include " Mr. Li ", start image capture module;
Step 304:N pictures are obtained by image capture module, wherein N pictures can be the N frames in one section of video
Image;
Step 305:Determine that a directionality points to gesture by N pictures, wherein, directionality points to gesture can basis
User gesture direction or finger motion direction in N pictures are determined;
Step 306:Gesture is pointed to according to directionality and determines the collection position of image capture module, it is determined that collection position
Gather image, as the first image;
Step 307:First image is recognized by face recognition engine, determines that the corresponding identity of the first image is
" Li Ming ";Wherein, the working method of face recognition engine is:Face characteristic is extracted from the first image, by the face characteristic
It is compared with facial feature database, the corresponding identity of face characteristic data for determining matching is " Li Ming ";
Step 308:It is determined that " Li Ming " is the referents of " Mr. Li ";
Step 309:The corresponding operational order of input voice is performed, by corresponding network service by currently playing local song
Curly hair gives " Li Ming " corresponding network service address.Wherein, the generation of execute instruction can occur after step 302, step
Any instant before rapid 309;Network service includes multimedia message service, E-mail address service, wechat service etc., the network of " Li Ming "
Address of service corresponds to phone number, email address, WeChat ID.
Above three example is several corresponding examples in the embodiment of the present application technical scheme, remaining technical scheme
Concrete application is similar, and the application no longer illustrates one by one.
Referring to Fig. 7, the embodiment of the present application provides a kind of electronic equipment, and the electronic equipment can be smart mobile phone, intelligent hand
The smart machines such as table, tablet personal computer, intelligent television, intelligent refrigerator, intelligent automobile.The electronic equipment includes:
Phonetic acquisition unit 10, for obtaining input voice;
Voice recognition unit 20, for passing through speech recognition engine identified input voice;
Data acquiring unit 30, for when identifying that input voice includes personal pronoun, obtaining the first data;
Determining unit 40, for determining the referents that personal pronoun is referred to based on the first data;
Instruction execution unit 50, for performing operational order based on referents, wherein, operational order is to be known by voice
After other engine identified input voice, the corresponding instruction of input voice that speech recognition engine is identified.
In the embodiment of the present application above-mentioned technical proposal, when can include personal pronoun in input voice is identified, pass through
Obtain the first data to determine the referents of personal pronoun reference, can correctly be performed according to the referents determined
Input the corresponding operational order of voice.And then solve the technology for the personal pronoun that electronic equipment can not correctly in voice command recognition
Problem, the identification of lifting electronic equipment, the ability for performing voice command, improves the usage experience of user.
Further, electronic equipment also includes:First loading unit, for identifying that inputting voice includes personal pronoun
When, identity identification module is loaded, to cause identity identification module to be in running status;
Determining unit 40 includes identity determining unit, for being carried out by identity identification module to the first data
Identification, determines the first identity of correspondence of the first data, the pointing object that the first identity is referred to as personal pronoun.
Further, identity identification module includes face recognition module, and data acquiring unit 30 is obtained including the first image
Unit, for identify input voice include personal pronoun when, load image acquisition module, to cause IMAQ mould
Block is in running status;And the first data are used as by image capture module the first image of acquisition, the first image includes personage couple
As;
Identity determining unit includes the first determination subelement, for being carried out by face recognition module to the first image
Identification, produces recognition result, recognition result is corresponding first identity of who object in the first image, by the first identity
Identify the pointing object referred to as personal pronoun.
Further, identity identification module includes voiceprint identification module;Data acquiring unit 30 includes vocal print and obtains single
Member, for when identifying that input voice includes personal pronoun, voiceprint extraction module being loaded, to cause at voiceprint extraction module
In running status;And extraction voice print database is used as the first data from input voice by voiceprint extraction module;
Identity determining unit includes the second determination subelement, for being carried out by voiceprint identification module to voice print database
Identification, determines voice print database the first identity of correspondence, the pointing object that the first identity is referred to as personal pronoun.
Further, data acquiring unit includes the second image acquiring unit, for identifying that inputting voice includes people
When the corresponding instruction of input voice that pronoun and speech recognition engine are identified is called picture searching instruction, load image collection mould
Block, to cause image capture module to be in running status;And the first data are used as by image capture module the first image of acquisition,
First image includes who object;
Determining unit 40 by the first image specifically for being defined as the referents that personal pronoun is referred to;
Instruction execution unit 50 is specifically for extracting the signature identification in the first image, by signature identification and picture database
It is compared, determines to meet the M pictures of signature identification from picture database, M is natural number.
Further, data acquiring unit includes the 3rd image acquiring unit, for identifying that inputting voice includes people
When claiming pronoun and the personal pronoun to belong to Equations of The Second Kind personal pronoun, start image capture module, to cause image capture module to be in
Running status;And N pictures are gathered by image capture module, determine that there is a directionality to point to gesture by N pictures, with
And control image capture module is based on directionality and points to gesture the first image of acquisition as the first data, N is positive integer.
Various information processing manners and instantiation in information processing method in previous embodiment are equally applicable to this
The electronic equipment of embodiment, by the way that to the detailed description of information processing method, those skilled in the art can be with previous embodiment
The implementation of electronic equipment in the present embodiment is apparent from, thus it is succinct for specification, it will not be described in detail herein.
The one or more technical schemes provided in the embodiment of the present application, have at least the following technical effects or advantages:
In the embodiment of the present application, when can include personal pronoun in input voice is identified, by obtaining the first data
To determine the referents of personal pronoun reference, input voice correspondence can be correctly performed according to the referents determined
Operational order.And then the technical problem for the personal pronoun that electronic equipment can not correctly in voice command recognition is solved, lifting is electric
Sub- equipment identification, the ability for performing voice command, improve the usage experience of user.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, the application can be using the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the application can be used in one or more computers for wherein including computer usable program code
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is the flow with reference to method, equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram are described.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which is produced, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
Specifically, the corresponding computer program instructions of information processing method in the embodiment of the present application can be stored in
On CD, hard disk, the storage medium such as USB flash disk, when computer program instructions quilt corresponding with information processing method in storage medium
When one electronic equipment reads or is performed, comprise the following steps:
Obtain input voice;
Pass through speech recognition engine identified input voice;
When identifying that input voice includes personal pronoun, the first data are obtained;
The referents that personal pronoun is referred to are determined based on the first data;
Operational order is performed based on referents, wherein, operational order is to pass through speech recognition engine identified input voice
Afterwards, the corresponding instruction of input voice that speech recognition engine is identified.
Optionally, be also stored with other computer instruction in the storage medium, these computer instructions with step
Suddenly:The referents that the personal pronoun is referred to are determined based on first data, corresponding computer instruction is performed it
Before be performed, comprise the following steps when executed:
When identifying that the input voice includes the personal pronoun, identity identification module is loaded, to cause
The identity identification module is in running status;
Stored in storage medium and step:The reference pair that the personal pronoun is referred to is determined based on first data
As corresponding computer instruction specifically includes following steps during specific be performed:
First data are identified by the identity identification module, first data correspondence the is determined
One identity;
The pointing object that first identity is referred to as the personal pronoun.
Optionally, the identity identification module includes face recognition module, store in storage medium and step:
When identifying that the input voice includes personal pronoun, the first data are obtained, corresponding computer instruction is specifically being performed
During, specifically include following steps:
When identifying that the input voice includes the personal pronoun, load image acquisition module is described to cause
Image capture module is in running status;
First image is obtained by described image acquisition module and is used as first data, described first image includes personage
Object;
Stored in storage medium and step:First data are known by the identity identification module
Not, the first identity of the first data correspondence is determined, corresponding computer instruction is during specific be performed, specific bag
Include following steps:
Described first image is identified by the face recognition module, recognition result, the recognition result is produced
For corresponding first identity of the who object in described first image.
Optionally, the identity identification module includes voiceprint identification module, store in storage medium and step:
When identifying that the input voice includes personal pronoun, the first data are obtained, corresponding computer instruction is specifically being performed
During, specifically include following steps:
When identifying that the input voice includes first kind personal pronoun, voiceprint extraction module is loaded, to cause
State voiceprint extraction module and be in running status;
Voice print database is extracted from the input voice by the voiceprint extraction module and is used as first data;
Stored in storage medium and step:First data are known by the identity identification module
Not, the first identity of the first data correspondence is determined, corresponding computer instruction is during specific be performed, specific bag
Include following steps:
The voice print database is identified by the voiceprint identification module, voice print database correspondence described the is determined
One identity.
Optionally, stored in storage medium and step:When identifying that the input voice includes personal pronoun, obtain
The first data are obtained, corresponding computer instruction specifically includes following steps during specific be performed:
Described in identifying that the input voice includes the personal pronoun and the speech recognition engine identifies
When inputting the corresponding instruction of voice for picture searching instruction, load image acquisition module, to cause at described image acquisition module
In running status;
First image is obtained by described image acquisition module and is used as first data, described first image includes personage
Object;
Stored in storage medium and step:The reference pair that the personal pronoun is referred to is determined based on first data
As corresponding computer instruction specifically includes following steps during specific be performed:
Described first image is defined as the referents that the personal pronoun is referred to;
Stored in storage medium and step:Operational order, corresponding computer instruction are performed based on the referents
During specific be performed, following steps are specifically included:
Extract the signature identification in described first image;
The signature identification and picture database are compared, determine to meet the feature from the picture database
The M pictures of mark, M is natural number.
Stored in storage medium and step:When identifying that the input voice includes personal pronoun, first is obtained
Data, corresponding computer instruction specifically includes following steps during specific be performed:
When identifying that the input voice includes personal pronoun and the personal pronoun belongs to Equations of The Second Kind personal pronoun,
Start image capture module, to cause described image acquisition module to be in running status;
N pictures are gathered by described image acquisition module, N is positive integer;
Determine that there is a directionality to point to gesture by the N pictures;
Described image acquisition module is based on directionality sensing gesture the first image of acquisition and is used as first data.
Although having been described for the preferred embodiment of the application, those skilled in the art once know basic creation
Property concept, then can make other change and modification to these embodiments.So, appended claims are intended to be construed to include excellent
Select embodiment and fall into having altered and changing for the application scope.
Obviously, those skilled in the art can carry out the essence of various changes and modification without departing from the application to the application
God and scope.So, if these modifications and variations of the application belong to the scope of the application claim and its equivalent technologies
Within, then the application is also intended to comprising including these changes and modification.
Claims (10)
1. a kind of information processing method, applied in electronic equipment, methods described includes:
Obtain input voice;
The input voice is recognized by speech recognition engine;
When identifying that the input voice includes personal pronoun, the first data are obtained, including:Identifying the input language
Sound includes personal pronoun and when the personal pronoun belongs to Equations of The Second Kind personal pronoun, starts image capture module, to cause
State image capture module and be in running status;N pictures are gathered by described image acquisition module, N is positive integer;By described
N pictures determine that there is a directionality to point to gesture;Described image acquisition module is based on the directionality and points to gesture obtaining the
One image is used as first data;
The referents that the personal pronoun is referred to are determined based on first data;
Operational order is performed based on the referents, wherein, the operational order is recognized to be described by speech recognition engine
After the input voice, the corresponding instruction of the input voice that the speech recognition engine is identified.
2. the method as described in claim 1, it is characterised in that based on first data determine the personal pronoun described
Before the referents referred to, methods described also includes:
When identifying that the input voice includes the personal pronoun, identity identification module is loaded, it is described to cause
Identity identification module is in running status;
It is described to determine the referents that the personal pronoun is referred to based on first data, including:
First data are identified by the identity identification module, the first body of the first data correspondence is determined
Part mark;
The pointing object that first identity is referred to as the personal pronoun.
3. method as claimed in claim 2, it is characterised in that the identity identification module includes face recognition module,
It is described to obtain the first data when identifying that the input voice includes personal pronoun, including:
When identifying that the input voice includes the personal pronoun, load image acquisition module, to cause described image
Acquisition module is in running status;
First image is obtained by described image acquisition module and is used as first data, described first image includes personage couple
As;
It is described that first data are identified by the identity identification module, determine first data correspondence the
One identity, including:
Described first image is identified by the face recognition module, recognition result is produced, the recognition result is institute
State corresponding first identity of the who object in the first image.
4. method as claimed in claim 2, it is characterised in that the identity identification module includes voiceprint identification module,
It is described to obtain the first data when identifying that the input voice includes personal pronoun, including:
When identifying that the input voice includes first kind personal pronoun, voiceprint extraction module is loaded, to cause the sound
Line extraction module is in running status;
Voice print database is extracted from the input voice by the voiceprint extraction module and is used as first data;
It is described that first data are identified by the identity identification module, determine first data correspondence the
One identity, including:
The voice print database is identified by the voiceprint identification module, the voice print database correspondence first body is determined
Part mark.
5. the method as described in claim 1, it is characterised in that described to identify that the input voice includes personal pronoun
When, the first data are obtained, including:
Identify it is described input voice include the input that the personal pronoun and the speech recognition engine are identified
When the corresponding instruction of voice is picture searching instruction, load image acquisition module, to cause described image acquisition module to be in fortune
Row state;
First image is obtained by described image acquisition module and is used as first data, described first image includes personage couple
As;
It is described to determine the referents that the personal pronoun is referred to based on first data, including:
Described first image is defined as the referents that the personal pronoun is referred to;
It is described to perform operational order based on the referents, including:
Extract the signature identification in described first image;
The signature identification and picture database are compared, determine to meet the signature identification from the picture database
M pictures, M is natural number.
6. a kind of electronic equipment, including:
Phonetic acquisition unit, for obtaining input voice;
Voice recognition unit, for recognizing the input voice by speech recognition engine;
Data acquiring unit, for when identifying that the input voice includes personal pronoun, obtaining the first data, wherein,
The data acquiring unit include the 3rd image acquiring unit, for identify it is described input voice include personal pronoun and
When the personal pronoun belongs to Equations of The Second Kind personal pronoun, start image capture module, to cause described image acquisition module to be in
Running status;And N pictures are gathered by described image acquisition module, determine that there is a directionality to refer to by the N pictures
It is based on directionality sensing gesture the first image of acquisition to gesture, and control described image acquisition module and is used as described first
Data, N is positive integer;
Determining unit, for determining the referents that the personal pronoun is referred to based on first data;
Instruction execution unit, for performing operational order based on the referents, wherein, the operational order passes through to be described
After the speech recognition engine identification input voice, the corresponding finger of the input voice that the speech recognition engine is identified
Order.
7. electronic equipment as claimed in claim 6, it is characterised in that the electronic equipment also includes:
First loading unit, for when identifying that the input voice includes the personal pronoun, loading identity to be known
Other module, to cause the identity identification module to be in running status;
The determining unit includes identity determining unit, for being counted by the identity identification module to described first
According to being identified, the first identity of the first data correspondence is determined, first identity is regard as the person generation
The pointing object that word is referred to.
8. electronic equipment as claimed in claim 7, it is characterised in that the identity identification module includes recognition of face mould
Block;
The data acquiring unit include the first image acquiring unit, for identify it is described input voice include the people
When claiming pronoun, load image acquisition module, to cause described image acquisition module to be in running status;And adopted by described image
Collect module and obtain the first image as first data, described first image includes who object;
The identity determining unit include the first determination subelement, for by the face recognition module to described first
Image is identified, and produces recognition result, and the recognition result is the who object corresponding the in described first image
One identity, the pointing object that first identity is referred to as the personal pronoun.
9. electronic equipment as claimed in claim 7, it is characterised in that the identity identification module includes Application on Voiceprint Recognition mould
Block;
The data acquiring unit include vocal print obtaining unit, for identify it is described input voice include the person generation
During word, voiceprint extraction module is loaded, to cause the voiceprint extraction module to be in running status;And pass through the voiceprint extraction mould
Block extracts voice print database from the input voice and is used as first data;
The identity determining unit include the second determination subelement, for by the voiceprint identification module to the vocal print
Data are identified, and determine first identity of voice print database correspondence, using first identity as described
The pointing object that personal pronoun is referred to.
10. electronic equipment as claimed in claim 6, it is characterised in that the data acquiring unit is obtained including the second image
Unit, for described in identify that the input voice includes the personal pronoun and the speech recognition engine identifies
When inputting the corresponding instruction of voice for picture searching instruction, load image acquisition module, to cause at described image acquisition module
In running status;And first data, described first image bag are used as by described image acquisition module the first image of acquisition
Include who object;
The determining unit by described first image specifically for being defined as the referents that the personal pronoun is referred to;
The instruction execution unit is specifically for extracting the signature identification in described first image, by the signature identification and picture
Database is compared, and determines to meet the M pictures of the signature identification from the picture database, M is natural number.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410211567.3A CN103984415B (en) | 2014-05-19 | 2014-05-19 | A kind of information processing method and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410211567.3A CN103984415B (en) | 2014-05-19 | 2014-05-19 | A kind of information processing method and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103984415A CN103984415A (en) | 2014-08-13 |
CN103984415B true CN103984415B (en) | 2017-08-29 |
Family
ID=51276425
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410211567.3A Active CN103984415B (en) | 2014-05-19 | 2014-05-19 | A kind of information processing method and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103984415B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104714640A (en) * | 2015-02-06 | 2015-06-17 | 上海语镜汽车信息技术有限公司 | Vehicle-mounted terminal device based on gesture control and cloud computation technology with voice interaction and high-definition image obtaining functions |
CN109524853B (en) * | 2018-10-23 | 2020-11-24 | 珠海市杰理科技股份有限公司 | Gesture recognition socket and socket control method |
CN110516083B (en) | 2019-08-30 | 2022-07-12 | 京东方科技集团股份有限公司 | Album management method, storage medium and electronic device |
CN114063856A (en) * | 2021-11-17 | 2022-02-18 | 塔米智能科技(北京)有限公司 | Identity registration method, device, equipment and medium |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140046891A1 (en) * | 2012-01-25 | 2014-02-13 | Sarah Banas | Sapient or Sentient Artificial Intelligence |
US20130217297A1 (en) * | 2012-02-21 | 2013-08-22 | Makoto Araki | Toy having voice recognition and method for using same |
-
2014
- 2014-05-19 CN CN201410211567.3A patent/CN103984415B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Also Published As
Publication number | Publication date |
---|---|
CN103984415A (en) | 2014-08-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10275672B2 (en) | Method and apparatus for authenticating liveness face, and computer program product thereof | |
CN109034069B (en) | Method and apparatus for generating information | |
WO2017185630A1 (en) | Emotion recognition-based information recommendation method and apparatus, and electronic device | |
CN105095882B (en) | The recognition methods of gesture identification and device | |
CN107545241A (en) | Neural network model is trained and biopsy method, device and storage medium | |
WO2015101289A1 (en) | Image management method, apparatus and system | |
CN110225387A (en) | A kind of information search method, device and electronic equipment | |
CN106778450A (en) | A kind of face recognition method and device | |
JP6969663B2 (en) | Devices and methods for identifying the user's imaging device | |
CN106529255B (en) | Method for identifying ID and device based on person's handwriting fingerprint | |
WO2022089170A1 (en) | Caption area identification method and apparatus, and device and storage medium | |
CN109194689B (en) | Abnormal behavior recognition method, device, server and storage medium | |
CN103984415B (en) | A kind of information processing method and electronic equipment | |
US9519355B2 (en) | Mobile device event control with digital images | |
CN112818909A (en) | Image updating method and device, electronic equipment and computer readable medium | |
CN107679457A (en) | User identity method of calibration and device | |
CN109190654A (en) | The training method and device of human face recognition model | |
CN108345612A (en) | A kind of question processing method and device, a kind of device for issue handling | |
CN104966016A (en) | Method for collaborative judgment and operating authorization restriction for mobile terminal child user | |
CN113254491A (en) | Information recommendation method and device, computer equipment and storage medium | |
CN107526994A (en) | A kind of information processing method, device and mobile terminal | |
CN102890777A (en) | Computer system capable of identifying facial expressions | |
CN112052784A (en) | Article searching method, device, equipment and computer readable storage medium | |
CN112699811B (en) | Living body detection method, living body detection device, living body detection apparatus, living body detection storage medium, and program product | |
CN110363187B (en) | Face recognition method, face recognition device, machine readable medium and equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |