CN109658941A - A kind of intelligent refrigerator information flow method for pushing and device based on Application on Voiceprint Recognition - Google Patents
A kind of intelligent refrigerator information flow method for pushing and device based on Application on Voiceprint Recognition Download PDFInfo
- Publication number
- CN109658941A CN109658941A CN201811467356.0A CN201811467356A CN109658941A CN 109658941 A CN109658941 A CN 109658941A CN 201811467356 A CN201811467356 A CN 201811467356A CN 109658941 A CN109658941 A CN 109658941A
- Authority
- CN
- China
- Prior art keywords
- vocal print
- registration
- print feature
- feature information
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000001755 vocal effect Effects 0.000 claims abstract description 206
- 239000000284 extract Substances 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000002716 delivery method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/14—Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/1066—Session management
- H04L65/1073—Registration or de-registration
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Cold Air Circulating Systems And Constructional Details In Refrigerators (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of intelligent refrigerator information flow method for pushing and device based on Application on Voiceprint Recognition, method include: the voice for receiving target user, extract vocal print feature information to be identified according to the voice of target user using sound-groove model；Vocal print feature information is registered in selection one by one in registration vocal print library, and calculates the registration vocal print feature information of selection and the similarity of vocal print feature information to be identified；According to similarity judge that this selects register vocal print feature information whether as target user it is pre-registered；If so, obtaining target information stream type corresponding with the registration vocal print feature information of the selection, and the information of target information stream type is pushed to target user；Wherein, target information stream type is that target user is pre-set when registering.The present invention, can determine the flow type of setting, and then more efficiently filter out garbage stream, carry out the information of push preference information stream type.
Description
Technical field
The present invention relates to intelligent refrigerator technical field, in particular to a kind of intelligent refrigerator information flow based on Application on Voiceprint Recognition pushes away
Delivery method and device.
Background technique
With the development of refrigerator technology and the raising of living standards of the people, start in people's daily life generally using intelligence
Refrigerator, intelligent refrigerator not only can control internal temperature of refrigerator and mode, also can provide the multimedias such as music and video playing
Using for consumer entertainment.The function this and more of intelligent refrigerator, because of the relationship of intelligence system, creating may more be allowed
The new intelligent function of user experience, wherein push news information stream be exactly it is one such, user can be clear on intelligent refrigerator
Related news information is look at, alternatively, intelligent refrigerator is that user speech broadcasts related news information.But news is many kinds of, very
To the news having be not that user likes and sees, thus it is a kind of can the method for quick filtering useless information flow become current intelligence
A kind of demand of energy refrigerator.
Summary of the invention
The embodiment of the invention provides a kind of intelligent refrigerator information flow method for pushing and device based on Application on Voiceprint Recognition, with solution
Problem certainly of the existing technology.
To achieve the above object, the present invention provides a kind of intelligent refrigerator information flow method for pushing based on Application on Voiceprint Recognition,
Include:
The voice for receiving target user extracts vocal print spy to be identified according to the voice of the target user using sound-groove model
Reference breath；
The selection registration vocal print feature information one by one in registration vocal print library, and calculate the registration vocal print feature information of selection with
The similarity of vocal print feature information to be identified；
According to the similarity judge that this selects register vocal print feature information whether as the target user it is registered in advance
's；
If so, obtain corresponding with the registration vocal print feature information of selection target information stream type, and by the mesh
The information of mark flow type is pushed to the target user；Wherein, the target information stream type is target user note
It is pre-set when volume.
Preferably, the similarity of the registration vocal print feature information for calculating selection and vocal print feature information to be identified, packet
It includes: calculating the registration vocal print feature information of selection and the similarity of vocal print feature information to be identified using following formula:
Wherein, Q (T, Si) ∈ [0,1], and T=| T1,T2……TN|, Si=| Si1,Si2……SiM|；
Wherein, Q (T, Si) it is the registration vocal print feature information selected in vocal print feature information T to be identified and registration vocal print library
SiSimilarity, i indicate it is different registration vocal print feature information marks, when registration vocal print library in registration vocal print feature packet
When including multiple, it is denoted as S1、S2……Si, SiEach element is for characterizing a vocal print feature parameter in set；It is each in T set
Element is for characterizing a vocal print feature parameter.
Preferably, parameter N is equal with the value of parameter M, and T set in SiThe vocal print feature parameter phase for including in set
Together.
Preferably, described to judge that whether what this selected registers vocal print feature information as target use according to the similarity
Family is pre-registered, comprising: when the similarity is not less than given threshold, it is determined that the registration vocal print feature information of the selection
It is that the target user is pre-registered, otherwise, it determines the registration vocal print feature information of the selection is not that the target user is pre-
First register.
Preferably, before the voice for receiving target user, further includes:
The voice for receiving registration user extracts registration vocal print according to the voice of the registration user using the sound-groove model
Characteristic information, by the registration vocal print feature information storage of the registration user into registration vocal print library；
The flow type for obtaining the registration user setting, by the registration vocal print feature information of the registration user and its
The flow type of setting is bound, and stores binding relationship.
To achieve the above object, the present invention also provides a kind of, and the intelligent refrigerator information flow based on Application on Voiceprint Recognition pushes dress
It sets, comprising:
Receiving module, for receiving the voice of target user；
Extraction module is believed for extracting vocal print feature to be identified according to the voice of the target user using sound-groove model
Breath；
Computing module for selecting registration vocal print feature information one by one in registration vocal print library, and calculates the registration of selection
The similarity of vocal print feature information and vocal print feature information to be identified；
Judgment module, for judging that whether what this selected registers vocal print feature information as the target according to the similarity
User is pre-registered；
Module is obtained, when the judgment module judging result, which is, is, then obtains and believes with the registration vocal print feature of the selection
Cease corresponding target information stream type；Wherein, the target information stream type is that the target user is pre-set when registering；
Pushing module, for the information of the target information stream type to be pushed to the target user.
Preferably, the computing module, specifically for calculated using following formula the registration vocal print feature information of selection with
The similarity of vocal print feature information to be identified:
Wherein, Q (T, Si) ∈ [0,1], and T=| T1,T2……TN|, Si=| Si1,Si2……SiM|；
Wherein, Q (T, Si) it is the registration vocal print feature information selected in vocal print feature information T to be identified and registration vocal print library
SiSimilarity, i indicate it is different registration vocal print feature information marks, when registration vocal print library in registration vocal print feature packet
When including multiple, it is denoted as S1、S2……Si, SiEach element is for characterizing a vocal print feature parameter in set；It is each in T set
Element is for characterizing a vocal print feature parameter.
Preferably, parameter N is equal with the value of parameter M, and T set in SiThe vocal print feature parameter phase for including in set
Together.
Preferably, the judgment module is specifically used for when the similarity is not less than given threshold, it is determined that the selection
Registration vocal print feature information be that the target user is pre-registered, otherwise, it determines the registration vocal print feature information of the selection
It is not that the target user is pre-registered.
Preferably, further includes: registration module, for receiving the voice of registration user, using the sound-groove model according to institute
The voice for stating registration user extracts registration vocal print feature information, by the registration vocal print feature information storage of the registration user to note
In volume vocal print library；The flow type for obtaining the registration user setting, by the registration vocal print feature information of the registration user
The flow type being arranged with it is bound, and stores binding relationship.
The embodiment of the invention provides a kind of intelligent refrigerator information flow method for pushing and device based on Application on Voiceprint Recognition, utilization
Sound-groove model extracts the vocal print feature information to be identified of target user, and selection registration vocal print feature is believed one by one in registration vocal print library
Breath, calculates the registration vocal print feature information of selection and the similarity of vocal print feature information to be identified, judges the choosing according to similarity
Select register vocal print feature information whether as target user it is pre-registered, if so, obtaining special with the registration vocal print of the selection
Reference ceases corresponding target information stream type, and the information of target information stream type is pushed to target user.The present invention, Yong Hutong
Cross in intelligent refrigerator it is registered in advance itself vocal print feature information and set the flow type of preference, intelligent refrigerator is receiving
To after the voice of user, similarity calculation is carried out with good vocal print feature information registered in advance in registration vocal print library, so as to
It determines the flow type of setting, and then more efficiently filters out garbage stream, carry out push preference information stream type
Information.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is the intelligent refrigerator information flow method for pushing process provided by one embodiment of the present invention based on Application on Voiceprint Recognition
Figure；
Fig. 2 is the structure of the intelligent refrigerator information flow driving means provided by one embodiment of the present invention based on Application on Voiceprint Recognition
Schematic diagram；
Fig. 3 is the structure of the intelligent refrigerator information flow driving means provided by one embodiment of the present invention based on Application on Voiceprint Recognition
Schematic diagram.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments, based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Embodiment 1
Referring to FIG. 1, the embodiment of the invention provides a kind of intelligent refrigerator information flow method for pushing based on Application on Voiceprint Recognition,
Include:
Step 101: receiving the voice of target user, extracted according to the voice of the target user wait know using sound-groove model
Other vocal print feature information.
In the present embodiment, intelligent refrigerator can push the information flow of preference, specifically, target according to user speech for it
User issues voice in the range of intelligent refrigerator can acquire voice, and intelligent refrigerator can collect the voice of target user, benefit
Vocal print feature information to be identified is extracted according to the voice of target user with sound-groove model.
Wherein, vocal print feature information to be identified at least may include: cepstrum, formant.For example, the sound to be identified extracted
Line characteristic information can indicate with a set T, set T=| T1,T2……TN|, wherein each element is used in T set
In characterizing a vocal print feature parameter, for example, T1For cepstrum, T2For formant ... ....N is the integer not less than 1.
Sound-groove model constructs in advance, for the voice of different user, the parameter phase of the vocal print feature information extracted
Together.
Wherein, the voice that user issues can be any a word, be also possible to if specifying, the particular content root of voice
It is determined according to the setting of intelligent refrigerator.
Step 102: vocal print feature information is registered in selection one by one in registration vocal print library, and the registration vocal print for calculating selection is special
The similarity of reference breath and vocal print feature information to be identified.
In the present embodiment, a registration vocal print library can be constructed in advance, and different user can be in advance by the voice of oneself
It is registered, specifically: registration user carries out voice registration by the set interface of intelligent refrigerator, can acquire language in intelligent refrigerator
Voice is issued in the range of sound, intelligent refrigerator can collect the voice of registration user, using sound-groove model according to registration user
Voice extract registration vocal print feature information, and will register user registration vocal print feature information storage to registration vocal print library in.
For example, one set S of the registration vocal print feature information of each registration useriIt indicates, set Si=| Si1,Si2……
SiM|, wherein SiEach element indicates different registration vocal print feature information for characterizing a vocal print feature parameter, i in set
Mark is denoted as S when it includes multiple for registering the registration vocal print feature information in vocal print library1、S2……Si, each registration vocal print
Characteristic information includes M vocal print feature parameter.
In registration process, in order to which intelligent refrigerator can collect voice, and it is special extracting vocal print using sound-groove model
Reference is more accurate when ceasing, and can set the duration that user issues voice, sending can be determined according to the setting of intelligent refrigerator
The duration of voice, for example, issuing a length of 10s when voice.
Wherein, after the registration vocal print feature information storage that will register user is into registration vocal print library, intelligent refrigerator can
Think that registration user distributes a unique mark ID.
Further, in order to push the information flow of type of preferences in subsequent process for user, registration user can be
The flow type of preference is set in intelligent refrigerator, and all flow types can be showed registration user, note by intelligent refrigerator
Volume user selects in the flow type of displaying, and intelligent refrigerator sets the registration vocal print feature information for registering user with it
The flow type set is bound, and is also possible to bind the flow type that the ID for registering user is arranged with it, and
Store binding relationship.
Due to registering with the registration vocal print feature information of different user in registration vocal print library, in order to determine step
In 101 target user whether registration vocal print library in mistake registered in advance, need one by one registration vocal print library in selection one registration
Vocal print feature information is compared, until determining with the target user's with the vocal print feature information to be identified of target user
Until the identical registration vocal print feature information of vocal print feature information to be identified, alternatively, until all registration sound in registration vocal print library
Until line characteristic information has compared.
In the similarity of the registration vocal print feature information and vocal print feature information to be identified that calculate selection, Europe can be used
The modes such as formula distance, cosine similarity still when the number of elements in two set is very big, while having many set again
When needing to judge respectively similarity between any two, using Euclidean distance, cosine similarity calculate similarity will be quite time-consuming, meter
Calculate low efficiency.
In the present embodiment, registration vocal print feature information and the vocal print to be identified that selection can be calculated using following formula are special
The similarity of reference breath:
Wherein, Q (T, Si) ∈ [0,1], Q (T, Si) it is the note selected in vocal print feature information T to be identified and registration vocal print library
Volume vocal print feature information SiSimilarity.
In an embodiment of the invention, set T and set SiInterior element number is identical, i.e. the value of parameter N and parameter M
It is equal, and T set in SiThe vocal print feature parameter for including in set is identical.For example, Si1For cepstrum, Si2For formant.
Step 103: judging that whether what this selected registers vocal print feature information as the target user according to the similarity
It is pre-registered.
In the present embodiment, similarity value is bigger, and the similarity of two set is higher.
In the present embodiment, a threshold value can be set, when similarity is greater than the given threshold, it is determined that the note of the selection
Volume vocal print feature information is that the target user is pre-registered, otherwise, it determines the registration vocal print feature information of the selection is not
The target user is pre-registered.For example, the given threshold is 0.9.
Step 104: if so, target information stream type corresponding with the registration vocal print feature information of the selection is obtained, and
The information of the flow type is pushed to the target user；Wherein, the target information stream type is target use
Family is pre-set when registering.
In the present embodiment, the binding relationship of vocal print feature information and flow type is registered due to being previously stored with, or
Person is previously stored with the binding relationship of registration User ID and flow type, can determine and be somebody's turn to do according to the binding relationship is registered
The corresponding target information stream type of target user.
After target information stream type has been determined, intelligent refrigerator requests the target information stream type to message flow server
Information flow, and the information flow requested is pushed to target user, is target user to be filtered to garbage stream
Push the information flow of type of preferences.
In the embodiment of the present invention, the vocal print feature information to be identified of target user is extracted using sound-groove model, in registration sound
Vocal print feature information is registered in selection one by one in line library, calculates the registration vocal print feature information and vocal print feature information to be identified of selection
Similarity, according to similarity judge that this selects register vocal print feature information whether as target user it is pre-registered, if so,
Target information stream type corresponding with the registration vocal print feature information of the selection is then obtained, the information of target information stream type is pushed away
Give target user.The present invention, user by intelligent refrigerator it is registered in advance itself vocal print feature information and set preference
Flow type, intelligent refrigerator after receiving the voice of user, with registration vocal print library in good vocal print feature registered in advance
Information carries out similarity calculation, may thereby determine that out the flow type set, and then more efficiently filter out useless letter
Breath stream, carries out the information of push preference information stream type.
Referring to FIG. 2, a kind of intelligent refrigerator information flow driving means based on Application on Voiceprint Recognition is shown, in the present embodiment
In, the intelligent refrigerator information flow driving means based on Application on Voiceprint Recognition may include or be divided into one or more program modules,
One or more program module is stored in storage medium, and as performed by one or more processors, to complete this hair
It is bright, and can realize the above-mentioned intelligent refrigerator information flow method for pushing based on Application on Voiceprint Recognition.The so-called program module of the present invention refers to
The series of computation machine program instruction section that can complete specific function, than program itself more suitable for describing based on Application on Voiceprint Recognition
Implementation procedure of the intelligent refrigerator information flow driving means in storage medium.Each program of the present embodiment will specifically be introduced by being described below
The function of module:
Receiving module 201, for receiving the voice of target user；
Extraction module 202, for extracting vocal print feature to be identified according to the voice of the target user using sound-groove model
Information；
Computing module 203 for selecting registration vocal print feature information one by one in registration vocal print library, and calculates the note of selection
The similarity of volume vocal print feature information and vocal print feature information to be identified；
Judgment module 204, for judging that this selected registers whether vocal print feature information is described according to the similarity
Target user is pre-registered；
Module 205 is obtained, when the judgment module judging result, which is, is, then obtains the registration vocal print feature with the selection
The corresponding target information stream type of information；Wherein, the target information stream type is that the target user presets when registering
's；
Pushing module 206, for the information of the target information stream type to be pushed to the target user.
In an embodiment of the invention, the computing module 203, specifically for calculating the note of selection using following formula
The similarity of volume vocal print feature information and vocal print feature information to be identified:
Wherein, Q (T, Si) ∈ [0,1], and T=| T1,T2……TN|, Si=| Si1,Si2……SiM|；
Wherein, Q (T, Si) it is the registration vocal print feature information selected in vocal print feature information T to be identified and registration vocal print library
SiSimilarity, i indicate it is different registration vocal print feature information marks, when registration vocal print library in registration vocal print feature packet
When including multiple, it is denoted as S1、S2……Si, SiEach element is for characterizing a vocal print feature parameter in set；It is each in T set
Element is for characterizing a vocal print feature parameter.
In an embodiment of the invention, parameter N is equal with the value of parameter M, and T set in SiThe sound for including in set
Line characteristic parameter is identical.
In an embodiment of the invention, the judgment module 204 is specifically used in the similarity not less than setting threshold
When value, it is determined that the registration vocal print feature information of the selection is that the target user is pre-registered, otherwise, it determines the selection
Registering vocal print feature information is not that the target user is pre-registered.
It in an embodiment of the invention, referring to FIG. 3, should the intelligent refrigerator information flow driving means based on Application on Voiceprint Recognition
Further include: registration module 207, for receiving the voice of registration user, using the sound-groove model according to the registration user's
Voice extracts registration vocal print feature information, by the registration vocal print feature information storage of the registration user into registration vocal print library；
The flow type for obtaining the registration user setting, the letter that the registration vocal print feature information of the registration user is arranged with it
Stream type binding is ceased, and stores binding relationship.
To sum up, each embodiment of the present invention at least may be implemented it is following the utility model has the advantages that
1, the vocal print feature information to be identified that target user in embodiments of the present invention, is extracted using sound-groove model, is being infused
Vocal print feature information is registered in selection one by one in volume vocal print library, calculates the registration vocal print feature information and vocal print feature to be identified of selection
The similarity of information, according to similarity judge that this selects register vocal print feature information whether as target user it is pre-registered,
If so, target information stream type corresponding with the registration vocal print feature information of the selection is obtained, by target information stream type
Information is pushed to target user.The present invention, user by intelligent refrigerator it is registered in advance itself vocal print feature information and set
Determine the flow type of preference, intelligent refrigerator is after receiving the voice of user, with good sound registered in advance in registration vocal print library
Line characteristic information carries out similarity calculation, may thereby determine that out the flow type set, and then more efficiently filter out
Garbage stream carries out the information of push preference information stream type.
The contents such as the information exchange between each unit, implementation procedure in above-mentioned apparatus, due to implementing with the method for the present invention
Example is based on same design, and for details, please refer to the description in the embodiment of the method for the present invention, and details are not described herein again.
It should be noted that, in this document, such as first and second etc relational terms are used merely to an entity
Or operation is distinguished with another entity or operation, is existed without necessarily requiring or implying between these entities or operation
Any actual relationship or order.Moreover, the terms "include", "comprise" or its any other variant be intended to it is non-
It is exclusive to include, so that the process, method, article or equipment for including a series of elements not only includes those elements,
It but also including other elements that are not explicitly listed, or further include solid by this process, method, article or equipment
Some elements.In the absence of more restrictions, the element limited by sentence " including one ", is not arranged
Except there is also other identical factors in the process, method, article or apparatus that includes the element.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can store in computer-readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes: ROM, RAM, magnetic disk or light
In the various media that can store program code such as disk.
Finally, it should be noted that the foregoing is merely presently preferred embodiments of the present invention, it is merely to illustrate skill of the invention
Art scheme, is not intended to limit the scope of the present invention.Any modification for being made all within the spirits and principles of the present invention,
Equivalent replacement, improvement etc., are included within the scope of protection of the present invention.
Claims (10)
1. a kind of intelligent refrigerator information flow method for pushing based on Application on Voiceprint Recognition characterized by comprising
The voice for receiving target user extracts vocal print feature to be identified according to the voice of the target user using sound-groove model and believes
Breath；
The selection registration vocal print feature information one by one in registration vocal print library, and calculate the registration vocal print feature information of selection with wait know
The similarity of other vocal print feature information；
According to the similarity judge that this selects register vocal print feature information whether as the target user it is pre-registered；
If so, obtaining target information stream type corresponding with the registration vocal print feature information of the selection, and the target is believed
The information of breath stream type is pushed to the target user；Wherein, when the target information stream type is that the target user registers
It is pre-set.
2. the intelligent refrigerator information flow method for pushing based on Application on Voiceprint Recognition according to claim 1, which is characterized in that the meter
Calculate the registration vocal print feature information of selection and the similarity of vocal print feature information to be identified, comprising: calculate choosing using following formula
The similarity of the registration vocal print feature information and vocal print feature information to be identified selected:
Wherein, Q (T, Si) ∈ [0,1], and T=| T1,T2……TN|, Si=| Si1,Si2……SiM|；
Wherein, Q (T, Si) it is the registration vocal print feature information S selected in vocal print feature information T to be identified and registration vocal print libraryi's
Similarity, i indicate the mark of different registration vocal print feature information, when the registration vocal print feature information in registration vocal print library includes more
When a, it is denoted as S1、S2……Si, SiEach element is for characterizing a vocal print feature parameter in set；Each element in T set
For characterizing a vocal print feature parameter.
3. the intelligent refrigerator information flow method for pushing based on Application on Voiceprint Recognition according to claim 2, which is characterized in that parameter N
It is equal with the value of parameter M, and T set in SiThe vocal print feature parameter for including in set is identical.
4. the intelligent refrigerator information flow method for pushing based on Application on Voiceprint Recognition according to claim 1, which is characterized in that described
According to the similarity judge that this selects register vocal print feature information whether as the target user it is pre-registered, comprising:
When the similarity is not less than given threshold, it is determined that the registration vocal print feature information of the selection is that the target user infuses in advance
Volume, otherwise, it determines the registration vocal print feature information of the selection is not that the target user is pre-registered.
5. any intelligent refrigerator information flow method for pushing based on Application on Voiceprint Recognition, feature exist in -4 according to claim 1
In before the voice for receiving target user, further includes:
The voice for receiving registration user extracts registration vocal print feature according to the voice of the registration user using the sound-groove model
Information, by the registration vocal print feature information storage of the registration user into registration vocal print library；
The registration vocal print feature information of the registration user is arranged the flow type for obtaining the registration user setting with it
Flow type binding, and store binding relationship.
6. a kind of intelligent refrigerator information flow driving means based on Application on Voiceprint Recognition characterized by comprising
Receiving module, for receiving the voice of target user；
Extraction module, for extracting vocal print feature information to be identified according to the voice of the target user using sound-groove model；
Computing module for selecting registration vocal print feature information one by one in registration vocal print library, and calculates the registration vocal print of selection
The similarity of characteristic information and vocal print feature information to be identified；
Judgment module, for judging that whether what this selected registers vocal print feature information as the target user according to the similarity
It is pre-registered；
Module is obtained, when the judgment module judging result, which is, is, then obtains the registration vocal print feature information pair with the selection
The target information stream type answered；Wherein, the target information stream type is that the target user is pre-set when registering；
Pushing module, for the information of the target information stream type to be pushed to the target user.
7. the intelligent refrigerator information flow driving means based on Application on Voiceprint Recognition according to claim 6, which is characterized in that the meter
Calculate module, the phase of registration vocal print feature information and vocal print feature information to be identified specifically for calculating selection using following formula
Like degree:
Wherein, Q (T, Si) ∈ [0,1], and T=| T1,T2……TN|, Si=| Si1,Si2……SiM|；
Wherein, Q (T, Si) it is the registration vocal print feature information S selected in vocal print feature information T to be identified and registration vocal print libraryi's
Similarity, i indicate the mark of different registration vocal print feature information, when the registration vocal print feature information in registration vocal print library includes more
When a, it is denoted as S1、S2……Si, SiEach element is for characterizing a vocal print feature parameter in set；Each element in T set
For characterizing a vocal print feature parameter.
8. the intelligent refrigerator information flow driving means based on Application on Voiceprint Recognition according to claim 7, which is characterized in that parameter N
It is equal with the value of parameter M, and T set in SiThe vocal print feature parameter for including in set is identical.
9. the intelligent refrigerator information flow driving means based on Application on Voiceprint Recognition according to claim 6, which is characterized in that described to sentence
Disconnected module is specifically used for when the similarity is not less than given threshold, it is determined that the registration vocal print feature information of the selection is
The target user is pre-registered, otherwise, it determines the registration vocal print feature information of the selection is not that the target user is preparatory
Registration.
10. according to the intelligent refrigerator information flow driving means based on Application on Voiceprint Recognition any in claim 6-9, feature exists
In, further includes: registration module, for receiving the voice of registration user, using the sound-groove model according to the registration user's
Voice extracts registration vocal print feature information, by the registration vocal print feature information storage of the registration user into registration vocal print library；
The flow type for obtaining the registration user setting, the letter that the registration vocal print feature information of the registration user is arranged with it
Stream type binding is ceased, and stores binding relationship.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811467356.0A CN109658941B (en) | 2018-12-03 | 2018-12-03 | Intelligent refrigerator information flow pushing method and device based on voiceprint recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811467356.0A CN109658941B (en) | 2018-12-03 | 2018-12-03 | Intelligent refrigerator information flow pushing method and device based on voiceprint recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109658941A true CN109658941A (en) | 2019-04-19 |
| CN109658941B CN109658941B (en) | 2021-02-19 |
Family
ID=66111684
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811467356.0A Active CN109658941B (en) | 2018-12-03 | 2018-12-03 | Intelligent refrigerator information flow pushing method and device based on voiceprint recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109658941B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110671875A (en) * | 2019-09-09 | 2020-01-10 | 珠海格力电器股份有限公司 | Control method for use conflict behavior of refrigerator compartment |
| CN110827834A (en) * | 2019-11-11 | 2020-02-21 | 广州国音智能科技有限公司 | Voiceprint registration method, system and computer-readable storage medium |
| CN114999488A (en) * | 2022-06-27 | 2022-09-02 | 中国电信股份有限公司 | Voice recognition method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8798995B1 (en) * | 2011-09-23 | 2014-08-05 | Amazon Technologies, Inc. | Key word determinations from voice data |
| CN104810025A (en) * | 2015-03-31 | 2015-07-29 | 天翼爱音乐文化科技有限公司 | Audio similarity detecting method and device |
| CN105244040A (en) * | 2015-07-20 | 2016-01-13 | 杭州联汇数字科技有限公司 | Audio signal consistency comparison method |
| CN108062354A (en) * | 2017-11-22 | 2018-05-22 | 上海博泰悦臻电子设备制造有限公司 | Information recommendation method, system, storage medium, electronic equipment and vehicle |
-
2018
- 2018-12-03 CN CN201811467356.0A patent/CN109658941B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8798995B1 (en) * | 2011-09-23 | 2014-08-05 | Amazon Technologies, Inc. | Key word determinations from voice data |
| CN104810025A (en) * | 2015-03-31 | 2015-07-29 | 天翼爱音乐文化科技有限公司 | Audio similarity detecting method and device |
| CN105244040A (en) * | 2015-07-20 | 2016-01-13 | 杭州联汇数字科技有限公司 | Audio signal consistency comparison method |
| CN108062354A (en) * | 2017-11-22 | 2018-05-22 | 上海博泰悦臻电子设备制造有限公司 | Information recommendation method, system, storage medium, electronic equipment and vehicle |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110671875A (en) * | 2019-09-09 | 2020-01-10 | 珠海格力电器股份有限公司 | Control method for use conflict behavior of refrigerator compartment |
| CN110671875B (en) * | 2019-09-09 | 2020-11-17 | 珠海格力电器股份有限公司 | Control method for use conflict behavior of refrigerator compartment |
| CN110827834A (en) * | 2019-11-11 | 2020-02-21 | 广州国音智能科技有限公司 | Voiceprint registration method, system and computer-readable storage medium |
| CN110827834B (en) * | 2019-11-11 | 2022-07-12 | 广州国音智能科技有限公司 | Voiceprint registration method, system and computer readable storage medium |
| CN114999488A (en) * | 2022-06-27 | 2022-09-02 | 中国电信股份有限公司 | Voice recognition method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109658941B (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109658941A (en) | A kind of intelligent refrigerator information flow method for pushing and device based on Application on Voiceprint Recognition | |
| CN108075892B (en) | A method, apparatus and device for speech processing | |
| US8200061B2 (en) | Signal processing apparatus and method thereof | |
| CN110166818A (en) | Wait match generation method, computer equipment and the storage medium of audio-video | |
| CN107798032A (en) | Response message treating method and apparatus in self-assisted voice session | |
| CN107563569A (en) | Hotel reservation method, apparatus and its equipment based on more wheel interactive voices | |
| CN109376265A (en) | Song recommendations list generation method, medium, device and calculating equipment | |
| CN103617192B (en) | The clustering method and device of a kind of data object | |
| CN108920450A (en) | Knowledge point reviewing method based on electronic equipment and electronic equipment | |
| CN106897700B (en) | Single-sample face recognition method and system | |
| CN105898525A (en) | Method of searching videos in specific video database, and video terminal thereof | |
| CN109493543A (en) | The recommended method of function scene, device | |
| CN110049377A (en) | Expression packet generation method, device, electronic equipment and computer readable storage medium | |
| CN108536762A (en) | A kind of high-volume text data automatically analyzes scheme | |
| WO2020024525A1 (en) | Electrical appliance control method and apparatus, storage medium and electrical appliance | |
| CN109377990A (en) | A kind of information processing method and electronic equipment | |
| CN103530313A (en) | Searching method and device of application information | |
| CN113782026A (en) | An information processing method, apparatus, medium and equipment | |
| CN108959889A (en) | A kind of Accreditation System and method of intelligent appliance | |
| CN109688430A (en) | A kind of court trial file playback method, system and storage medium | |
| CN115482824A (en) | Speaker recognition method and device, electronic equipment and computer readable storage medium | |
| CN109697676A (en) | Customer analysis and application method and device based on social group | |
| CN103327153A (en) | Method and device for grouping contact persons | |
| CN109002511A (en) | A kind of intelligent recommendation method and apparatus of public lavatory | |
| CN105550308A (en) | Information processing method, retrieval method and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |