CN110164450A - Login method, device, playback equipment and storage medium - Google Patents
Login method, device, playback equipment and storage medium Download PDFInfo
- Publication number
- CN110164450A CN110164450A CN201910384945.0A CN201910384945A CN110164450A CN 110164450 A CN110164450 A CN 110164450A CN 201910384945 A CN201910384945 A CN 201910384945A CN 110164450 A CN110164450 A CN 110164450A
- Authority
- CN
- China
- Prior art keywords
- account
- application
- voice signal
- user
- playback equipment
- 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 57
- 230000004044 response Effects 0.000 claims abstract description 16
- 238000012790 confirmation Methods 0.000 claims abstract description 15
- 230000001755 vocal effect Effects 0.000 claims description 90
- 239000013598 vector Substances 0.000 claims description 69
- 238000012545 processing Methods 0.000 claims description 22
- 230000015654 memory Effects 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 9
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000005192 partition Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000002093 peripheral effect Effects 0.000 description 9
- 230000001133 acceleration Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 230000005236 sound signal Effects 0.000 description 6
- 239000000284 extract Substances 0.000 description 5
- 238000009434 installation Methods 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 208000001491 myopia Diseases 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/083—Network architectures or network communication protocols for network security for authentication of entities using passwords
Abstract
Present disclose provides a kind of login method, device, playback equipment and storage mediums, belong to field of terminal technology.Method includes: the first voice signal that acquisition is entered, and the first voice signal is converted to the first text information;Identify that the first user is intended to the application identities with the first application from the first text information;When the first user, which is intended to account, logs in intention, determines and apply the first account to be logged in first party;According to the application identities of the first application, logging request is sent to the terminal for logging in the first account by the first application server;When receiving the confirmation response of the terminal returned by the first application server, the second current application is logged in by the first account.In the embodiments of the present disclosure, user is directly by inputting the first voice signal into playback equipment, triggers playback equipment by the first voice signal and carries out register, does not need user and scans the two-dimensional code using mobile phone that login can be realized, improve login efficiency.
Description
Technical field
This disclosure relates to field of terminal technology, in particular to a kind of login method, device, playback equipment and storage medium.
Background technique
With the development of terminal technology, the function of television set is more and more.Television set can not only play in television channel
Video, can with foradownloaded video play APP (Application, application program), pass through video playing APP play application clothes
The video being engaged in device.When television set plays the video in application server by video playing APP, television set can pass through society
It hands over and logs in video playing APP using account, to enjoy more privileges.
Currently, when the video playing APP on television set logs in video playing APP by social application account, Yong Hutong
Two-dimensional code display on remote control control television set is crossed, mobile phone is then dug out, social application is opened, walks close to television set, pass through mobile phone
On social application in scanning function scan the two dimensional code, confirmed on mobile phone, to complete login process.
User needs to dig out mobile phone in the above method, walks close to TV, can just scan the two-dimensional code and complete login process, above-mentioned mistake
Journey is cumbersome, low efficiency.
Summary of the invention
The embodiment of the present disclosure provides a kind of login method, device, playback equipment and storage medium, steps at present for solving
The problem of recording low efficiency.The technical solution is as follows:
On the one hand, a kind of login method is provided, the method is applied in playback equipment, which comprises
The first voice signal being entered is acquired, first voice signal is converted into the first text information;
Identify that the first user is intended to the application identities with the first application from first text information;
When first user, which is intended to account, logs in intention, determines and apply the first account to be logged in the first party
Number;
According to the application identities of first application, by the first application server to the terminal for logging in first account
Send logging request;
When receiving the confirmation response of the terminal returned by first application server, pass through described first
Account logs in the second current application.
In one possible implementation, described to identify that the first user is intended to and first from first text information
The application identities of application, comprising:
Word segmentation processing is carried out to first text information, obtains sequence of terms, includes multiple words in the sequence of terms
Language;
Digital vectors processing is carried out to the sequence of terms, term vector sequence is obtained, includes in the term vector sequence
The corresponding term vector of multiple words;
It in the term vector sequence inputting disaggregated model, will obtain that first user is intended to and first application is answered
With mark.
In alternatively possible implementation, it is described in the term vector sequence inputting disaggregated model, will obtain it is described
First user is intended to and the application identities of first application, comprising:
The term vector sequence is sequentially input in the first sorter network of disaggregated model by positive sequence, obtains the first classification
As a result;
The term vector sequence is sequentially input in reverse order in the second sorter network of the disaggregated model, obtains second
Classification results;
First classification results and second classification results are integrated, point of first voice signal is obtained
Class is as a result, include that first user is intended to the application identities applied with described first in the classification results.
In alternatively possible implementation, the determination applies the first account to be logged in, packet in the first party
It includes:
According to the application identities of first application, determines the account rule of first application, advised according to the account
Then, first account is identified from first text information;Alternatively,
Communicating number is identified from first text information, according to the application identities of first application, is obtained in institute
State in the first application with associated first account of the communicating number;Alternatively,
The first vocal print feature for extracting first voice signal, according to first vocal print feature, from vocal print feature library
Middle selection and the matched vocal print feature of the first vocal print feature, obtain associated first account of vocal print feature with selection, institute
State at least one vocal print feature for storing and being arranged in vocal print feature library.
In alternatively possible implementation, the application identities according to first application pass through the first application
Before server sends logging request to the terminal for logging in first account, the method also includes:
It is matched with first voice signal when existing in account library including first account, and in voice signal library
When the second voice signal, execute it is described according to it is described first application application identities, by the first application server to log in institute
The step of terminal of the first account sends logging request is stated, stores at least one account being arranged in the account library, it is described
At least one second voice signal being arranged is stored in voice signal library.
In alternatively possible implementation, the application identities according to first application pass through the first application
Before server sends logging request to the terminal for logging in first account, the method also includes:
The first voice signal mark and the second voice signal mark are obtained, first voice signal is identified as described in setting
The mark of the voice signal of first account, second voice signal are identified as and matched second language of first voice signal
The mark of sound signal;
When first voice signal mark is identical with the second voice signal mark, execution is described according to described the
The application identities of one application send the step of logging request by the first application server to the terminal for logging in first account
Suddenly.
In alternatively possible implementation, before the first voice signal that the acquisition is entered, the method is also
Include:
The second voice signal being entered is acquired, second voice signal is converted into the second text information;
Identify that second user is intended to from second text information;
When the second user, which is intended to account setting, to be intended to, it is corresponding to be placed to determine that the account setting is intended to
Second account;
Second account storage is stored into the account library, and by second voice signal to the voice
In signal library.
In alternatively possible implementation, the application identities according to first application pass through the first application
Before server sends logging request to the terminal for logging in first account, the method also includes:
When the playback equipment is non-laissezpasser equipment, alternatively, when acquire time of first voice signal with it is upper
When time difference between primary login is greater than preset time difference threshold value, alternatively, when second application is specified in application, execution
The application identities according to first application are sent by the first application server to the terminal for logging in first account
The step of logging request.
On the other hand, a kind of entering device is provided, described device is applied in playback equipment, and described device includes:
First voice signal is converted to the first text for acquiring the first voice signal being entered by acquisition module
This information;
Identification module, for identifying that the first user is intended to and the application of the first application is marked from first text information
Know;
Determining module, for determining in the first party application when first user is intended to account login intention
First account to be logged in;
Sending module, for the application identities according to first application, by the first application server to described in login
The terminal of first account sends logging request;
Login module, for when the confirmation response for receiving the terminal returned by first application server
When, the second current application is logged in by first account.
In one possible implementation, the identification module is also used to segment first text information
Processing obtains sequence of terms, includes multiple words in the sequence of terms;The sequence of terms is carried out at digital vectors
Reason obtains term vector sequence, includes the corresponding term vector of multiple words in the term vector sequence;The term vector sequence is defeated
Enter in disaggregated model, obtains first user and be intended to the application identities applied with described first.
In alternatively possible implementation, the identification module is also used to the term vector sequence is suitable by positive sequence
Sequence is input in the first sorter network of disaggregated model, obtains the first classification results;In reverse order sequentially by the term vector sequence
It is input in the second sorter network of the disaggregated model, obtains the second classification results;By first classification results and described
Second classification results are integrated, and obtain the classification results of first voice signal, include described the in the classification results
One user is intended to and the application identities of first application.
In alternatively possible implementation, the determining module is also used to the application mark according to first application
Know, determine the account rule of first application, according to account rule, described the is identified from first text information
One account;Alternatively,
The determining module is also used to identify communicating number from first text information, according to first application
Application identities, obtain it is described first application in associated first account of the communicating number;Alternatively,
The determining module is also used to extract the first vocal print feature of first voice signal, according to first sound
Line feature, selection and the matched vocal print feature of the first vocal print feature from vocal print feature library obtain special with the vocal print of selection
Associated first account is levied, at least one vocal print feature being arranged is stored in the vocal print feature library.
In alternatively possible implementation, the application identities according to first application pass through the first application
Before server sends logging request to the terminal for logging in first account, described device further include:
It is matched with first voice signal when existing in account library including first account, and in voice signal library
When the second voice signal, execute it is described according to it is described first application application identities, by the first application server to log in institute
The step of terminal of the first account sends logging request is stated, stores at least one account being arranged in the account library, it is described
At least one second voice signal being arranged is stored in voice signal library.
In alternatively possible implementation, described device further include:
Module is obtained, for obtaining the first voice signal mark and the second voice signal mark, first voice signal
It is identified as the mark that the voice signal of first account is set, second voice signal is identified as to be believed with first voice
The mark of number matched second voice signal;
The sending module is also used to when first voice signal mark is identical with the second voice signal mark
When, according to the application identities of first application, sent by the first application server to the terminal for logging in first account
Logging request.
In alternatively possible implementation, described device further include:
The acquisition module is also used to acquire the second voice signal being entered, second voice signal is converted to
Second text information;
The identification module is also used to identify that second user is intended to from second text information;
The determining module is also used to determine that the account is set when the second user is intended to account setting intention
It sets and is intended to corresponding second account to be placed;
Memory module, for storing second account into the account library, and by second voice signal
It stores in the voice signal library.
In alternatively possible implementation, described device further include:
The sending module is also used to when the playback equipment is non-laissezpasser equipment, alternatively, when acquisition described first
When time difference between the time of voice signal and last login is greater than preset time difference threshold value, answered alternatively, working as described second
With being specified in application, according to the application identities of first application, by the first application server to logging in first account
Number terminal send logging request.
On the other hand, a kind of playback equipment is provided, the playback equipment includes processor and memory, the memory
In be stored at least one instruction, at least a Duan Chengxu, code set or instruction set, described instruction, described program, the code set
Or described instruction collection is loaded by the processor and is executed with operation performed in above-mentioned login method.
On the other hand, a kind of computer readable storage medium is provided, is stored in the computer readable storage medium
At least one instruction, at least a Duan Chengxu, code set or instruction set, described instruction, described program, the code set or the finger
Collection is enabled to be loaded by processor and executed to realize operation performed in above-mentioned login method.
The technical solution that the embodiment of the present disclosure provides has the benefit that
In the embodiments of the present disclosure, playback equipment acquires the first voice signal being entered, and the first voice signal is converted
For the first text information;Identify that the first user is intended to the application identities with the first application from the first text information;When the first use
When family is intended to account login intention, determines and apply the first account to be logged in first party;According to the application mark of the first application
Know, logging request is sent to the terminal for logging in the first account by the first application server;It is taken when receiving by the first application
When the confirmation response for the terminal that business device returns, passes through the first account logs in currently second and apply.When user's control playback equipment
When login, user triggers playback equipment directly by inputting the first voice signal into playback equipment, by the first voice signal
Register is carried out, playback equipment identifies that the first user of the first voice signal is intended to, and is intended to when the first user is intended to log in
When, subsequent login operation is carried out, user directly inputs the i.e. triggerable playback equipment of the first voice signal and logs in during being somebody's turn to do
Operation, is not needed user and is scanned the two-dimensional code using mobile phone, improve login efficiency.
Detailed description of the invention
In order to illustrate more clearly of the technical solution in the embodiment of the present disclosure, will make below to required in embodiment description
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present disclosure, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of implementation environment of the login method provided according to the embodiment of the present disclosure;
Fig. 2 is a kind of login method flow chart provided according to an exemplary embodiment;
Fig. 3 is a kind of architecture diagram of account setting provided according to an exemplary embodiment;
Fig. 4 is a kind of login method flow chart provided according to an exemplary embodiment;
Fig. 5 is a kind of schematic diagram of the disaggregated model assorting process provided according to an exemplary embodiment;
Fig. 6 is a kind of schematic diagram of the login method provided according to an exemplary embodiment;
Fig. 7 is the matched schematic diagram of a kind of voice signal provided according to an exemplary embodiment;
Fig. 8 is the architecture diagram logged according to a kind of account that an exemplary embodiment provides;
Fig. 9 is a kind of block diagram of the entering device provided according to the embodiment of the present disclosure;
Figure 10 is a kind of structural schematic diagram of the playback equipment provided according to the embodiment of the present disclosure.
Specific embodiment
To keep the purposes, technical schemes and advantages of the disclosure clearer, below in conjunction with attached drawing to disclosure embodiment party
Formula is described in further detail.
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Fig. 1 is the implementation environment of the embodiment of the present disclosure, includes playback equipment, terminal, the first application clothes in the implementation environment
Business device.Playback equipment and terminal pass through network connection between application server respectively.The first application of installation in terminal, being based on should
First application can log in the first application server, to carry out information exchange with the first application server.First application can be with
For social networking application, payment application or shopping application etc..The second application of installation on playback equipment, the second application and first are answered
It, can not also be identical with can be identical;This is not especially limited in the embodiments of the present disclosure.When the second application and the first application
When identical, the second application or social networking application, payment application or shopping application.When the second application and the first application
When different, the second application can play application, game application for TV (television, television set) video playing APP, audio
Deng.
When the second application and identical the first application, when needing to log in the first application server on playback equipment, and eventually
Passed through on end the first account log in the first application server when, user can not need on playback equipment input account and
Password, user directly pass through voice control playback equipment and send logging request to terminal by the first application server.Work as terminal
Allow when logging in the first account on the playback equipment, confirmation response is returned to playback equipment by the first application server.When
When playback equipment receives the confirmation response of terminal return, the first application is logged in by the first account.
It can also include the second application server in the implementation environment when the second application and different the first application.It plays
Equipment can log in the second application server based on the second application, to carry out information exchange with the second application server.Also,
Information exchange can be carried out between second application server and the first application server, so that playback equipment can be by means of second
Information exchange between application server realizing and the first application server.Correspondingly, when needing to log in the on playback equipment
Two application servers, and when having logged on the first application server in terminal, user can not need to input in playback equipment
Account and password, user directly pass through voice control playback equipment and pass through the first application server and the second application server to end
End sends logging request.When terminal permission logs in the first account on the playback equipment, pass through the first application server and the
Two application servers return to confirmation response to playback equipment.When playback equipment receives the confirmation response of terminal return, pass through
First account logs in the second application.
In the embodiments of the present disclosure, user can be directly to playback equipment input speech signal, and playback equipment identifies the language
The user of sound signal is intended to;When the user be intended to account log in be intended to when, directly carry out subsequent register, from without
It wants user to walk close to playback equipment, scans the two-dimensional code control playback equipment and carry out register, improve login efficiency.And into
Before row logs in, the associated account of voice signal can also be arranged in user in playback equipment, broadcast by voice signal control
When putting equipment and being logged in, playback equipment can be controlled by the voice signal and be stepped on by the associated account of the voice signal
Record, improves safety.
Wherein, playback equipment can be any equipment that can have playing function such as television set or computer.Terminal can
Think mobile phone terminal, PAD (Portable Android Device, tablet computer) any installation such as terminal or computer equipment
The equipment of short-sighted frequency APP.First application server, which refers to, provides the server of background service for terminal, can be a service
Device, or the server cluster consisted of several servers or a cloud computing server center, the embodiment of the present disclosure
This is not especially limited.In one possible implementation, the first application server can be first installed in terminal
The background server of application.Equally, the second application server, which refers to, provides the server of background service, Ke Yiwei for playback equipment
One server, or the server cluster consisted of several servers or a cloud computing server center, this public affairs
It opens embodiment and this is not especially limited.In one possible implementation, the second application server can be playback equipment
The background server of second application of middle installation.
Fig. 2 is a kind of flow chart of the login method provided according to an exemplary embodiment, and this method is applied to be set in broadcasting
It is standby.As shown in Fig. 2, in the embodiments of the present disclosure, being illustrated for account is arranged in playback equipment.This method include with
Lower step:
Step 201: playback equipment acquires the second voice signal being entered.
In one possible implementation, playback equipment can configure control equipment, and control and is arranged in equipment
One voice input button, user can pin the first voice input button, by the control equipment to playback equipment input the
Two voice signals.Correspondingly, this step can be with are as follows: when the first voice input button for controlling equipment is triggered, control equipment
The second voice signal being entered is acquired, sends the second voice signal to playback equipment, playback equipment receives the second voice signal.
Control equipment is the matched equipment of playback equipment.For example, control equipment can be television set when playback equipment is television set
Remote controler.
In alternatively possible implementation, user can wake up the voice collecting function of playback equipment by voice,
Then playback equipment starts to acquire voice signal.Correspondingly, this step can be with are as follows: the detection of playback equipment progress voice signal;
When detecting specified speech signal, the second voice signal being entered is acquired.Wherein, specified speech signal can be any use
In the voice signal for waking up playback equipment.For example, specified speech signal can be " Hi, television set " etc..
In alternatively possible implementation, the second voice input button, user are set in the main interface of playback equipment
The second voice input button can be clicked by controlling equipment, then input the second voice signal to playback equipment.Correspondingly,
This step can be with are as follows: playback equipment shows main interface, includes the second voice input button in the main interface;When the second voice inputs
When button is triggered, playback equipment acquires the second voice signal being entered.Account is included at least in second voice signal to be arranged
The word of intention can also include account to be placed.
For example, user, which says, " is arranged the account of my application 1 when user wants to be arranged in playback equipment and applies 1 account
Number are as follows: 112345678 ".Playback equipment, which obtained, " account of my application 1 was arranged are as follows: 112345678 " corresponding second voices
Signal.
Step 202: the second voice signal is converted to the second text information by playback equipment.
For example, the second voice signal is converted to the second text information by playback equipment, the second text information is " to be arranged mine
Using 1 account are as follows: 112345678 ".
Step 203: playback equipment identifies that second user is intended to from the second text information.
This step can be realized by following steps (1) to (3), comprising:
(1) playback equipment carries out word segmentation processing to the second text information, obtains the second sequence of terms, in the second sequence of terms
Including multiple second words.
In this step, playback equipment can carry out word segmentation processing to the second text information by Words partition system.Correspondingly,
This step can be with are as follows: playback equipment sends the second text information to Words partition system, and Words partition system receives the second text information, to the
Two text informations carry out word segmentation processing, obtain multiple second words, multiple second words are formed the second sequence of terms, to broadcasting
Equipment sends the second sequence of terms;Playback equipment receives the second sequence of terms.
It should be noted is that Words partition system can be any Words partition system for being able to carry out word segmentation processing.For example, should
Words partition system can be the Words partition system of open source.Also, Words partition system can be the Words partition system being deployed in playback equipment,
It can be third party's Words partition system independently of playback equipment.In the embodiments of the present disclosure, this is not especially limited.
For example, the second text information be " account of my social application is set are as follows: 112345678 ", then the second word sequence
Be classified as [setting/I// using 1/ ,/account/is/112345678].
(2) playback equipment carries out digital quantization processing to second sequence of terms, obtains the second word vectors sequence, this
Two word vectors sequences include the corresponding term vector of multiple second words.
Playback equipment obtains the corresponding term vector of each second word, and the corresponding term vector of each second word is formed the
Two word vectors sequences.Wherein, it is loaded with term vector library in playback equipment, includes the corresponding word of multiple words in the term vector library
Vector.Correspondingly, playback equipment obtain the step of each second word corresponding term vector can be with are as follows: playback equipment from the word to
Amount inquires the corresponding term vector of each second word in library.
In the embodiments of the present disclosure, word vectors are carried out word feature extraction so as to facilitate, improved by playback equipment
The efficiency of subsequent intention assessment.
(3) playback equipment in the second word vectors sequence inputting disaggregated model, will obtain second user intention.
Playback equipment inputs the second word vectors in disaggregated model, and the second voice signal of output and each designated user anticipate
Matching degree between figure;According to the matching degree between the second voice signal and each designated user intention, from each designated user
The highest designated user of matching degree in intention between selection and the second voice signal is intended to, and the designated user of selection is intended to make
For second user intention.
It should be noted is that designated user be intended to can only include user be intended to, can also include user be intended to and
Application identities.For example, the designated user is intended to be login when designated user is intended to be intended to including user with application identities
Account-applies 1, and login account-applies 2, and account is arranged-applies 1, and account is arranged-applies 2 and other settings etc..
Need to illustrate on the other hand, disaggregated model can for it is any can be based on the mould that word sequence vector is classified
Type.For example, disaggregated model can be LSTM (Long Short-Term Memory, length Memory Neural Networks) disaggregated model,
It and can be unidirectional LSTM disaggregated model, or two-way LSTM disaggregated model.In the embodiments of the present disclosure, to classification mould
Type is not especially limited.
When disaggregated model is two-way LSTM disaggregated model, playback equipment is by the second word vectors sequence according to positive sequence sequence
The first sorter network for inputting two-way LSTM disaggregated model, obtains third classification results, by the second word vectors sequence according to
Sequence sequentially inputs the second sorter network of two-way LSTM disaggregated model, obtains the 4th classification results, by third classification results and
Four classification results are integrated, and second user intention is obtained.
Wherein, third classification results include the first matching degree between the second voice signal and each designated user intention,
4th classification results also include the second matching degree between the second voice signal and each designated user intention;Correspondingly, playing
Equipment integrates third classification results and the 4th classification results, and obtaining the step of second user is intended to can be with are as follows: broadcasting is set
It is standby by the second voice signal in third classification results and each designated user be intended between the first matching degree and the 4th point
The second matching degree between the second voice signal in class result and each designated user intention is weighted summation, obtains second
Matching degree between voice signal and each designated user intention, selection and the second voice signal from each designated user intention
Between the highest designated user of matching degree be intended to, the designated user selected is intended to as second user intention.
Wherein, the first sorter network includes multiple LSTM units, and the second sorter network also includes multiple LSTM units, and the
The quantity for the LSTM unit that the quantity for the LSTM unit that one sorter network includes and the second sorter network include can be equal, can also
With unequal.In the embodiments of the present disclosure, the quantity for the LSTM unit for including with the first sorter network and the second sorter network packet
It is illustrated for the quantity of the LSTM unit included is equal.
For example, when disaggregated model be two-way LSTM disaggregated model when, playback equipment respectively will [setting/I// apply 1/
/ account/be/112345678] corresponding second word vectors input in LSTM, the second voice signal of output and each specified
User be intended between matching degree, respectively 1: it is 0.02 that account, which logs in-apply 1 corresponding matching degree, and account logs in-apply 2
Matching degree be 0.01, account be arranged-apply 1 matching degree be 0.95, account be arranged-apply 2 matching degree be 0.01, other
The matching degree of setting is 0.01;Playback equipment determine the second user of the second voice signal be intended to account be arranged-apply 1.
Step 204: when the second user, which is intended to account setting, to be intended to, playback equipment determines account setting intention pair
The second account to be placed answered.
It in one possible implementation, include the second account to be placed in the second voice signal.Correspondingly, playing
Equipment obtains the second account to be placed from the second text information.In alternatively possible implementation, work as playback equipment
When identifying that second user is intended to account setting intention, playback equipment prompt user inputs the second account to be placed.It plays
Equipment receives the second account being entered.Wherein, user can input the second account, user to playback equipment by control equipment
The second account can also be inputted to playback equipment by way of voice signal.Correspondingly, working as side of the user by voice signal
When formula inputs the second account to playback equipment, this step can be with are as follows: playback equipment acquires third voice signal, and third voice is believed
Third text information number is converted to, the second account for including in third text information is extracted.
Step 205: playback equipment stores the second account into account library, and the second voice signal is stored to voice
In signal library.
In one possible implementation, playback equipment directly stores the second voice signal.Correspondingly, this step can be with
Are as follows: playback equipment stores the second voice signal into voice signal library.In alternatively possible implementation, playback equipment
The second voice signal is not stored directly, but stores the second vocal print feature of the second voice signal.Correspondingly, this step can be replaced
It is changed to:
Playback equipment extracts the second vocal print feature of the second voice signal, by the second vocal print characteristic storage to vocal print feature library
In.Wherein, playback equipment can extract the vocal print feature of the second voice signal by any vocal print feature extracting method, obtain the
Two vocal print features.Wherein, which can be MFCC (Mel-scale Frequency Cepstral
Coefficients, mel cepstrum coefficients).
It should be noted is that playback equipment stores the second account into account library, and by the second vocal print feature
It, can be with the second account of associated storage and the second vocal print feature, in order to subsequent to user after storing in vocal print feature library
It is verified, when only vocal print feature and account match, just allows to carry out register.
The embodiment of the present disclosure provides a kind of system architecture that login account is arranged, and includes language in playback equipment referring to Fig. 3
Sound control access layer, speech recognition system and semantics recognition system;When household equipment receives the second voice signal, to the voice
It controls access layer and sends the second speech recognition request and the request of the second semantics recognition.Voice control access layer is by the second speech recognition
Request is transmitted to speech recognition system, and the request of the second semantics recognition is transmitted to semantics recognition system.Wherein, which knows
It does not invite in summation the second semantics recognition request and carries the second voice signal.Speech recognition system is identified from the second voice signal
Second vocal print feature stores the second vocal print feature.Semantics recognition system identifies the second account from the second voice signal, storage the
Two accounts.It with playback equipment is TV in Fig. 3, control equipment is remote controler, and the second application that playback equipment is currently opened is TV
Video APP, user are inputted for the second voice signal by remote controler and are illustrated.
In the embodiments of the present disclosure, before user is logged in by voice control playback equipment, user is existed by voice signal
Second account to be logged in is set in playback equipment, and playback equipment stores the second account and the second voice letter that the second account is arranged
Number, so that playback equipment can be based on the second account being arranged when subsequent user controls playback equipment login by voice signal
Number and the second voice signal verified;After being verified, register is just carried out, to improve safety.
Fig. 4 is a kind of flow chart of the login method provided according to an exemplary embodiment, and this method is applied to be set in broadcasting
In standby.As shown in figure 4, in the embodiments of the present disclosure, being illustrated for being logged in playback equipment.This method includes
Following steps:
Step 401: playback equipment acquires the first voice signal being entered.
This step and step 201 are similar, and details are not described herein.Also, it includes at least in the first voice signal for identifying
The word that user is intended to and the word for identifying application identities.It also, may include to be logged in the first voice signal
One account can not also include the first account to be logged in.
For example, collected first voice signal of playback equipment is " I, which wants to log in, applies 1 account " corresponding voice letter
Number.
Step 402: the first voice signal is converted to the first text information by playback equipment.
This step and step 202 are similar, and details are not described herein.For example, the first voice signal is converted to by playback equipment
One text information is " I, which wants to log in, applies 1 account ".
Step 403: playback equipment identifies that the first user is intended to the application identities with the first application from the first text information.
This step can be realized by following steps (1) to (3), comprising:
(1) playback equipment carries out word segmentation processing to the first text information, obtains the first sequence of terms, in the first sequence of terms
Including multiple first words.
For example, playback equipment carries out word segmentation processing to " I, which wants to log in, applies 1 account ", obtaining the first sequence of terms is
[I/want/login/apply 1/ account].
(2) playback equipment carries out digital vectors processing to the first sequence of terms, obtains the first term vector sequence, the first word
It include the corresponding term vector of multiple first words in sequence vector.
Playback equipment obtains the corresponding term vector of each first word, and the corresponding term vector of each first word is formed the
One word vectors sequence.For example, household equipment obtains " I " " desired " " login " " applying 1 " " account " corresponding term vector difference
For (0.1,0.2,0.3) (0.1,0.3,0.4) (0.9,0.8,0.4) (0.9,0.1,0.2) (0.8,0.6,0.5).
(3) playback equipment in the first term vector sequence inputting disaggregated model, will obtain the first user intention and the first application
Application identities.
Playback equipment inputs the first word vectors in disaggregated model, and the first voice signal of input and each designated user anticipate
Matching degree between figure;According to the matching degree between the first voice signal and each designated user intention, from each designated user
The highest designated user of matching degree in intention between selection and the second voice signal is intended to, and the designated user of selection is intended to make
For the first user intention.It wherein, include the application identities of the first application in the first user intention, playback equipment is anticipated from the first user
The application identities of the first application are obtained in figure.
When disaggregated model is two-way LSTM, the first word vectors are sequentially inputted two-way LSTM according to positive sequence by playback equipment
First sorter network of disaggregated model, obtains the first classification results, the first word vectors sequence is sequentially inputted according to inverted order double
To the second sorter network of LSTM disaggregated model, obtain the second classification results, by the first classification results and the second classification results into
Row integration obtains the first user intention.
For example, with reference to Fig. 5, playback equipment is successively by " I " " desired " " login " " applying 1 " " account " corresponding term vector
(0.1,0.2,0.3) (0.1,0.3,0.4) (0.9,0.8,0.4) (0.9,0.1,0.2) (0.8,0.6,0.5) sequentially inputs two-way
In 5 LSTM units in first sorter network of LSTM disaggregated model, the first classification results are obtained.Playback equipment is by " account "
" applying 1 " " login " " desired " " I " corresponding term vector (0.8,0.6,0.5) (0.9,0.1,0.2) (0.9,0.8,0.4)
It is mono- that (0.1,0.3,0.4) (0.1,0.2,0.3) sequentially inputs 5 LSTM in the second sorter network of two-way LSTM disaggregated model
In member, the second classification results are obtained.Playback equipment integrates the first classification results and the second classification results, obtains the first language
It is 0.95 that matching degree between sound signal and each designated user intention, which is respectively as follows: account to log in-apply 1 corresponding matching degree,
The matching degree that account logged in-applied 2 is 0.01, and the matching degree that account is arranged-applies 1 is 0.02, and account is arranged-applies 2
It is 0.01 with degree, the matching degree of other settings is 0.01;Playback equipment determines that the first user of the second voice signal is intended to account
Number login-applies 1.The application identities of first application are using 1.
For example, with reference to Fig. 6, when playback equipment gets the first voice signal, the first voice signal is inputted into Words partition system,
The first sequence of terms is obtained, by the first sequence of terms input word embedded system, the first word vectors sequence is obtained, by the first word
Sequence vector inputs two-way LSTM model, and the first user of input is intended to.
Step 404: when the first user, which is intended to account, logs in intention, playback equipment, which is determined, to be applied in first party wait log in
The first account.
Playback equipment can directly identify the first account, namely the first following realization side from the first text information
Formula;Playback equipment is also based on the first account of communication number acquisition namely following second of implementation;Playback equipment may be used also
To obtain the first account, namely the third following implementation according to the vocal print feature of the first voice signal.
For the first implementation, this step can be realized by following steps (1) to (2), comprising:
(1) playback equipment determines the account rule of the first application according to the application identities of the first application.
The corresponding relationship of application identities and account rule is stored in playback equipment.Correspondingly, this step can be with are as follows: broadcasting is set
The standby application identities according to the first application, from the account rule for obtaining the first application in the corresponding relationship of application identities and account rule
Then.
For example, the account rule using 1 is that account is 5-12 continuous numbers when the first application is using 1.When
When one application is using 2, the account rule using 2 is the continuous number that account is 12.
(2) playback equipment identifies the first account according to the account rule of the first application from the first text information.
Playback equipment identifies the first account for meeting the account rule of the first application from the first text information.
For second of implementation, this step can be with are as follows: and playback equipment identifies communicating number from the first text information,
According to first application application identities, obtain first application in associated first account of the communicating number.Wherein, messenger
Code can be telephone number etc..
For the third implementation, this step can be realized by following steps (A) to (C), comprising:
(A) playback equipment extracts the first vocal print feature of the first voice signal.
The step of this step is with the second vocal print feature for extracting the second voice signal in step 205 is similar, no longer superfluous herein
It states.
(B) playback equipment is according to the first vocal print feature, selection and the matched sound of the first vocal print feature from vocal print feature library
Line feature.
At least one vocal print feature being arranged is stored in vocal print feature library.Playback equipment determines the first vocal print feature harmony
The matching degree between each vocal print feature in line feature database;According to each vocal print in the first vocal print feature and vocal print feature database
Matching degree between feature, from vocal print feature library selection the first vocal print feature between the highest vocal print feature of matching degree.
For each vocal print feature in vocal print feature library, playback equipment determine the first vocal print feature and the vocal print feature it
Between COS distance, using the COS distance as the matching degree between the first vocal print feature and the vocal print feature.
(C) playback equipment obtains associated first account of vocal print feature with selection.
User is arranged after account in playback equipment, the second account and the second vocal print of the setting of playback equipment associated storage
Feature.Correspondingly, in this step, playback equipment is obtained and is closed with the vocal print feature of the selection according to the vocal print feature of the selection
First account of connection.
Step 405: playback equipment determines in account library whether to include the first account, and determine in voice signal library whether
In the presence of with matched second voice signal of the first voice signal.
When account is arranged, when playback equipment stores the second voice signal being arranged into voice signal library, broadcast
It puts equipment to determine in voice signal library with the presence or absence of can be in the first voice signal matched second voice signal the step of are as follows: broadcast
Equipment is put to extract the first vocal print feature of the first voice signal and extract the second voice signal of each of voice signal library
Second vocal print feature;Determine the matching degree between the first vocal print feature and the second vocal print feature of each second voice signal;Root
According to the matching degree between the first vocal print feature and the second vocal print feature of each second voice signal, when the first vocal print feature and often
When including the matching degree more than preset matching degree threshold value in the matching degree between the second vocal print feature of a second voice signal, broadcast
It puts equipment and determines exist and matched second voice signal of the first voice signal.When the first vocal print feature and each second voice are believed
Number the second vocal print feature between matching degree in there is no more than preset matching degree threshold value matching degree when, playback equipment determine
There is no with matched second voice signal of the first voice signal, referring to Fig. 7.
When account is arranged, playback equipment is by the second vocal print characteristic storage of the second voice signal being arranged to voice
When in signal library, in this step, playback equipment do not need repeat extract the second voice signal the second vocal print feature, directly into
The matching degree operation of row vocal print feature.Wherein, preset matching degree threshold value, which can according to need, is configured and changes, at this
In open embodiment, preset matching degree threshold value is not especially limited;For example, preset matching degree threshold value can for 85% or
90%.
It should be noted is that when including the first account in account library, and exist and the first voice signal matched the
Two voice signals execute step 406;When not including the first account in account library, or there is no match with the first voice signal
The second voice signal when, export the first standby signal.First standby signal is for prompting user to re-enter voice signal.
And the reason that in first standby signal further includes that it fails to match.Should it fails to match reason can be mismatched for vocal print or account
Mismatch etc..Also, first standby signal can be voice signal, or prompt information.In the embodiments of the present disclosure,
It is not especially limited with the concrete form of first standby signal.
Need to illustrate on the other hand, when in account library include the first account, and in voice signal library exist and the first language
When matched second voice signal of sound signal, playback equipment can also detect whether the second voice signal and the first account are same
A user setting.Correspondingly, returning method further include:
Playback equipment obtains the first voice signal mark and the second voice signal mark, and the first voice signal is identified as setting
The mark of the voice signal of first account, the second voice signal is identified as setting to be believed with matched second voice of the first voice signal
Number mark;When the first voice signal mark is identical with the second voice signal mark, step 406 is just executed.When the first voice
When signal identification and different the second voice signal mark, the second standby signal, the second standby signal and the first standby signal are exported
Can be identical, it can not also be identical.
In the embodiments of the present disclosure, in addition to whether the first account of progress matches with the account in account library and the second language
Outside the whether matched process of the second voice signal in sound signal and voice signal library, the second voice signal and the first account are also carried out
Number whether matched process, so that user A be avoided to be provided with account 1 in playback equipment, user B is provided in playback equipment
Account 2, but user A controls the case where account 2 logs in using vocal print, further improves the safety of login.
It should be noted is that execute the step 404, can directly execute in step 406 " playback equipment is according to
The application identities of one application send logging request to the terminal for logging in the first account by the first application server " the step of.
Step 406: matched with the first voice signal when existing in account library including the first account, and in voice signal library
When the second voice signal, playback equipment is according to the application identities of the first application, by the first application server to logging in the first account
Number terminal send logging request.
This step can be realized by following steps (1) to (3), comprising:
(1) playback equipment sends the first logging request to the first application server according to the application identities of the first application, the
One logging request at least carries the first account.
First logging request can also carry in the application identities of device identification and the second application of playback equipment at least
One.
(2) first application servers receive the first logging request of playback equipment, to the terminal hair for logging in first account
Send the second logging request.
Second logging request can carry at least one in the application identities of device identification and the second application of playback equipment
It is a.
(3) terminal receives the second logging request of the first application server, shows ACK button and cancel button.
When user is with being intended to log in the first account on playback equipment, user can click ACK button;When user's difference
When being intended to log in the first account on playback equipment, user can click cancel button.When ACK button is triggered, terminal passes through
First application server sends confirmation response to playback equipment;When cancel button is triggered, terminal passes through the first application service
Device is sent to playback equipment cancels response.
Step 407: when receiving the confirmation response of the terminal returned by the first application server, playback equipment passes through
First account logs in the second current application.
It should be noted is that in step 406 " playback equipment according to first application application identities, pass through first
Application server sends logging request to the terminal for logging in the first account " it is actually the process that using terminal is verified.?
In the embodiment of the present disclosure, 405 can also be executed the step, directly passes through the first account in execution step 407 without verifying
The step of logging in the second current application.
Some rules can also be arranged in playback equipment, for example, then executing the step when playback equipment is laissezpasser equipment
405, the step of current second is applied directly is logged in by the first account in execution step 407.When playback equipment is non-tests
Demonstrate,prove equipment when, execute first carry out in step 406 " playback equipment according to first application application identities, pass through first application clothes
After the step of terminal transmission logging request of the business device to the first account of login ", step 407 is just executed.
For another example, it when the time difference between login twice is shorter, does not need to be verified yet.Correspondingly, when acquisition first
When time difference between the time of voice signal and last login is less than preset time difference threshold value, 405 are executed the step, directly
It executes in step 407 and the step of current second is applied is logged in by the first account.When the time difference is poor greater than preset time
When threshold value, execute first carry out in step 406 " playback equipment according to first application application identities, pass through the first application service
After the step of terminal transmission logging request of the device to the first account of login ", step 407 is just executed.
For another example, only login security requires relatively high application to be verified, and login security is relatively low
Using not needing to be verified.Correspondingly, directly executing step when second using not being specified in application, executing the step 405
The step of current second is applied is logged in by the first account in 407.When the second application is specified in application, execution first carries out
In step 406 " playback equipment according to the application identities of the first application, by the first application server to logging in first account
After the step of terminal transmission logging request ", step 407 is just executed.Wherein, specify application that can answer for payment application, shopping
With etc..
The embodiment of the present disclosure provides a kind of system architecture of login account, includes voice control in playback equipment referring to Fig. 8
Access layer, speech recognition system, semantics recognition system, external login system and inquiry system processed;Household equipment receives first
When voice signal, the first speech recognition request and the request of the first semantics recognition are sent to the voice control access layer.Voice control
First speech recognition request is transmitted to speech recognition system by access layer, and the request of the first semantics recognition is transmitted to semantics recognition system
System.Wherein, the first voice signal is carried in first speech recognition request and the request of the first semantics recognition.Speech recognition system
The first vocal print feature is identified from the first voice signal, and the first vocal print feature is transferred to inquiry system.Semantics recognition system from
The first account is identified in first voice signal, and the first account is transferred to inquiry system.Inquiry system receives the first vocal print feature
With the first account, when including the first account in account library, and in vocal print feature library include and the first vocal print feature matched second
When vocal print feature, voice control access layer sends logging request to external login system, to request in the second current application
Log in the first account.It is in fig. 8 TV with playback equipment, control equipment is remote controler, and what playback equipment was currently opened second answers
With for TV video APP, user inputs the first voice signal by remote controler, and inquiry system is audio and account inquiry system is
Example is illustrated.
In the embodiments of the present disclosure, playback equipment acquires the first voice signal being entered, and the first voice signal is converted
For the first text information;Identify that the first user is intended to the application identities with the first application from the first text information;When the first use
When family is intended to account login intention, determines and apply the first account to be logged in first party;According to the application mark of the first application
Know, logging request is sent to the terminal for logging in the first account by the first application server;It is taken when receiving by the first application
When the confirmation response for the terminal that business device returns, passes through the first account logs in currently second and apply.When user's control playback equipment
When login, user triggers playback equipment directly by inputting the first voice signal into playback equipment, by the first voice signal
Register is carried out, playback equipment identifies that the first user of the first voice signal is intended to, and is intended to when the first user is intended to log in
When, subsequent login operation is carried out, user directly inputs the i.e. triggerable playback equipment of the first voice signal and logs in during being somebody's turn to do
Operation, is not needed user and is scanned the two-dimensional code using mobile phone, improve login efficiency.
Fig. 9 is a kind of block diagram of the entering device provided according to an exemplary embodiment.The device is for executing above-mentioned login
The step of playback equipment executes in method, referring to Fig. 9, device includes:
First voice signal is converted to the first text for acquiring the first voice signal being entered by acquisition module 901
This information;
Identification module 902, for identifying that the first user is intended to and the application of the first application is marked from first text information
Know;
Determining module 903, for when first user be intended to account log in be intended to when, determine the first party apply to
The first account logged in;
Sending module 904, for the application identities according to first application, by the first application server to log in this
The terminal of one account sends logging request;
Login module 905, for when receive by first application server return the terminal confirmation response when,
The second current application is logged in by first account.
In one possible implementation, the identification module 902 is also used to carry out at participle first text information
Reason, obtains sequence of terms, includes multiple words in the sequence of terms;Digital vectors processing is carried out to the sequence of terms, is obtained
Term vector sequence includes the corresponding term vector of multiple words in the term vector sequence;By the term vector sequence inputting disaggregated model
In, obtain application identities of first user intention and first application.
In alternatively possible implementation, which is also used to the term vector sequence by positive sequence sequence
It is input in the first sorter network of disaggregated model, obtains the first classification results;The term vector sequence is sequentially inputted in reverse order
Into the second sorter network of the disaggregated model, the second classification results are obtained;By first classification results and the second classification knot
Fruit is integrated, and the classification results of first voice signal are obtained, include in the classification results first user be intended to and this
The application identities of one application.
In alternatively possible implementation, which is also used to the application mark according to first application
Know, determines that the account rule of first application identifies first account according to account rule from first text information;
Alternatively,
The determining module 903 is also used to identify communicating number from first text information, according to answering for first application
With mark, obtain in first application with associated first account of the communicating number;Alternatively,
The determining module 903 is also used to extract the first vocal print feature of first voice signal, according to first vocal print spy
Sign, selection and the matched vocal print feature of the first vocal print feature, obtain and are associated with the vocal print feature of selection from vocal print feature library
The first account, store at least one vocal print feature being arranged in the vocal print feature library.
In alternatively possible implementation, this passes through the first application service according to first application identities applied
Before device sends logging request to the terminal for logging in first account, the device further include:
When in account library include first account, and in voice signal library exist and first voice signal matched second
When voice signal, execute this according to this first application application identities, by the first application server to log in first account
Terminal the step of sending logging request, store at least one account being arranged in the account library, deposited in the voice signal library
Store up at least one second voice signal being arranged.
In alternatively possible implementation, the device further include:
Module is obtained, for obtaining the first voice signal mark and the second voice signal mark, the first voice signal mark
Know for the mark of the voice signal of first account is arranged, which is identified as matched with first voice signal
The mark of second voice signal;
The sending module 904 is also used to when first voice signal identifies and second voice signal mark is identical, root
According to the application identities of first application, logging request is sent to the terminal for logging in first account by the first application server.
In alternatively possible implementation, the device further include:
The acquisition module 901 is also used to acquire the second voice signal for being entered, which is converted to the
Two text informations;
The identification module 902 is also used to identify that second user is intended to from second text information;
The determining module 903 is also used to determine account setting meaning when the second user is intended to account setting intention
Scheme corresponding second account to be placed;
Memory module, for arriving second account storage into the account library, and by the second voice signal storage
In the voice signal library.
In alternatively possible implementation, the device further include:
The sending module 904 is also used to when the playback equipment is non-laissezpasser equipment, alternatively, when acquiring first language
When time difference between the time of sound signal and last login is greater than preset time difference threshold value, alternatively, when second application is
It is specified in application, according to the application identities of first application, by the first application server to the terminal for logging in first account
Send logging request.
In the embodiments of the present disclosure, playback equipment acquires the first voice signal being entered, and the first voice signal is converted
For the first text information;Identify that the first user is intended to the application identities with the first application from the first text information;When the first use
When family is intended to account login intention, determines and apply the first account to be logged in first party;According to the application mark of the first application
Know, logging request is sent to the terminal for logging in the first account by the first application server;It is taken when receiving by the first application
When the confirmation response for the terminal that business device returns, passes through the first account logs in currently second and apply.When user's control playback equipment
When login, user triggers playback equipment directly by inputting the first voice signal into playback equipment, by the first voice signal
Register is carried out, playback equipment identifies that the first user of the first voice signal is intended to, and is intended to when the first user is intended to log in
When, subsequent login operation is carried out, user directly inputs the i.e. triggerable playback equipment of the first voice signal and logs in during being somebody's turn to do
Operation, is not needed user and is scanned the two-dimensional code using mobile phone, improve login efficiency.
It should be understood that entering device provided by the above embodiment log in when, only with above-mentioned each functional module draw
Divide and be illustrated, in practical application, can according to need and be completed by different functional modules above-mentioned function distribution, i.e.,
The internal structure of device is divided into different functional modules, to complete all or part of the functions described above.On in addition,
The entering device and login method embodiment for stating embodiment offer belong to same design, and specific implementation process is detailed in method implementation
Example, which is not described herein again.
Figure 10 shows the structural block diagram of the playback equipment 1000 of one exemplary embodiment of disclosure offer.The broadcasting is set
Standby 1000 may is that television set, laptop or desktop computer.In general, playback equipment 1000 includes: 1001 He of processor
Memory 1002.
Processor 1001 may include one or more processing cores, such as 4 core processors, 8 core processors etc..Place
Reason device 1001 can use DSP (Digital Signal Processing, Digital Signal Processing), FPGA (Field-
Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array, may be programmed
Logic array) at least one of example, in hardware realize.Processor 1001 also may include primary processor and coprocessor, master
Processor is the processor for being handled data in the awake state, also referred to as CPU (Central Processing
Unit, central processing unit);Coprocessor is the low power processor for being handled data in the standby state.?
In some embodiments, processor 1001 can be integrated with GPU (Graphics Processing Unit, image processor),
GPU is used to be responsible for the rendering and drafting of content to be shown needed for display screen.In some embodiments, processor 1001 can also be wrapped
AI (Artificial Intelligence, artificial intelligence) processor is included, the AI processor is for handling related machine learning
Calculating operation.
Memory 1002 may include one or more computer readable storage mediums, which can
To be non-transient.Memory 1002 may also include high-speed random access memory and nonvolatile memory, such as one
Or multiple disk storage equipments, flash memory device.In some embodiments, the non-transient computer in memory 1002 can
Storage medium is read for storing at least one instruction, at least one instruction performed by processor 1001 for realizing this Shen
Please in login method embodiment provide method.
In some embodiments, playback equipment 1000 is also optional includes: peripheral device interface 1003 and at least one outside
Peripheral equipment.It can be connected by bus or signal wire between processor 1001, memory 1002 and peripheral device interface 1003.Respectively
A peripheral equipment can be connected by bus, signal wire or circuit board with peripheral device interface 1003.Specifically, peripheral equipment packet
It includes: radio circuit 1004, touch display screen 1005, camera 1006, voicefrequency circuit 1007, positioning component 1008 and power supply 1009
At least one of.
Peripheral device interface 1003 can be used for I/O (Input/Output, input/output) is relevant outside at least one
Peripheral equipment is connected to processor 1001 and memory 1002.In some embodiments, processor 1001, memory 1002 and periphery
Equipment interface 1003 is integrated on same chip or circuit board;In some other embodiments, processor 1001, memory
1002 and peripheral device interface 1003 in any one or two can be realized on individual chip or circuit board, this implementation
Example is not limited this.
Radio circuit 1004 is for receiving and emitting RF (Radio Frequency, radio frequency) signal, also referred to as electromagnetic signal.
Radio circuit 1004 is communicated by electromagnetic signal with communication network and other communication equipments.Radio circuit 1004 is by telecommunications
Number being converted to electromagnetic signal is sent, alternatively, the electromagnetic signal received is converted to electric signal.Optionally, radio circuit
1004 include: antenna system, RF transceiver, one or more amplifiers, tuner, oscillator, digital signal processor, volume solution
Code chipset, first user identity module card etc..Radio circuit 1004 can by least one wireless communication protocol come with
Other playback equipments are communicated.The wireless communication protocol includes but is not limited to: Metropolitan Area Network (MAN), each third generation mobile communication network (2G,
3G, 4G and 5G), WLAN and/or WiFi (Wireless Fidelity, Wireless Fidelity) network.In some embodiments
In, radio circuit 1004 can also include NFC (Near Field Communication, wireless near field communication) related electricity
Road, the application are not limited this.
Display screen 1005 is for showing UI (User Interface, the first user interface).The UI may include figure, text
Sheet, icon, video and its their any combination.When display screen 1005 is touch display screen, display screen 1005, which also has, to be adopted
Collect the ability in the touch signal on the surface or surface of display screen 1005.The touch signal can be used as control signal input
It is handled to processor 1001.At this point, display screen 1005 can be also used for providing virtual push button and/or dummy keyboard, also referred to as
Soft button and/or soft keyboard.In some embodiments, display screen 1005 can be one, be arranged before playback equipment 1000
Plate;In further embodiments, display screen 1005 can be at least two, be separately positioned on the different surfaces of playback equipment 1000
It or is in foldover design;In still other embodiments, display screen 1005 can be flexible display screen, and playback equipment 1000 is arranged in
On curved surface or on fold plane.Even, display screen 1005 can also be arranged to non-rectangle irregular figure, namely abnormity
Screen.Display screen 1005 can use LCD (Liquid Crystal Display, liquid crystal display), OLED (Organic
Light-Emitting Diode, Organic Light Emitting Diode) etc. materials preparation.
CCD camera assembly 1006 is for acquiring image or video.Optionally, CCD camera assembly 1006 includes front camera
And rear camera.In general, the front panel of playback equipment is arranged in front camera, playback equipment is arranged in rear camera
The back side.In some embodiments, rear camera at least two are main camera, depth of field camera, wide-angle imaging respectively
Head, any one in focal length camera, to realize that main camera and the fusion of depth of field camera realize that background blurring function, master are taken the photograph
As head and wide-angle camera fusion realize pan-shot and VR (Virtual Reality, virtual reality) shooting function or
Other fusion shooting functions.In some embodiments, CCD camera assembly 1006 can also include flash lamp.Flash lamp can be list
Colour temperature flash lamp is also possible to double-colored temperature flash lamp.Double-colored temperature flash lamp refers to the combination of warm light flash lamp and cold light flash lamp,
It can be used for the light compensation under different-colour.
Voicefrequency circuit 1007 may include microphone and loudspeaker.Microphone is used to acquire the sound of the first user and environment
Wave, and convert sound waves into electric signal and be input to processor 1001 and handled, or be input to radio circuit 1004 to realize
Voice communication.For stereo acquisition or the purpose of noise reduction, microphone can be separately positioned on playback equipment 1000 to be multiple
Different parts.Microphone can also be array microphone or omnidirectional's acquisition type microphone.Loudspeaker is then used to that processor will to be come from
1001 or the electric signal of radio circuit 1004 be converted to sound wave.Loudspeaker can be traditional wafer speaker, be also possible to press
Electroceramics loudspeaker.When loudspeaker is piezoelectric ceramic loudspeaker, the audible sound of the mankind can be not only converted electrical signals to
Wave can also convert electrical signals to the sound wave that the mankind do not hear to carry out the purposes such as ranging.In some embodiments, audio-frequency electric
Road 1007 can also include earphone jack.
Positioning component 1008 is used for the current geographic position of positioning playing equipment 1000, to realize navigation or LBS
(Location Based Service, location based service).Positioning component 1008 can be the GPS based on the U.S.
The dipper system of (Global Positioning System, global positioning system), China, the Gray of Russia receive this system
Or the positioning component of the Galileo system of European Union.
Power supply 1009 is used to be powered for the various components in playback equipment 1000.Power supply 1009 can be alternating current,
Direct current, disposable battery or rechargeable battery.When power supply 1009 includes rechargeable battery, which can be supported
Wired charging or wireless charging.The rechargeable battery can be also used for supporting fast charge technology.
In some embodiments, playback equipment 1000 further includes having one or more sensors 1100.The one or more
Sensor 1100 includes but is not limited to: acceleration transducer 1101, gyro sensor 1102, pressure sensor 1103, fingerprint
Sensor 1104, optical sensor 1105 and proximity sensor 1106.
Acceleration transducer 1101 can detecte adding in three reference axis of the coordinate system established with playback equipment 1000
Velocity magnitude.For example, acceleration transducer 1101 can be used for detecting component of the acceleration of gravity in three reference axis.Processing
The acceleration of gravity signal that device 1001 can be acquired according to acceleration transducer 1101 controls touch display screen 1005 with lateral view
Figure or longitudinal view carry out the display of the first user interface.Acceleration transducer 1101 can be also used for game or the first user
Exercise data acquisition.
Gyro sensor 1102 can detecte body direction and the rotational angle of playback equipment 1000, gyro sensor
1102 can cooperate with the first user of acquisition to act the 3D of playback equipment 1000 with acceleration transducer 1101.Processor 1001
According to the data that gyro sensor 1102 acquires, following function may be implemented: action induction (such as the inclination according to the first user
Operate to change UI), shooting when image stabilization, game control and inertial navigation.
Pressure sensor 1103 can be set under the side frame of playback equipment 1000 and/or touch display screen 1005
Layer.When the side frame of playback equipment 1000 is arranged in pressure sensor 1103, the first user can detecte to playback equipment
1000 gripping signal, the gripping signal acquired by processor 1001 according to pressure sensor 1103 carry out right-hand man's identification or fast
Victory operation.When the lower layer of touch display screen 1005 is arranged in pressure sensor 1103, by processor 1001 according to the first user
To the pressure operation of touch display screen 1005, realization controls the operability control on the interface UI.Operability control
Including at least one of button control, scroll bar control, icon control, menu control.
Fingerprint sensor 1104 is used to acquire the fingerprint of the first user, is adopted by processor 1001 according to fingerprint sensor 1104
The identity of the first user of fingerprint recognition collected, alternatively, being used by fingerprint sensor 1104 according to collected fingerprint recognition first
The identity at family.When the identity for identifying the first user is trusted identity, first user is authorized to execute phase by processor 1001
The sensitive operation of pass, the sensitive operation include solving lock screen, checking encryption information, downloading software, payment and change setting etc..Refer to
The front, the back side or side of playback equipment 1000 can be set in line sensor 1104.When being provided with object on playback equipment 1000
When managing key or manufacturer Logo, fingerprint sensor 1104 can be integrated with physical button or manufacturer Logo.
Optical sensor 1105 is for acquiring ambient light intensity.In one embodiment, processor 1001 can be according to light
The ambient light intensity that sensor 1105 acquires is learned, the display brightness of touch display screen 1005 is controlled.Specifically, work as ambient light intensity
When higher, the display brightness of touch display screen 1005 is turned up;When ambient light intensity is lower, the aobvious of touch display screen 1005 is turned down
Show brightness.In another embodiment, the ambient light intensity that processor 1001 can also be acquired according to optical sensor 1105, is moved
The acquisition parameters of state adjustment CCD camera assembly 1006.
Proximity sensor 1106, also referred to as range sensor are generally arranged at the front panel of playback equipment 1000.Close to sensing
Device 1106 is used to acquire the distance between the front of the first user Yu playback equipment 1000.In one embodiment, it is passed when close
When sensor 1106 detects that the distance between the front of the first user and playback equipment 1000 gradually becomes smaller, controlled by processor 1001
Touch display screen 1005 processed is switched to breath screen state from bright screen state;When proximity sensor 1106 detects the first user and plays
When the distance between the front of equipment 1000 becomes larger, touch display screen 1005 is controlled by processor 1001 and is cut from breath screen state
It is changed to bright screen state.
It will be understood by those skilled in the art that structure shown in Figure 10 does not constitute the restriction to playback equipment 1000,
It may include perhaps combining certain components than illustrating more or fewer components or being arranged using different components.
The embodiment of the present disclosure additionally provides a kind of computer readable storage medium, which is applied to
Terminal is stored at least one instruction, at least a Duan Chengxu, code set or instruction set in the computer readable storage medium, should
Instruction, the program, the code set or the instruction set are loaded by processor and executed to be played in the method to realize above-described embodiment
Operation performed by equipment.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely the preferred embodiments of the disclosure, not to limit the disclosure, all spirit in the disclosure and
Within principle, any modification, equivalent replacement, improvement and so on be should be included within the protection scope of the disclosure.
Claims (15)
1. a kind of login method, which is characterized in that the method is applied in playback equipment, which comprises
The first voice signal being entered is acquired, first voice signal is converted into the first text information;
Identify that the first user is intended to the application identities with the first application from first text information;
When first user, which is intended to account, logs in intention, determines and apply the first account to be logged in the first party;
According to the application identities of first application, sent by the first application server to the terminal for logging in first account
Logging request;
When receiving the confirmation response of the terminal returned by first application server, pass through first account
Log in the second current application.
2. the method according to claim 1, wherein described identify the first user from first text information
It is intended to the application identities with the first application, comprising:
Word segmentation processing is carried out to first text information, obtains sequence of terms, includes multiple words in the sequence of terms;
Digital vectors processing is carried out to the sequence of terms, obtains term vector sequence, includes multiple in the term vector sequence
The corresponding term vector of word;
First user in the term vector sequence inputting disaggregated model, will be obtained to be intended to mark with the application of first application
Know.
3. according to the method described in claim 2, it is characterized in that, described by the term vector sequence inputting disaggregated model,
It obtains first user and is intended to the application identities applied with described first, comprising:
The term vector sequence is sequentially input in the first sorter network of disaggregated model by positive sequence, obtains the first classification knot
Fruit;
The term vector sequence is sequentially input in reverse order in the second sorter network of the disaggregated model, the second classification is obtained
As a result;
First classification results and second classification results are integrated, the classification knot of first voice signal is obtained
Fruit includes that first user is intended to and the application identities of first application in the classification results.
4. the method according to claim 1, wherein the determination applies to be logged in first in the first party
Account, comprising:
According to the application identities of first application, the account rule of first application is determined, it is regular according to the account, from
First account is identified in first text information;Alternatively,
Communicating number is identified from first text information, according to the application identities of first application, is obtained described the
One application in associated first account of the communicating number;Alternatively,
The first vocal print feature for extracting first voice signal is selected from vocal print feature library according to first vocal print feature
It selects with the matched vocal print feature of the first vocal print feature, associated first account of vocal print feature for obtaining and selecting, the sound
At least one vocal print feature being arranged is stored in line feature database.
5. method according to claim 1-4, which is characterized in that the application according to first application is marked
Know, before sending logging request to the terminal for logging in first account by the first application server, the method also includes:
When in account library include first account, and in voice signal library exist and first voice signal matched second
When voice signal, the application identities according to first application are executed, by the first application server to logging in described the
The terminal of one account sends the step of logging request, stores at least one account being arranged, the voice in the account library
At least one second voice signal being arranged is stored in signal library.
6. according to the method described in claim 5, it is characterized in that, the application identities according to first application, pass through
Before first application server sends logging request to the terminal for logging in first account, the method also includes:
The first voice signal mark and the second voice signal mark are obtained, first voice signal is identified as setting described first
The mark of the voice signal of account, second voice signal is identified as to be believed with matched second voice of first voice signal
Number mark;
When first voice signal mark is identical with the second voice signal mark, execution is described to answer according to described first
Application identities, the step of logging request is sent to the terminal for logging in first account by the first application server.
7. according to the method described in claim 5, it is characterized in that, it is described acquire the first voice signal for being entered before, institute
State method further include:
The second voice signal being entered is acquired, second voice signal is converted into the second text information;
Identify that second user is intended to from second text information;
When the second user, which is intended to account setting, to be intended to, determine that account setting is intended to corresponding to be placed second
Account;
Second account storage is stored into the account library, and by second voice signal to the voice signal
In library.
8. method according to claim 1-4, which is characterized in that the application according to first application is marked
Know, before sending logging request to the terminal for logging in first account by the first application server, the method also includes:
When the playback equipment is non-laissezpasser equipment, alternatively, when the time and last time that acquire first voice signal
When time difference between login is greater than preset time difference threshold value, alternatively, when second application is specified in application, described in execution
According to the application identities of first application, is sent and logged in the terminal for logging in first account by the first application server
The step of request.
9. a kind of entering device, which is characterized in that described device is applied in playback equipment, and described device includes:
First voice signal is converted to the first text envelope for acquiring the first voice signal being entered by acquisition module
Breath;
Identification module, for identifying that the first user is intended to the application identities with the first application from first text information;
Determining module, for determining and applying in the first party wait step on when first user is intended to account login intention
First account of record;
Sending module, for according to it is described first application application identities, by the first application server to log in described first
The terminal of account sends logging request;
Login module, for leading to when receiving the confirmation response of the terminal returned by first application server
It crosses first account and logs in the second current application.
10. device according to claim 9, which is characterized in that the identification module is also used to first text envelope
Breath carries out word segmentation processing, obtains sequence of terms, includes multiple words in the sequence of terms;Number is carried out to the sequence of terms
Vectorization processing obtains term vector sequence, includes the corresponding term vector of multiple words in the term vector sequence;By institute's predicate to
It measures in sequence inputting disaggregated model, obtains first user and be intended to the application identities applied with described first.
11. device according to claim 10, which is characterized in that the identification module is also used to the term vector sequence
Column are sequentially input in the first sorter network of disaggregated model by positive sequence, obtain the first classification results;By the term vector sequence
It is sequentially input in the second sorter network of the disaggregated model in reverse order, obtains the second classification results;Described first is classified
As a result it is integrated with second classification results, obtains the classification results of first voice signal, in the classification results
It is intended to the application identities with first application including first user.
12. according to the described in any item devices of claim 9-11, which is characterized in that the application according to first application
Mark, before sending logging request to the terminal for logging in first account by the first application server, described device is also wrapped
It includes:
When in account library include first account, and in voice signal library exist and first voice signal matched second
When voice signal, the application identities according to first application are executed, by the first application server to logging in described the
The terminal of one account sends the step of logging request, stores at least one account being arranged, the voice in the account library
At least one second voice signal being arranged is stored in signal library.
13. device according to claim 12, which is characterized in that described device further include:
The acquisition module is also used to acquire the second voice signal being entered, second voice signal is converted to second
Text information;
The identification module is also used to identify that second user is intended to from second text information;
The determining module is also used to determine the account setting meaning when the second user is intended to account setting intention
Scheme corresponding second account to be placed;
Memory module, for storing second account storage into the account library, and by second voice signal
Into the voice signal library.
14. a kind of playback equipment, which is characterized in that the playback equipment includes processor and memory, is deposited in the memory
Contain at least one instruction, at least a Duan Chengxu, code set or instruction set, described instruction, described program, the code set or institute
Instruction set is stated to be loaded as the processor and executed to realize institute in the method as described in claim 1 to 8 any claim
The operation of execution.
15. a kind of computer readable storage medium, which is characterized in that be stored at least one in the computer readable storage medium
Item instruction, at least a Duan Chengxu, code set or instruction set, described instruction, described program, the code set or described instruction collection by
Processor is loaded and is executed to realize operation performed in the method as described in claim 1 to 8 any claim.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910384945.0A CN110164450B (en) | 2019-05-09 | 2019-05-09 | Login method, login device, playing equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910384945.0A CN110164450B (en) | 2019-05-09 | 2019-05-09 | Login method, login device, playing equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110164450A true CN110164450A (en) | 2019-08-23 |
CN110164450B CN110164450B (en) | 2023-11-28 |
Family
ID=67633866
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910384945.0A Active CN110164450B (en) | 2019-05-09 | 2019-05-09 | Login method, login device, playing equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110164450B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104092542A (en) * | 2013-09-11 | 2014-10-08 | 腾讯科技(深圳)有限公司 | Account login method, device and system |
CN105141619A (en) * | 2015-09-15 | 2015-12-09 | 北京云知声信息技术有限公司 | Account login method and device |
CN105681162A (en) * | 2015-11-09 | 2016-06-15 | 乐视致新电子科技(天津)有限公司 | Method, device and system for synchronizing information |
CN105897686A (en) * | 2015-12-21 | 2016-08-24 | 乐视致新电子科技(天津)有限公司 | Smart television user account speech management method and smart television |
CN106130881A (en) * | 2016-07-07 | 2016-11-16 | 腾讯科技(深圳)有限公司 | A kind of account number login method and device |
CN106375336A (en) * | 2016-09-28 | 2017-02-01 | 北京金山安全软件有限公司 | Login information storage and providing method and device |
CN107395352A (en) * | 2016-05-16 | 2017-11-24 | 腾讯科技(深圳)有限公司 | Personal identification method and device based on vocal print |
CN107403619A (en) * | 2017-06-30 | 2017-11-28 | 武汉泰迪智慧科技有限公司 | A kind of sound control method and system applied to bicycle environment |
CN108040032A (en) * | 2017-11-02 | 2018-05-15 | 阿里巴巴集团控股有限公司 | A kind of voiceprint authentication method, account register method and device |
US10013984B1 (en) * | 2014-09-19 | 2018-07-03 | United Services Automobile Association (Usaa) | Systems and methods for authentication program enrollment |
CN108804411A (en) * | 2018-04-09 | 2018-11-13 | 平安科技(深圳)有限公司 | A kind of semantic role analysis method, computer readable storage medium and terminal device |
CN109360557A (en) * | 2018-10-10 | 2019-02-19 | 腾讯科技(北京)有限公司 | The method, apparatus and computer equipment of voice control application program |
-
2019
- 2019-05-09 CN CN201910384945.0A patent/CN110164450B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104092542A (en) * | 2013-09-11 | 2014-10-08 | 腾讯科技(深圳)有限公司 | Account login method, device and system |
US10013984B1 (en) * | 2014-09-19 | 2018-07-03 | United Services Automobile Association (Usaa) | Systems and methods for authentication program enrollment |
CN105141619A (en) * | 2015-09-15 | 2015-12-09 | 北京云知声信息技术有限公司 | Account login method and device |
CN105681162A (en) * | 2015-11-09 | 2016-06-15 | 乐视致新电子科技(天津)有限公司 | Method, device and system for synchronizing information |
CN105897686A (en) * | 2015-12-21 | 2016-08-24 | 乐视致新电子科技(天津)有限公司 | Smart television user account speech management method and smart television |
CN107395352A (en) * | 2016-05-16 | 2017-11-24 | 腾讯科技(深圳)有限公司 | Personal identification method and device based on vocal print |
CN106130881A (en) * | 2016-07-07 | 2016-11-16 | 腾讯科技(深圳)有限公司 | A kind of account number login method and device |
CN106375336A (en) * | 2016-09-28 | 2017-02-01 | 北京金山安全软件有限公司 | Login information storage and providing method and device |
CN107403619A (en) * | 2017-06-30 | 2017-11-28 | 武汉泰迪智慧科技有限公司 | A kind of sound control method and system applied to bicycle environment |
CN108040032A (en) * | 2017-11-02 | 2018-05-15 | 阿里巴巴集团控股有限公司 | A kind of voiceprint authentication method, account register method and device |
CN108804411A (en) * | 2018-04-09 | 2018-11-13 | 平安科技(深圳)有限公司 | A kind of semantic role analysis method, computer readable storage medium and terminal device |
CN109360557A (en) * | 2018-10-10 | 2019-02-19 | 腾讯科技(北京)有限公司 | The method, apparatus and computer equipment of voice control application program |
Also Published As
Publication number | Publication date |
---|---|
CN110164450B (en) | 2023-11-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109905318A (en) | Apparatus control method, device and storage medium | |
CN111739517B (en) | Speech recognition method, device, computer equipment and medium | |
WO2022057435A1 (en) | Search-based question answering method, and storage medium | |
CN108806670B (en) | Audio recognition method, device and storage medium | |
CN110059652A (en) | Face image processing process, device and storage medium | |
CN107959893A (en) | The method and apparatus for showing account head portrait | |
CN109711832A (en) | The methods, devices and systems paid | |
CN110533585A (en) | A kind of method, apparatus that image is changed face, system, equipment and storage medium | |
CN108320756A (en) | It is a kind of detection audio whether be absolute music audio method and apparatus | |
CN110109608A (en) | Text display method, device, terminal and storage medium | |
CN111062248A (en) | Image detection method, device, electronic equipment and medium | |
CN110099360A (en) | Voice message processing method and device | |
CN111582862A (en) | Information processing method, device, system, computer device and storage medium | |
CN109961802A (en) | Sound quality comparative approach, device, electronic equipment and storage medium | |
CN112215598A (en) | Voice payment method and electronic equipment | |
CN113518261B (en) | Guiding video playing method, guiding video playing device, computer equipment and storage medium | |
CN106980836A (en) | Auth method and device | |
CN109218169A (en) | Instant communication method, device and storage medium | |
CN109085991A (en) | Application control method and device, terminal, storage medium | |
CN109544117A (en) | Meeting room information display method, device, terminal, server and storage medium | |
CN109614212A (en) | Using starting method, apparatus, terminal and storage medium | |
CN108922533A (en) | Determine whether the method and apparatus sung in the real sense | |
CN111341317B (en) | Method, device, electronic equipment and medium for evaluating wake-up audio data | |
CN110166275A (en) | Information processing method, device and storage medium | |
CN110097368A (en) | Recognition methods, server, terminal and the service equipment of facial image |
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 |