CN109753778A - Checking method, device, equipment and the storage medium of user - Google Patents
Checking method, device, equipment and the storage medium of user Download PDFInfo
- Publication number
- CN109753778A CN109753778A CN201811648912.4A CN201811648912A CN109753778A CN 109753778 A CN109753778 A CN 109753778A CN 201811648912 A CN201811648912 A CN 201811648912A CN 109753778 A CN109753778 A CN 109753778A
- Authority
- CN
- China
- Prior art keywords
- vocal print
- encoded radio
- prestored
- user
- print encoded
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the checking method of user a kind of, device, equipment and storage mediums, firstly, then identifying the corresponding vocal print encoded radio of audio by obtaining pending user identifier and corresponding audio；If vocal print encoded radio is greater than similarity threshold with the vocal print encoded radio similarity prestored, and pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that pending user is exception object.The present embodiment carries out the audit of user using everyone sound wave feature with uniqueness, can recognize specific user, solve the problems, such as multi-user's malicious registration, improve the safety of transaction platform.
Description
Technical field
The present embodiments relate to information technology field more particularly to a kind of checking method of user, device, equipment and deposit
Storage media.
Background technique
With the development of science and technology the development of internet and mobile Internet, current various traditional transaction all start in net
It is realized on network platform.It such as calls a taxi, eat, the dealing of second-hand article.Since the threshold of some transaction platforms is lower, in order to attract use
The phenomenon that family and registration amount, universal early period, audit was looser, caused a large amount of identity registrations multiple platform users, although this measure
More economic interests are brought for registration user, but inconvenience are caused to the management of platform, and keep transaction risk bigger.
For specification platform management and Transaction Safety, each platform has generally all formulated risk recognition system, will malice
Blacklist is added in the user of registration.Existing risk recognition system is to identify adventure account according to user data, can not be recognized
Specific risk natural person.And existing risk recognition system is easy to be felt out risk control rule by black industry, gives platform
Bring loss.
Summary of the invention
The present invention provide it is a kind of come user checking method, device, equipment and storage medium, to realize according to the sound of user
Frequency recognizes specific user (natural person), improves the safety of transaction platform.
In a first aspect, the embodiment of the invention provides the checking methods of user a kind of, comprising:
Obtain pending user identifier and corresponding audio；
Identify the corresponding vocal print encoded radio of the audio；
If the vocal print encoded radio is greater than similarity threshold with the vocal print encoded radio similarity prestored, and described pending
User identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that the pending user is exception object.
Further, the corresponding vocal print encoded radio of the identification audio, comprising:
The corresponding vocal print feature vector of the audio is identified by Application on Voiceprint Recognition model；
Corresponding vocal print encoded radio is generated according to the vocal print feature vector.
Further, before the corresponding sound characteristic vector by the Application on Voiceprint Recognition model identification audio,
Further include:
If the data format of the audio and preset data form be not identical, by the Data Format Transform of the audio
For preset data form, wherein the preset data form is corresponding with the Application on Voiceprint Recognition model.
Further, the vocal print encoded radio prestored is stored in vocal print code database with corresponding mark.
It further, will if the vocal print encoded radio is less than similarity threshold with the vocal print encoded radio similarity prestored
The vocal print code database is added in the vocal print encoded radio and pending user identifier.
Further, if the vocal print encoded radio is greater than similarity threshold with the vocal print encoded radio similarity prestored, and
Pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that the pending user is abnormal
Object, comprising:
If the vocal print encoded radio and the vocal print encoded radio similarity prestored are greater than similarity threshold, and the sound
Line encoded radio is in vocal print black list database, it is determined that the pending user is risk subjects；
If the vocal print encoded radio is greater than similarity threshold with the vocal print encoded radio similarity prestored, and the vocal print is compiled
Code value then judges pending user identifier mark corresponding with the vocal print encoded radio prestored not in vocal print black list database
Whether identical know；
If pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that described pending
Core user is exception object.
Further, the determination pending user is after exception object, further includes:
It polymerize the vocal print encoded radio and the vocal print encoded radio prestored；
By after polymerization vocal print encoded radio, the pending user identifier and the vocal print encoded radio prestored it is corresponding
Mark is associated, and is stored to vocal print code database.
Second aspect, the embodiment of the invention also provides the audit devices of user a kind of, comprising:
Module is obtained, for obtaining pending user identifier and corresponding audio；
Identification module, for identification corresponding vocal print encoded radio of the audio；
Determining module, if being greater than similarity threshold with the vocal print encoded radio similarity prestored for the vocal print encoded radio
Value, and pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that the pending user
For exception object.
Further, identification module includes:
Recognition unit, for identifying the corresponding vocal print feature vector of the audio by Application on Voiceprint Recognition model；
Generation unit, for generating corresponding vocal print encoded radio according to the vocal print feature vector.
Further, further includes:
Audio format conversion module will if the data format and preset data form for the audio be not identical
The Data Format Transform of the audio is preset data form, wherein the preset data form and the Application on Voiceprint Recognition model pair
It answers.
Further, the vocal print encoded radio prestored is stored in vocal print code database with corresponding mark.
Further, described device further include:
Memory module, if being less than similarity threshold with the vocal print encoded radio similarity prestored for the vocal print encoded radio
Value, the vocal print encoded radio and pending user identifier are stored to the vocal print code database.
Further, determining module includes:
First determination unit, if being greater than phase for the vocal print encoded radio and the vocal print encoded radio similarity prestored
Like degree threshold value, and the vocal print encoded radio is in vocal print black list database, it is determined that the pending user is risk subjects；
Judging unit, if being greater than similarity threshold with the vocal print encoded radio similarity prestored for the vocal print encoded radio
Value, and the vocal print encoded radio is in vocal print black list database then judges the pending user identifier and the sound that prestores
Line encoded radio is corresponding identify whether it is identical；
Second determination unit, if not for pending user identifier mark corresponding with the vocal print encoded radio prestored
Together, it is determined that the pending user is exception object.
Further, described device further include:
Aggregation module, for polymerizeing the vocal print encoded radio and the vocal print encoded radio prestored；
Relating module, for by polymerization after vocal print encoded radio, the pending user identifier and the sound prestored
The corresponding user identifier of line encoded radio is associated, and is stored to vocal print code database.
The third aspect, the embodiment of the invention also provides a kind of equipment, the equipment includes:
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the checking method of the user as described in any in above-mentioned first aspect.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the checking method of the user as described in any in above-mentioned first aspect when the program is executed by processing unit.
Checking method, device, equipment and the storage medium of a kind of user provided by the above embodiment, firstly, passing through acquisition
Then pending user identifier and corresponding audio identify the corresponding vocal print encoded radio of audio；If vocal print encoded radio with prestore
Vocal print encoded radio similarity be greater than similarity threshold, and pending user identifier mark corresponding with the vocal print encoded radio prestored
It is different, it is determined that pending user is exception object.The present embodiment is used using everyone sound wave feature with uniqueness
The audit at family can recognize specific user (natural person), solve the problems, such as multi-user's malicious registration, improve transaction platform
Safety.
Detailed description of the invention
Fig. 1 is the flow chart of the checking method for the user that the embodiment of the present invention one provides；
Fig. 2 is the structural schematic diagram for the risk control system that the embodiment of the present invention one provides；
Fig. 3 is the flow chart of the checking method of user provided by Embodiment 2 of the present invention；
Fig. 4 is the flow chart of the checking method for the user that the embodiment of the present invention three provides；
Fig. 5 is the interaction diagrams of the platform that the embodiment of the present invention four provides and risk control system；
Fig. 6 is the structural schematic diagram of the audit device for the user that the embodiment of the present invention five provides；
Fig. 7 is a kind of structural schematic diagram for equipment that the embodiment of the present invention six provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow chart of the checking method for the user that the embodiment of the present invention one provides, and the present embodiment is applicable to audit
The checking method of the case where user of transaction platform, user provided in this embodiment can be executed by the audit device of user,
The audit device of the user can realize by way of software and/or hardware, the audit device of the user can be two or
Multiple physical entities are constituted, and are also possible to a physical entity and are constituted, and are typically integrated in server apparatus.It needs to illustrate
It is that the checking method of user provided by the present embodiment is specifically held by establishing the equipment of communication connection relationship with each platform
Row, and be believed that and specifically executed by integrating the audit device of user on the device.
It should be noted that the audit device of user provided in this embodiment is integrated in risk control system.Risk control
System refers to that manager adopts various measures and reduces a possibility that risk case occurs, or possible loss is controlled certain
In range, to avoid the burdensome loss of bring when risk case occurs.The audit side of user provided in this embodiment
Method is only a portion content in risk control system.
Specifically, as shown in Figure 1, the checking method of user provided in this embodiment mainly includes the following steps:
S110, pending user identifier and corresponding audio are obtained.
It should be noted that user is frequently necessary to phone contact in platform process of exchange, but platform is in order to guarantee user
Dependence of the safety and user of information to platform, both sides not can know that the true identity of other side.Many malice are caused to be infused
The user of volume, i.e. a user (natural person) register multiple accounts in a short time, bring risk to transaction platform.
In the present embodiment, pending user refers to that needs trade in platform or carry out relevant activity in platform
And log in the user of platform.Further, pending user is determined by platform, such as: each can be logged in into the platform
User is determined as pending user.For another example: preset quantity can be spaced or preset time obtains a user, be determined as pending
Core user.Preset quantity and preset time can be set by platform according to the number of users of platform.Illustratively, can between
A user is obtained every 10 users, the user that will acquire is determined as pending user.It can also be spaced 10 seconds and obtain one
A user is determined as pending user.The method for only obtaining pending user to platform in the present embodiment is illustrated, rather than is limited
Fixed, platform can design other methods for determining pending user according to the actual situation.
Further, pending user identifier refers to the register name, phone number, note that can uniquely indicate user identity
Volume identity (Identification, ID) number or other certificates etc..Corresponding audio refers to sound when user logs in platform
The audio-frequency information of frequency verifying input, such as: when user logs in platform validation, needs user to read some according to the requirement of platform and consolidate
Determine content, immobilized substance is provided by platform, can be a word, a word or a word.It is also possible to user flat
When carrying out correlated activation on platform, the audio-frequency information of typing.Such as: user is during replying or issuing some model, hair
The audio content of cloth.Alternatively, user in platform process of exchange, carries out telephonic communication, the telephonograph of the user of platform interception
Audio etc..It should be noted that only corresponding audio is illustrated in the present embodiment, and it is non-limiting, platform can be according to reality
The other methods for obtaining corresponding audio of border situation design.
Obtain pending user identifier and corresponding audio that platform determines.Fig. 2 is the wind that the embodiment of the present invention one provides
The structural schematic diagram of dangerous control system.As shown in Fig. 2, a risk system 201 can establish communication link with multiple platforms 202
It connects, i.e. the pending user that the available multiple platforms 202 of a risk system 201 provide.In this way, risk control system 201
The black list user that the malicious registration user of multiple platforms or platform set can be polymerize, so that platform is available
Pending user whether be other platforms black list user so that platform can to black list user carry out emphasis at
Reason prevents the loss of black list user's bring in advance, improves the safety of platform.
Further, in the present embodiment, pending user identifier and corresponding audio are obtained, can be platform will be pending
Core user identifier and corresponding audio are sent to third method, memory device, and platform is by pending user identifier and corresponding audio
Storage address is sent to risk control system, and risk control system obtains pending user identifier and corresponding by storage address
Audio.Such as: third method, memory device can be internet, correspondingly, storage address is uniform resource locator.That is, platform
Pending user identifier and corresponding audio are uploaded to internet, risk control system passes through uniform resource locator from interconnection
Pending user identifier and corresponding audio are downloaded on the net.Third method, memory device is also possible to server or computer equipment
Storage device.It should be noted that the present embodiment is only illustrated third method, memory device, and non-limiting, according to can be with
Actual conditions choose suitable third method, memory device.
Further, pending user identifier and corresponding audio are obtained, is also possible to risk control system directly from flat
Platform obtains pending user identifier and corresponding audio.
S120, the corresponding vocal print encoded radio of identification audio.
In the present embodiment, the vocal print is the sound wave spectrum for the carrying verbal information that electricity consumption acoustic instrument is shown.The mankind
The generation of language is a complicated physiology physical process between Body Languages maincenter and vocal organs, what people used in speech
Phonatory organ --- tongue, tooth, larynx, lung, nasal cavity everyone widely different in terms of size and form, so any two
The voiceprint map of natural person is all variant.Vocal print encoded radio refers to the unique encodings of the characterization voiceprint map gone out according to audio identification
Value.
In the present embodiment, the corresponding vocal print encoded radio of audio is identified according to the Application on Voiceprint Recognition model pre-established.Into
One step, Application on Voiceprint Recognition model can be the identification model that can recognize that vocal print feature vector.It can be by gathered in advance
A large amount of telephonographs or speech audio training come the Application on Voiceprint Recognition model that is pre-established, also can be used it is existing
Trained Application on Voiceprint Recognition model is carried out according to self-demand into being adjusted and improve the Application on Voiceprint Recognition mould pre-established
Type.Only the method for building up of Application on Voiceprint Recognition model is illustrated in the present embodiment, and it is non-limiting, it can be according to actual use situation
Establish suitable Application on Voiceprint Recognition model.
It should be noted that can regularly detect Application on Voiceprint Recognition model in the use process of risk control system
Recognition capability can be used audio and Application on Voiceprint Recognition model revised and adjusted if there are deviations for it, allow to meet more
Multi-platform demand.
Further, in the present embodiment, Application on Voiceprint Recognition model can be Direct Recognition and go out audio corresponding vocal print coding
The identification model of value is also possible to identify the corresponding vocal print feature vector of audio, calculates vocal print according to vocal print feature vector and compiles
Code value.
Vocal print feature vector refers to one group of one-dimensional or multidimensional the sound characteristic vector that can uniquely characterize diaphone frequency.
Vocal print encoded radio is generation one 64 string values according to sound characteristic vector.Vocal print encoded radio can use simplicity
Mode indicates corresponding audio, simplifies subsequent treatment process, more easy compared with vocal print feature vector, can be improved
The calculating speed of subsequent treatment process.
If S130, vocal print encoded radio are greater than similarity threshold, and pending use with the vocal print encoded radio similarity prestored
It is different that family identifies mark corresponding from the vocal print encoded radio prestored, it is determined that pending user is exception object.
In the present embodiment, the vocal print encoded radio prestored is stored in vocal print code database.It should be noted that one
Natural person may use 2 or 3 phone number registration accounts, therefore, the sound that each of vocal print code database prestores
Line encoded radio can correspond at least one user identifier prestored.
Whether it is a natural person that similarity threshold is by two vocal print encoded radios of a measurement of staff's setting
Numerical value.It should be noted that similarity threshold can be adjusted according to demand.In the present embodiment, similarity threshold is preferred
It is 0.95.In this way, the vocal print encoded radio that can permit a natural person in different times has differences, and such as: natural person is normal
When state and sick state, vocal print encoded radio may not be identical.The checking method of user provided in this embodiment allows in this way
The case where exist, the usage experience of user can be promoted.
After identifying vocal print encoded radio in S120, the vocal print all prestored in vocal print encoded radio and vocal print code database is calculated
Similarity between coding.In the present embodiment, similarity calculating method can use cosine similarity algorithm, can also use
Euclidean distance algorithm, the present embodiment are not defined the calculation method of similarity, can choose the calculating side of any similarity
Method.
Further, if vocal print encoded radio is greater than similarity threshold with the vocal print encoded radio similarity prestored, in sound
Vocal print encoded radio is inquired in line black list database, if vocal print encoded radio is in vocal print black list database, it is determined that pending
Core user is risk subjects.Further, storage is believed by user corresponding with vocal print encoded radio in vocal print black list database
Breath, user information include: the corresponding user identifier of vocal print encoded radio and the correlated activation information that user carries out in platform,
Such as: the model of publication, the message etc. of reply.
Further, by user information corresponding with vocal print encoded radio in vocal print black list database and risk class,
It is back to platform, user provides reference for platform processes.
If not inquiring vocal print encoded radio in vocal print black list database, judges pending user identifier and prestore
Vocal print encoded radio it is corresponding identify whether it is identical, if pending user identifier mark corresponding with the vocal print encoded radio prestored
It is not identical, it determines that pending user is exception object, and vocal print encoded radio and the vocal print encoded radio prestored are polymerize, polymerize
For a new vocal print encoded radio, by the mark of new vocal print encoded radio, pending user after polymerization and the vocal print prestored
The corresponding user identifier of encoded radio is associated, and is stored to vocal print code database.
If pending user identifier is identical as the corresponding mark of vocal print encoded radio prestored, determine that pending user is positive
Normal object, and be that normal information is back to platform by auditing result.
The checking method of a kind of user provided in this embodiment, firstly, by obtaining pending user identifier and corresponding
Then audio identifies the corresponding vocal print encoded radio of audio；If vocal print encoded radio is greater than with the vocal print encoded radio similarity prestored
Similarity threshold, and pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that pending user
For exception object.The present embodiment carries out the audit of user using everyone sound wave feature with uniqueness, can recognize tool
The user (natural person) of body, solves the problems, such as multi-user's malicious registration, improves the safety of transaction platform.
Embodiment two
On the basis of the above embodiments, the embodiment of the present invention has advanced optimized the checking method of user, and Fig. 3 is this hair
The flow chart of the checking method for the user that bright embodiment two provides.As shown in figure 3, the checking method of user provided in this embodiment
Mainly include the following steps:
S310, pending user identifier and corresponding audio are obtained.
S320, the corresponding vocal print encoded radio of identification audio.
S330, judge whether vocal print encoded radio and the vocal print encoded radio similarity prestored are greater than similarity threshold.
Similarity threshold is to measure whether two vocal print encoded radios are that a user is (natural by one of staff's setting
People) numerical value.It should be noted that similarity threshold can be adjusted according to demand.In the present embodiment, similarity threshold
Preferably 0.95.In this way, the vocal print encoded radio that can permit a user in different times has differences, and such as: user is normal
When state and sick state, vocal print encoded radio may not be identical.The checking method of user provided in this embodiment allows in this way
The case where exist, the usage experience of user can be promoted.In the present embodiment, the vocal print encoded radio prestored is stored in vocal print
In code database.
If vocal print encoded radio is less than similarity threshold with the vocal print encoded radio similarity prestored, S340 is executed, if
Vocal print encoded radio is greater than similarity threshold with the vocal print encoded radio similarity prestored, then executes S350.
Vocal print code database is added in S340, vocal print encoded radio and pending user identifier.
It should be noted that vocal print encoded radio is less than similarity threshold with the vocal print encoded radio similarity prestored, then illustrate
User's line encoded radio is not present in vocal print code database.Therefore, it is necessary to add the corresponding vocal print encoded radio of pending user
To vocal print code database.
S350, judge vocal print encoded radio whether in vocal print black list database.
Storage is by black list user's information corresponding with vocal print encoded radio, black list user in vocal print black list database
Information includes: the corresponding user identifier of vocal print encoded radio and the correlated activation information that user carries out in platform, such as: hair
The model of cloth, the message etc. of reply.Black list user's information can be provided by each platform, be also possible to risk control system and adopted
Collection.
If vocal print encoded radio executes S360 in vocal print black list database, if vocal print encoded radio is not in vocal print
In black list database, then S370 is executed.
S360, determine that pending user is risk subjects.
In the present embodiment, risk subjects refer to that the presence of user may make the other users on platform or platform
At the user of unnecessary damage.
It further, further, can also be according to vocal print black list database after risk system determines risk subjects
The information of the risk subjects of middle storage determines the risk class of pending user.Illustratively, risk class can be divided into 5
Grade.Such as: issuing illegal information can be risk class 5.Life attack or rubbish marketing can be risk class 1.It needs
It is noted that only risk class is illustrated in the present embodiment, and it is non-limiting.It can design and plan according to the actual situation
Risk class.
Further, by user information corresponding with vocal print encoded radio in vocal print black list database and risk class,
It is back to platform, user provides reference for platform processes.
S370, judge pending user identifier it is corresponding with the vocal print encoded radio prestored identify whether it is identical.
If vocal print encoded radio illustrates that pending user is not risk subjects not in vocal print black list database, pending
Core user is normal users, it is also necessary to further judgement.Judge that pending user identifier is encoded with the vocal print prestored
Be worth it is corresponding identify whether it is identical.
Judge pending user identifier it is corresponding with the vocal print encoded radio prestored identify whether it is identical, it is pending in order to determine
Whether user identifier and the vocal print encoded radio prestored are a user identifier, are a user (natural person) in order to determine
Have registered multiple accounts.Wherein, account and user identifier correspond.
Judge pending user identifier it is corresponding with the vocal print encoded radio prestored identify whether it is identical, if so then execute 380.
If it is not, then executing 390.
S380, determine that pending user is normal subjects.
If pending user identifier is identical as the corresponding mark of vocal print encoded radio prestored, determine that pending user is positive
Normal object, the i.e. corresponding user identifier of a user.It is that normal information is back to platform by auditing result.
S390, determine that pending user is exception object.
If pending user identifier mark corresponding with the vocal print encoded radio prestored is not identical, determine that pending user is
Exception object, and vocal print encoded radio and the vocal print encoded radio prestored are polymerize, it is polymerized to a new vocal print encoded radio, it will
The mark of new vocal print encoded radio, pending user after polymerization and the corresponding user identifier of the vocal print encoded radio prestored carry out
Association, and store to vocal print code database.
If pending user identifier is identical as the corresponding mark of vocal print encoded radio prestored, determine that pending user is positive
Normal object, and be that normal information is back to platform by auditing result.
The checking method of a kind of user provided in this embodiment, firstly, by obtaining pending user identifier and corresponding
Then audio identifies the corresponding vocal print encoded radio of audio；If vocal print encoded radio is greater than with the vocal print encoded radio similarity prestored
Similarity threshold, and pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that pending user
For exception object.The present embodiment carries out the audit of user using everyone sound wave feature with uniqueness, can recognize tool
The user (natural person) of body, solves the problems, such as multi-user's malicious registration, improves the safety of transaction platform.
Embodiment three
On the basis of the above embodiments, the embodiment of the present invention has advanced optimized the checking method of user, and Fig. 4 is this hair
The flow chart of the checking method for the user that bright embodiment two provides.As shown in figure 4, the checking method of user provided in this embodiment
Mainly include the following steps:
S401, pending user identifier and corresponding audio are obtained.
If the data format and preset data form of S402, audio be not identical, the data format of the audio is turned
It is changed to preset data form.
In the present embodiment, it is communicated to connect since a risk system can be established with multiple platforms, i.e. a risk system
The pending user that available multiple platforms of uniting provide.The audio data format that unused platform may provide is different,
Therefore, it is necessary to the audio of different data format is converted to preset data form.Wherein preset data form and Application on Voiceprint Recognition mould
Type is corresponding.I.e. preset data form is to meet the data format of Application on Voiceprint Recognition model needs.
Further, audio is cleared up, removes dirty data.The sound that Application on Voiceprint Recognition model can be made to identify in this way
Line feature vector is more accurate.
S403, the corresponding vocal print feature vector of audio is identified by Application on Voiceprint Recognition model.
Vocal print feature vector refers to one group of one-dimensional or multidimensional the sound characteristic vector that can uniquely characterize diaphone frequency.
Application on Voiceprint Recognition model can recognize that the corresponding vocal print feature vector of audio.
The Application on Voiceprint Recognition mould pre-established by a large amount of telephonographs gathered in advance or speech audio training
Type, telephonograph or speech audio can be provided by each platform, i.e., the telephonograph of the user of each platform registration, can also
To be that risk control system is acquired in other way.
It should be noted that can regularly detect Application on Voiceprint Recognition model in the use process of risk control system
Recognition capability, if that there are deviations is larger for its recognition effect, can be used a large amount of audio to Application on Voiceprint Recognition model carry out revision and
Adjustment, allows to meet the needs of more multi-platform.
S404, corresponding vocal print encoded radio is generated according to vocal print feature vector.
In the present embodiment, vocal print encoded radio is generation one 64 string values according to sound characteristic vector.Sound
Line encoded radio can indicate corresponding audio with easy mode, simplify subsequent treatment process, with vocal print feature vector phase
Than, it is more easy, the calculating speed in later period can be improved.
Corresponding vocal print encoded radio is generated according to preset calculation method according to vocal print feature vector.It further, can be with
It is that corresponding vocal print encoded radio is obtained by certain linear transformation according to vocal print feature vector.In the present embodiment not to generation
The method of corresponding vocal print encoded radio is defined, and can be designed according to the actual situation and reasonably be generated corresponding vocal print encoded radio
Method.
S405, judge whether vocal print encoded radio and the vocal print encoded radio similarity prestored are greater than similarity threshold.
Similarity threshold be measured by one of staff's setting two vocal print encoded radios whether be a user number
Value.It should be noted that similarity threshold can be adjusted according to demand.In the present embodiment, similarity threshold is preferably
0.95.The vocal print encoded radio prestored is stored in vocal print code database with corresponding mark.It is stored in the vocal print code database a large amount of
Vocal print encoded radio.Vocal print encoded radio in the vocal print code database is generated by the audio that platform provides.The audio that platform provides
The audio for needing to record when can be registration is also possible to user during using platform, the audio of platform acquisition.
Calculate the similarity between the vocal print coding all prestored in vocal print encoded radio and vocal print code database.And judgement sound
Whether line encoded radio and the vocal print encoded radio similarity prestored are greater than similarity threshold, if vocal print encoded radio is compiled with the vocal print prestored
Code value similarity is less than similarity threshold, then executes S406.If vocal print encoded radio is greater than with the vocal print encoded radio similarity prestored
Similarity threshold then executes S407.
Vocal print code database is added in S406, vocal print encoded radio and pending user identifier.
It should be noted that vocal print encoded radio is less than similarity threshold with the vocal print encoded radio similarity prestored, then illustrate
The vocal print encoded radio of the user is not present in vocal print code database.Therefore, it is necessary to by the corresponding vocal print encoded radio of pending user
It is added to vocal print code database.
S407, judge vocal print encoded radio whether in vocal print black list database.
If vocal print encoded radio is greater than similarity threshold with the vocal print encoded radio similarity prestored, illustrate in vocal print code database
It is middle there are the vocal print encoded radio of the user, it is corresponding to indicate that the corresponding natural person of the pending user registered risk control system
Platform account.Therefore, it is necessary to judge the whether illegal registration of pending user or malicious registration.
Storage is by black list user's information corresponding with vocal print encoded radio, black list user in vocal print black list database
Information includes: the corresponding user identifier of vocal print encoded radio and the correlated activation information that user carries out in platform, such as: hair
The model of cloth, the message etc. of reply.Black list user's information can be provided by each platform, be also possible to risk control system and adopted
Collection.
If vocal print encoded radio executes S408 in vocal print black list database.If vocal print encoded radio is not black in vocal print
List data library, then execute S409.
S408, determine that pending user is risk subjects.
S409, judge pending user identifier it is corresponding with the vocal print encoded radio prestored identify whether it is identical.
If vocal print encoded radio illustrates that pending user is not risk subjects not in vocal print black list database, pending
Core user is normal users, it is also necessary to further judgement.Judge that pending user identifier is encoded with the vocal print prestored
Be worth it is corresponding identify whether it is identical.
Judge pending user identifier it is corresponding with the vocal print encoded radio prestored identify whether it is identical, it is pending in order to determine
Whether user identifier and the vocal print encoded radio prestored are a user identifier, are (user) natural person in order to determine
Have registered multiple accounts.Wherein, account and user identifier correspond.
Judge pending user identifier it is corresponding with the vocal print encoded radio prestored identify whether it is identical, if so then execute
S410.If it is not, then executing S410.
S410, determine that pending user is exception object.
If pending user identifier mark corresponding with the vocal print encoded radio prestored is not identical, illustrate to may be one
(user) natural person has registered at least one account.It at this moment, is exception object by the pending user of determination.And to exception object
Carry out key monitoring.
S411, polymerization vocal print encoded radio and the vocal print encoded radio prestored.
In the present embodiment, vocal print encoded radio and the vocal print encoded radio prestored are polymerize, is polymerized to a new sound
Line encoded radio, new vocal print encoded radio are encoded with vocal print encoded radio and the similar vocal print of vocal print encoded radio height prestored
Value.
S412, the vocal print encoded radio by after polymerization, pending user identifier and the corresponding use of vocal print encoded radio prestored
Family mark is associated, and is stored to vocal print code database.
By the mark of new vocal print encoded radio, pending user after polymerization and the corresponding use of vocal print encoded radio prestored
Family mark is associated, and is stored to vocal print code database.
Pending user is determined as after exception object, and the information of exception object is sent to platform, the letter of exception object
Breath includes: that vocal print encoded radio, vocal print encoded radio similarity and the associated all user identifiers of vocal print encoded radio are sent to platform,
Platform determines whether to exception object vocal print black list database is added according to the information of exception object.
S413, determine that pending user is normal subjects.
If pending user identifier is identical as the corresponding mark of vocal print encoded radio prestored, determine that pending user is positive
Normal object, the i.e. corresponding user identifier of a user.It is that normal information is back to platform by auditing result.
The checking method of user a kind of is present embodiments provided, firstly, by obtaining pending user identifier and corresponding
Then audio identifies the corresponding vocal print encoded radio of audio；If vocal print encoded radio is greater than with the vocal print encoded radio similarity prestored
Similarity threshold, and pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that pending user
For exception object.The present embodiment carries out the audit of user using everyone sound wave feature with uniqueness, can recognize tool
The user of body solves the problems, such as multi-user's malicious registration, improves the safety of transaction platform.
Embodiment three
On the basis of the above embodiments, the embodiment of the present invention provides a kind of preferred embodiment.Fig. 5 is the embodiment of the present invention three
The platform of offer and the interaction diagrams of risk control system.
As shown in figure 5, risk control system mainly includes Information Security Dept 20 and 30 two parts of vocal print identification part composition.
S501, platform 10 determine pending user.
Such as: the user that each can be logged in the platform is determined as pending user.For another example: present count can be spaced
Amount or preset time obtain a user, are determined as pending user.Preset quantity and preset time can by platform according to
The number of users of platform is set.Illustratively, 10 users can be spaced and obtain a user, the user that will acquire is true
It is set to pending user.It can also be spaced one user of acquisition in 10 seconds, be determined as pending user.
S502, judge pending user whether by corresponding audio file.
Since the risk control system is the risk control system based on Application on Voiceprint Recognition, pending user must deposit
In corresponding audio file.If audio file is not present, S514 is executed.
If there are pending user, there are corresponding audio files, then by audio file and corresponding pending user
Mark is uploaded to internet, and by corresponding uniform resource locator, is sent to Application on Voiceprint Recognition portion 30.
S503, Application on Voiceprint Recognition portion 30 are according to uniform resource locator from the pending user identifier of the Internet download and corresponding
Audio file.
S504, Application on Voiceprint Recognition portion 30 identify the corresponding vocal print encoded radio of audio by Application on Voiceprint Recognition model.
Audio will be downloaded to format and clean after dirty data, Application on Voiceprint Recognition model is sent into, identifies sound
Frequently corresponding vocal print feature vector calculates vocal print encoded radio according to vocal print feature vector.
S505, Application on Voiceprint Recognition portion 30 are similar to the vocal print encoded radio calculating prestored in vocal print code database by vocal print encoded radio
Degree.
S506, Application on Voiceprint Recognition portion 30 determine vocal print encoded radio with the presence or absence of in vocal print code database according to similarity.
If vocal print encoded radio is greater than similarity threshold with the vocal print encoded radio similarity prestored, illustrate in vocal print code database
It is middle there are the vocal print encoded radio of the user, it is corresponding flat to indicate that the corresponding user's registration of the pending user crosses risk control system
Account family.Then execute S507.
Vocal print encoded radio is less than similarity threshold with the vocal print encoded radio similarity prestored, then explanation is in vocal print code database
There is no the vocal print encoded radios of the user.Therefore, it is necessary to the corresponding vocal print encoded radio of pending user is added to vocal print coding
Library.
S507, vocal print encoded radio is inquired in the vocal print black list database in Information Security Dept 20.
S508, Information Security Dept 20 judge the no hit vocal print encoded radio of black list database book.
Judge that vocal print encoded radio whether there is in black list database, if so, executing S512.If it is not, then executing S509.
S509, Information Security Dept 20 judge pending user identifier it is corresponding with the encoded radio prestored identify whether it is identical.
If so then execute S511, if otherwise executing S510.
Line polymerize by S510,20 sound of Information Security Dept.
Vocal print encoded radio and the vocal print encoded radio prestored are polymerize, a new vocal print encoded radio is polymerized to.
S511, normal users.
If pending user identifier is identical as the corresponding mark of vocal print encoded radio prestored, determine that pending user is positive
Normal object, the i.e. corresponding user identifier of (user) natural person.It is that normal information is back to platform 10 by auditing result.
S512, platform 10 handle black list user.
In the present embodiment, it should be noted that by user corresponding with vocal print encoded radio in vocal print black list database
Information and risk class are back to platform 10, handle user for platform 10 and provide reference.Platform 10 can be to black list user
Relevant processing is carried out, such as: title forbids giving out information.
S513, platform 10 judge whether exception object vocal print black list database is added.
If platform, which is determined, is added vocal print black list database for exception object, Information Security Dept 20 by exception object and
Vocal print black list database is added in relevant information.If it is not, then executing S514.
S514, end.
End refers to that the auditing flow of a pending user is finished.
Risk control system can carry out the black list user that the malicious registration user of multiple platforms or platform set
Polymerization so that the available pending user of platform whether be other platforms black list user so that platform can be right
Black list user carries out emphasis processing, prevents the loss of black list user's bring in advance, improves the safety of platform.
Embodiment five
Fig. 6 is the structural schematic diagram of the audit device for the user that the embodiment of the present invention five provides, and the present embodiment is applicable to
Audit transaction platform user the case where, the audit device of the user can be realized by way of software and/or hardware, such as
Shown in Fig. 6, the audit device of user provided in this embodiment includes: to obtain module 610, identification module 620 and determining module
630。
Module 610 is obtained, for obtaining pending user identifier and corresponding audio；
Identification module 620, for identification corresponding vocal print encoded radio of the audio；
Determining module 630, if being greater than similarity with the vocal print encoded radio similarity prestored for the vocal print encoded radio
Threshold value, and pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that the pending use
Family is exception object.
The audit device of a kind of user provided in this embodiment, firstly, by obtaining pending user identifier and corresponding
Then audio identifies the corresponding vocal print encoded radio of audio；If vocal print encoded radio is greater than with the vocal print encoded radio similarity prestored
Similarity threshold, and pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that pending user
For exception object.The present embodiment carries out the audit of user using everyone sound wave feature with uniqueness, can recognize tool
The user (natural person) of body, solves the problems, such as multi-user's malicious registration, improves the safety of transaction platform.
Further, identification module 620 includes:
Recognition unit, for identifying the corresponding vocal print feature vector of the audio by Application on Voiceprint Recognition model；
Generation unit, for generating corresponding vocal print encoded radio according to the vocal print feature vector.
Further, further includes:
Audio format conversion module will if the data format and preset data form for the audio be not identical
The Data Format Transform of the audio is preset data form, wherein the preset data form and the Application on Voiceprint Recognition model pair
It answers.
Further, the vocal print encoded radio prestored is stored in vocal print code database with corresponding mark.
Further, described device further include:
Memory module, if being less than similarity threshold with the vocal print encoded radio similarity prestored for the vocal print encoded radio
Value, the vocal print encoded radio and pending user identifier are stored to the vocal print code database.
Further, determining module 630 includes:
First determination unit, if being greater than phase for the vocal print encoded radio and the vocal print encoded radio similarity prestored
Like degree threshold value, and the vocal print encoded radio is in vocal print black list database, it is determined that the pending user is risk subjects；
Judging unit, if being greater than similarity threshold with the vocal print encoded radio similarity prestored for the vocal print encoded radio
Value, and the vocal print encoded radio is in vocal print black list database then judges the pending user identifier and the sound that prestores
Line encoded radio is corresponding identify whether it is identical；
Second determination unit, if not for pending user identifier mark corresponding with the vocal print encoded radio prestored
Together, it is determined that the pending user is exception object.
Further, described device further include:
Aggregation module, for polymerizeing the vocal print encoded radio and the vocal print encoded radio prestored；
Relating module, for by polymerization after vocal print encoded radio, the pending user identifier and the sound prestored
The corresponding user identifier of line encoded radio is associated, and is stored to vocal print code database.
User provided by any embodiment of the invention can be performed in the audit device of user provided by the embodiment of the present invention
Checking method, have the corresponding functional module of execution method and beneficial effect.
Embodiment six
Fig. 7 is a kind of structural schematic diagram for equipment that the embodiment of the present invention six provides, as shown in fig. 7, the equipment includes place
Manage device 710, memory 720, input unit 730 and output device 740；In equipment the quantity of processor 710 can be one or
It is multiple, in Fig. 7 by taking a processor 710 as an example；Processor 710, memory 720, input unit 730 and output dress in equipment
Setting 740 can be connected by bus or other modes, in Fig. 7 for being connected by bus.
Memory 720 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, if the corresponding program instruction/module of the checking method of the user in the embodiment of the present invention is (for example, user's examines
Acquisition module 610, identification module 620 and determining module 630 in nuclear device).Processor 710 is stored in memory by operation
Software program, instruction and module in 720 are realized thereby executing the various function application and data processing of equipment
The checking method of the user stated.
Memory 720 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function；Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 720 may include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 720 can be into one
Step includes the memory remotely located relative to processor 710, these remote memories can pass through network connection to equipment.On
The example for stating network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 730 can be used for receiving the number or character information of input, and generate and equipment/terminal/server
User setting and function control related key signals input.Output device 740 may include that display screen etc. shows equipment.
Embodiment seven
The embodiment of the present invention seven also provides a kind of storage medium comprising computer executable instructions, and the computer can be held
Row is instructed when being executed by computer processor for executing the checking method of user a kind of, this method comprises:
Obtain pending user identifier and corresponding audio；
Identify the corresponding vocal print encoded radio of the audio；
If the vocal print encoded radio is greater than similarity threshold with the vocal print encoded radio similarity prestored, and described pending
User identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that the pending user is exception object.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed examining for user provided by any embodiment of the invention
Relevant operation in kernel method.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
It is worth noting that, included each unit and module are in the embodiment of the audit device of above-mentioned user
It is divided according to the functional logic, but is not limited to the above division, as long as corresponding functions can be realized；Separately
Outside, the specific name of each functional unit is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (16)
1. a kind of checking method of user characterized by comprising
Obtain pending user identifier and corresponding audio；
Identify the corresponding vocal print encoded radio of the audio；
If the vocal print encoded radio is greater than similarity threshold, and the pending user with the vocal print encoded radio similarity prestored
It is different to identify mark corresponding from the vocal print encoded radio prestored, it is determined that the pending user is exception object.
2. the method according to claim 1, wherein the corresponding vocal print encoded radio of the identification audio, packet
It includes:
The corresponding vocal print feature vector of the audio is identified by Application on Voiceprint Recognition model；
Corresponding vocal print encoded radio is generated according to the vocal print feature vector.
3. according to the method described in claim 2, it is characterized in that, described identify the audio by the Application on Voiceprint Recognition model
Before corresponding sound characteristic vector, further includes:
If the data format of the audio and preset data form be not identical, the Data Format Transform by the audio is pre-
If data format, wherein the preset data form is corresponding with the Application on Voiceprint Recognition model.
4. the method according to claim 1, wherein including: the vocal print encoded radio prestored and corresponding mark
Knowledge is stored in vocal print code database.
5. according to the method described in claim 4, it is characterized by further comprising: if the vocal print encoded radio and the sound prestored
Line encoded radio similarity is less than similarity threshold, and the vocal print is added in the vocal print encoded radio and pending user identifier and is encoded
Library.
6. the method according to claim 1, wherein if the vocal print encoded radio and the vocal print encoded radio prestored
Similarity is greater than similarity threshold, and pending user identifier mark corresponding from the vocal print encoded radio prestored is different, then
Determine that the pending user is exception object, comprising:
If the vocal print encoded radio and the vocal print encoded radio similarity prestored are greater than similarity threshold, and the vocal print is compiled
Code value is in vocal print black list database, it is determined that the pending user is risk subjects；
If the vocal print encoded radio is greater than similarity threshold, and the vocal print encoded radio with the vocal print encoded radio similarity prestored
Not in vocal print black list database, then judge that pending user identifier mark corresponding with the vocal print encoded radio prestored is
It is no identical；
If pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that the pending use
Family is exception object.
7. according to the method described in claim 6, it is characterized in that, the determination pending user be exception object it
Afterwards, further includes:
It polymerize the vocal print encoded radio and the vocal print encoded radio prestored；
By vocal print encoded radio, the pending user identifier and the corresponding user of vocal print encoded radio prestored after polymerization
Mark is associated, and is stored to vocal print code database.
8. the audit device of user a kind of characterized by comprising
Module is obtained, for obtaining pending user identifier and corresponding audio；
Identification module, for identification corresponding vocal print encoded radio of the audio；
Determining module, if it is greater than similarity threshold with the vocal print encoded radio similarity prestored for the vocal print encoded radio, and
Pending user identifier mark corresponding from the vocal print encoded radio prestored is different, it is determined that the pending user is abnormal
Object.
9. device according to claim 8, which is characterized in that identification module includes:
Recognition unit, for identifying the corresponding vocal print feature vector of the audio by Application on Voiceprint Recognition model；
Generation unit, for generating corresponding vocal print encoded radio according to the vocal print feature vector.
10. device according to claim 9, which is characterized in that further include:
Audio format conversion module will be described if the data format and preset data form for the audio be not identical
The Data Format Transform of audio is preset data form, wherein the preset data form is corresponding with the Application on Voiceprint Recognition model.
11. device according to claim 8 characterized by comprising the vocal print encoded radio prestored and corresponding mark
Knowledge is stored in vocal print code database.
12. device according to claim 11, which is characterized in that further include:
Memory module will if being less than similarity threshold with the vocal print encoded radio similarity prestored for the vocal print encoded radio
The vocal print encoded radio and pending user identifier are stored to the vocal print code database.
13. device according to claim 8, which is characterized in that determining module includes:
First determination unit, if being greater than similarity for the vocal print encoded radio and the vocal print encoded radio similarity prestored
Threshold value, and the vocal print encoded radio is in vocal print black list database, it is determined that the pending user is risk subjects；
Judging unit, if it is greater than similarity threshold with the vocal print encoded radio similarity prestored for the vocal print encoded radio, and
The vocal print encoded radio then judges that the pending user identifier is encoded with the vocal print prestored not in vocal print black list database
Be worth it is corresponding identify whether it is identical；
Second determination unit, if different for pending user identifier mark corresponding from the vocal print encoded radio prestored,
Then determine that the pending user is exception object.
14. device according to claim 13, which is characterized in that further include:
Aggregation module, for polymerizeing the vocal print encoded radio and the vocal print encoded radio prestored；
Relating module, for compiling vocal print encoded radio, the pending user identifier and the vocal print prestored after polymerization
The corresponding user identifier of code value is associated, and is stored to vocal print code database.
15. a kind of equipment, which is characterized in that the equipment includes:
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now checking method of the user as described in any in claim 1-7.
16. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that program dress processed
Set the checking method that the user as described in any in claim 1-7 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811648912.4A CN109753778A (en) | 2018-12-30 | 2018-12-30 | Checking method, device, equipment and the storage medium of user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811648912.4A CN109753778A (en) | 2018-12-30 | 2018-12-30 | Checking method, device, equipment and the storage medium of user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109753778A true CN109753778A (en) | 2019-05-14 |
Family
ID=66405044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811648912.4A Pending CN109753778A (en) | 2018-12-30 | 2018-12-30 | Checking method, device, equipment and the storage medium of user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109753778A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750774A (en) * | 2019-10-21 | 2020-02-04 | 深圳众赢维融科技有限公司 | Identity recognition method and device |
| CN111311267A (en) * | 2020-03-05 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Multi-account risk prevention and control method, system and equipment |
| CN114125494A (en) * | 2021-09-29 | 2022-03-01 | 阿里巴巴（中国）有限公司 | Content auditing auxiliary processing method and device and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956451A (en) * | 2016-05-05 | 2016-09-21 | 长沙海川自动化设备有限公司 | Identity identification method and device for tower crane and construction hoist |
| CN106302332A (en) * | 2015-05-22 | 2017-01-04 | 阿里巴巴集团控股有限公司 | The access control method of user data, Apparatus and system |
| CN107358075A (en) * | 2017-07-07 | 2017-11-17 | 四川大学 | A kind of fictitious users detection method based on hierarchical clustering |
| CN107665301A (en) * | 2016-07-28 | 2018-02-06 | 腾讯科技（深圳）有限公司 | Verification method and device |
| CN108282490A (en) * | 2018-02-09 | 2018-07-13 | 深圳壹账通智能科技有限公司 | Processing method, device, computer equipment and the storage medium of abnormal registration user |
| CN108681934A (en) * | 2018-04-25 | 2018-10-19 | 厦门快商通信息技术有限公司 | A kind of recognition methods of transaction platform and its bad user |
| CN108766444A (en) * | 2018-04-09 | 2018-11-06 | 平安科技（深圳）有限公司 | User ID authentication method, server and storage medium |
-
2018
- 2018-12-30 CN CN201811648912.4A patent/CN109753778A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106302332A (en) * | 2015-05-22 | 2017-01-04 | 阿里巴巴集团控股有限公司 | The access control method of user data, Apparatus and system |
| CN105956451A (en) * | 2016-05-05 | 2016-09-21 | 长沙海川自动化设备有限公司 | Identity identification method and device for tower crane and construction hoist |
| CN107665301A (en) * | 2016-07-28 | 2018-02-06 | 腾讯科技（深圳）有限公司 | Verification method and device |
| CN107358075A (en) * | 2017-07-07 | 2017-11-17 | 四川大学 | A kind of fictitious users detection method based on hierarchical clustering |
| CN108282490A (en) * | 2018-02-09 | 2018-07-13 | 深圳壹账通智能科技有限公司 | Processing method, device, computer equipment and the storage medium of abnormal registration user |
| CN108766444A (en) * | 2018-04-09 | 2018-11-06 | 平安科技（深圳）有限公司 | User ID authentication method, server and storage medium |
| CN108681934A (en) * | 2018-04-25 | 2018-10-19 | 厦门快商通信息技术有限公司 | A kind of recognition methods of transaction platform and its bad user |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750774A (en) * | 2019-10-21 | 2020-02-04 | 深圳众赢维融科技有限公司 | Identity recognition method and device |
| CN110750774B (en) * | 2019-10-21 | 2021-12-03 | 深圳众赢维融科技有限公司 | Identity recognition method and device |
| CN111311267A (en) * | 2020-03-05 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Multi-account risk prevention and control method, system and equipment |
| CN111311267B (en) * | 2020-03-05 | 2022-06-21 | 支付宝(杭州)信息技术有限公司 | Multi-account risk prevention and control method, system and equipment |
| CN114125494A (en) * | 2021-09-29 | 2022-03-01 | 阿里巴巴（中国）有限公司 | Content auditing auxiliary processing method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977776B (en) | Information processing method, device, server and computer readable storage medium | |
| CN107395352B (en) | Personal identification method and device based on vocal print | |
| CN109753778A (en) | Checking method, device, equipment and the storage medium of user | |
| CN108804884A (en) | Identity authentication method, device and computer storage media | |
| TWI686721B (en) | Login method and device and electronic equipment | |
| CN104935438B (en) | Method and apparatus for authentication | |
| WO2019137066A1 (en) | Electric appliance control method and device | |
| CN104252479B (en) | Processing method, the device and system of information | |
| CN107978311A (en) | A kind of voice data processing method, device and interactive voice equipment | |
| CN102413101A (en) | Voice-print authentication system having voice-print password voice prompting function and realization method thereof | |
| CN110458662B (en) | Anti-fraud wind control method and device | |
| CN106713370B (en) | A kind of identity identifying method, server and mobile terminal | |
| WO2017114167A1 (en) | Authenticity verification method, apparatus and system for terminal | |
| CN105446741B (en) | A kind of mobile applications discrimination method compared based on API | |
| CN111355781A (en) | Voice information communication management method, device and storage medium | |
| CN105871925A (en) | User terminal, biological recognition cloud server and social security platform server | |
| CN108804908A (en) | A kind of device-fingerprint generation method, device and computing device | |
| ATE382229T1 (en) | METHOD AND SYSTEM FOR AUTHENTICATION IN A COMPUTER NETWORK | |
| CN105095415A (en) | Method and apparatus for confirming network emotion | |
| CN103905482B (en) | Method, push server and the system of pushed information | |
| CN112634897B (en) | Equipment awakening method and device, storage medium and electronic device | |
| CN110491373A (en) | Model training method, device, storage medium and electronic equipment | |
| CN109859030A (en) | Methods of risk assessment, device, storage medium and server based on user behavior | |
| CN108681934A (en) | A kind of recognition methods of transaction platform and its bad user | |
| CN108596635A (en) | A kind of agricultural product source tracing method and system based on cloud platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190514 |