CN108985776A - Credit card security monitoring method based on multiple Information Authentication - Google Patents
Credit card security monitoring method based on multiple Information Authentication Download PDFInfo
- Publication number
- CN108985776A CN108985776A CN201811067698.3A CN201811067698A CN108985776A CN 108985776 A CN108985776 A CN 108985776A CN 201811067698 A CN201811067698 A CN 201811067698A CN 108985776 A CN108985776 A CN 108985776A
- Authority
- CN
- China
- Prior art keywords
- vocal print
- application
- platform
- credit card
- user
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 230000001755 vocal effect Effects 0.000 claims abstract description 55
- 238000000605 extraction Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- 238000010200 validation analysis Methods 0.000 claims description 4
- 230000005236 sound signal Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000012790 confirmation Methods 0.000 abstract description 10
- 238000004422 calculation algorithm Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 3
- 230000033764 rhythmic process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 206010011878 Deafness Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011840 criminal investigation Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
- G06Q20/40145—Biometric identity checks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/30—Payment architectures, schemes or protocols characterised by the use of specific devices or networks
- G06Q20/34—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using cards, e.g. integrated circuit [IC] cards or magnetic cards
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Strategic Management (AREA)
- Acoustics & Sound (AREA)
- Game Theory and Decision Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses the credit card security monitoring methods based on multiple Information Authentication, including call center, the output end of the call center is connect with the input terminal of dynamic voice print database, and the output end of dynamic voice print database is connect with the input terminal of Application on Voiceprint Recognition platform, the Application on Voiceprint Recognition platform is realized with call center and is bi-directionally connected, and the input terminal of Application on Voiceprint Recognition platform is connect with the output end in blacklist vocal print library, the input terminal in blacklist vocal print library and the output end of telephonograph connect, and are related to Internet technical field.It should be based on credit card security monitoring system and its monitoring method, very good solution credit card in use often occurs dangerous, the voice of vocal print feature obtains inconvenient problem, greatly reduce the cost for obtaining voice, it simplifies using step, is suitble to remote identity confirmation, vocal print identification is low with the algorithm complexity of confirmation, recognition accuracy is high, greatly improves the working efficiency of credit card centre.
Description
Technical field
The present invention relates to Internet technical fields, specially based on the credit card security monitoring method of multiple Information Authentication.
Background technique
Credit card is a kind of mode of non-cash transaction payment, is that bank is supplied to a kind of first consume of user and refunds afterwards
The micro-credit means of payment, earliest credit card come across at the end of the 19th century, and credit card is divided into credit card and two kinds of quasi- credit card, tool
It is provided with clearing service, facilitates purchase and consumption, enhances the sense of security;Simplify gathering formality, economize in social labor power;Promote commodity pin
The features such as selling, stimulating social demand, credit card is signed and issued to the good personage of those credit status by bank or other financial institutions,
For being a kind of special letter in specified businessman's shopping and consumption or in the special card of mechanism of appointed bank access cash
Use voucher
It is related to safe handling problem during credit card use, the invention patent presets amount by user, carries out
Security information pays a return visit service, and user first can voluntarily pay, and if necessary to verify, can star and tests more than amount and frequency of usage
Card service, is paid a return visit by telephone redialing and information, and return visit can set cell-phone number, identification card number, the problem of presetting, and
Sound groove recognition technology in e system carries out whether comprehensive judgement verification is user, if there are doubtful problem, banks for Information Problems
The amount of money will temporarily be locked, until guaranteeing that information verification correctly carries out information account transfer again.
Remotely identify and confirm to safety and precise the identity of credit card user;As long as can be simple and convenient and safe by certain
Reliable means ensure that identity is legal, so that it may prevent the phenomenon that credit card is by unauthorized theft substantially.Similar to the fingerprint of the mankind
And DNA, vocal print are also the unique individual character biological characteristic of human body, are difficult to find two duplicate people of vocal print, by adopting in advance
Collect the sample sound of credit card people, therefrom extract Application on Voiceprint Recognition " gene " sequence, then swipes the card excess and frequency is swiped the card
When number overrun is demonstrate,proved, confirmation is compared with the vocal print in vocal print library in the vocal print of credit card user, it will be able to easily
Judge whether receiptor is legal.For special populations such as minimal amount of deaf and dumb crowds, then it is aided with the confirmation of manual inspection means.In this way
It answers telephone number and default question answering and Application on Voiceprint Recognition combines, a possibility that usurping will not only be greatly lowered,
And greatly improve the working efficiency of credit card centre.
Summary of the invention
(1) the technical issues of solving
In view of the deficiencies of the prior art, the present invention provides the credit card security monitoring methods based on multiple Information Authentication, solve
Credit card in use often occurs dangerous, and it is inconvenient that the voice of vocal print feature obtains, and obtains the higher cost of voice,
Use cumbersome, unsuitable remote identity confirmation, the complicated height of the algorithm of vocal print identification and confirmation.The lower problem of recognition accuracy.
The problem of.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs: the credit card peace based on multiple Information Authentication
The output end of full monitoring method, including call center, the call center is connect with the input terminal of dynamic voice print database, and dynamic
The output end of state voice print database is connect with the input terminal of Application on Voiceprint Recognition platform, and the Application on Voiceprint Recognition platform and call center realize
It is bi-directionally connected, and the input terminal of Application on Voiceprint Recognition platform is connect with the output end in blacklist vocal print library, blacklist vocal print library
Input terminal and the output end of telephonograph connect, and blacklist vocal print library, Application on Voiceprint Recognition platform and dynamic voice print database with
Visualized O&M management platform realization is bi-directionally connected.
The present invention also provides the monitoring methods of the credit card security monitoring method based on multiple Information Authentication, specifically include
Following steps;
S1, amount being preset by user first, carries out security information and pays a return visit service, user first can voluntarily pay, if
It needs to verify, can star more than amount and the frequency of usage service for checking credentials, paid a return visit by telephone redialing and information, return visit can be set
Determine cell-phone number, identification card number, the problem of presetting, and sound groove recognition technology in e system carries out whether comprehensive judgement verification is use
Family;
After S2, call center receive the voice signal of user, carries out real-time characteristic and extract modeling, vocal print automatic identification model can
To pass through acoustic feature, lexical characteristics, prosodic features, languages, dialect and accent information and channel information respectively to the language of user
Sound signal extracts identification;
S3, dynamic voice print database can carry out News Search comparison to the user vocal feature of extraction, then pass through Application on Voiceprint Recognition
Platform carries out 1:1 identity validation, while real-time voice stream can be conveyed directly to Application on Voiceprint Recognition platform, and Application on Voiceprint Recognition platform will simultaneously be known
Other result issues call center, and telephonograph can carry out real-time recording to the voice calls of user, and by the audio signal under record
It carries out in feature extraction modeling storage to blacklist vocal print library;
Recognition result can be sent to visualized O&M management platform and can analyzed recognition result by S4, Application on Voiceprint Recognition platform,
If identifying strictly user, it will do it prompt and assist decision, it can be by the voice messaging of user to blacklist vocal print library
It is removed on blacklist vocal print library, if identifying when not being user, visualized O&M manages platform can be by blacklist vocal print
The data that caller's feature extraction goes out in library carry out 1:n identification by Application on Voiceprint Recognition platform, and the result of identification is transmitted
To visualized O&M management platform, the safety voiceprint of credit card is monitored to realize.
(3) beneficial effect
The present invention provides the credit card security monitoring methods based on multiple Information Authentication.Having compared with prior art following has
Beneficial effect: the output end and dynamic vocal print of the heart in a call should be passed through based on credit card security monitoring system and its monitoring method
The input terminal of database connects, and the output end of dynamic voice print database is connect with the input terminal of Application on Voiceprint Recognition platform, and vocal print is known
Other platform is realized with call center and is bi-directionally connected, and the input terminal of Application on Voiceprint Recognition platform and the output end in blacklist vocal print library connect
It connects, the output end of the input terminal in blacklist vocal print library and telephonograph connects, and blacklist vocal print library, Application on Voiceprint Recognition platform and dynamic
State voice print database is bi-directionally connected, it can be achieved that preset amount by user with visualized O&M management platform realization, into
Row security information pays a return visit service, and user first can voluntarily pay, and if necessary to verify, can star more than amount and frequency of usage
The service for checking credentials is paid a return visit by telephone redialing and information, and return visit can set cell-phone number, identification card number, the problem of presetting, with
And sound groove recognition technology in e system carries out whether comprehensive judgement verification is user, if there are doubtful problem, silver for Information Problems
It is about to temporarily lock the amount of money, until guaranteeing that information verification correctly carries out information account transfer again, remotely identifies to safety and precise and true
The identity for recognizing credit card user therefrom extracts Application on Voiceprint Recognition " gene " by collecting the sample sound of credit card people in advance
Sequence, then swipe the card excess and frequency swipe the card number overrun card when, will be in the vocal print of credit card user and vocal print library
Confirmation is compared in vocal print, it will be able to judge whether receiptor is legal easily, for special people such as minimal amount of deaf and dumb crowds
Group, then it is aided with the confirmation of manual inspection means, answer telephone number and default question answering and Application on Voiceprint Recognition in this way combines,
A possibility that usurping will not only be greatly lowered, but also greatly improve the working efficiency of credit card centre, thus well
It solves credit card and often occurs in use dangerous, the voice of vocal print feature obtains inconvenient problem, substantially reduces
The cost for obtaining voice is simplified using step, is suitble to remote identity confirmation, and vocal print identification is low with the algorithm complexity of confirmation,
Recognition accuracy is high.
Detailed description of the invention
Fig. 1 is the structural principle block diagram of present system.
In figure, 1 call center, 2 dynamic voice print databases, 3 Application on Voiceprint Recognition platforms, 4 blacklist vocal print libraries, 5 telephonographs,
6 visualized O&M manage platform.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, the embodiment of the present invention provides a kind of technical solution: the credit card security prison based on multiple Information Authentication
The output end of survey method, including call center 1, call center 1 is connect with the input terminal of dynamic voice print database 2, and dynamic sound
The output end of line database 2 is connect with the input terminal of Application on Voiceprint Recognition platform 3, and Application on Voiceprint Recognition platform 3 is realized two-way with call center 1
Connection, and the input terminal of Application on Voiceprint Recognition platform 3 is connect with the output end in blacklist vocal print library 4, the input terminal in blacklist vocal print library 4
Connect with the output end of telephonograph 5, and blacklist vocal print library 4, Application on Voiceprint Recognition platform 3 and dynamic voice print database 2 with can
It is bi-directionally connected depending on changing the realization of operation management platform 6, the task of feature extraction is that extract and select to have the vocal print of speaker can
Divide the acoustics or language feature of the characteristics such as property is strong, stability is high, different from speech recognition, the feature of Application on Voiceprint Recognition must be " a
Property " feature, and the feature of Speaker Identification must be " common feature " for speaker, although major part vocal print is known at present
Other system be all acoustics level feature, but characterize a personal touch feature should be multifaceted, comprising: (1)
Acoustic feature related with the anatomical structure of pronunciation mechanism of the mankind, nasal sound, band deep breathing sound, hoarse sound, laugh etc.;(2)
Semanteme, rhetoric, pronunciation, speech habit for being influenced by socioeconomic status, education level, birthplace etc. etc.;(3) personal touch
Or the features such as the rhythm, rhythm, speed, intonation, volume influenced by parent.Go out from the angle that can be modeled using mathematical method
Hair, the feature that vocal print automatic identification model can be used at present includes: (1) acoustic feature;(2) lexical characteristics;(3) rhythm is special
Sign;(4) languages, dialect and accent information;(5) channel information etc., according to different mission requirements, Application on Voiceprint Recognition is also faced with one
The problem of feature selecting or feature are selected, for example, to " channel " information, in criminal investigation using upper, it is desirable to not have to, that is to say, that it is desirable that
Influence of the channel to Speaker Identification is weakened, because it is desirable that regardless of it can be recognized speaker with what channel system
Come;And on bank transaction, it is desirable to use channel information, that is, wish that channel has larger impact to Speaker Identification, so as to pick
It except recording, the brings such as imitates and influences, in short, preferable feature, it should it can efficiently differentiate different speakers, but energy
Opposite stabilization is kept when same speaker's voice changes;It is not easy to be imitated or can preferably be solved by other people by other people
Imitation problem;There are following a few major class methods for pattern-recognition with preferable noiseproof feature:
(1) template matching method: using dynamic time bending (DTW) to be directed at trained and test feature sequence, it is mainly used for solid
Determine the application (usually text inter-related task) of phrase;
(2) arest neighbors method: retaining all characteristic vectors when training, and when identification finds in trained vector recently each vector
K, identified accordingly, the amount of usual model storage and similar calculating is all very big;
(3) neural network method: there are many kinds of form, such as Multilayer Perception, radial basis function (RBF), can explicitly train with
Speaker and its background speaker are distinguished, training burden is very big, and the replicability of model is bad;
(4) hidden Markov model (HMM) method: being ratio usually using the HMM or gauss hybrid models (GMM) of list state
More popular method, effect are relatively good;
(5) VQ clustering method (such as LBG): effect is relatively good, algorithm complexity is not high yet and HMM method cooperate more can be with
Receive better effect;
(6) multinomial classifier methods: there is higher precision, but model storage and calculation amount are all bigger;
Application on Voiceprint Recognition needs the critical issue that solves, and such as: can short speech problem carry out mould with very short voice there are also very much
Type training, and being identified with the very short time, this be mainly sound be not easy to obtain using required;Sound imitates
(or playing a record) problem will efficiently differentiate die sinking imitative sound (recording) and real sound;Target is said in the case of more speakers
Talk about effective detection of people;Eliminate or weaken sound variation (different language, content, mode, physical condition, time, age etc.) band
The influence come;Eliminating channel difference and background noise bring influences;Need to use some other technology at this time to assist completing,
Such as denoising, adaptive technology.
To speaker verification, it is also faced with a dilemma problem, in general, two of characterization speaker identification system performance
Important parameter is false rejection rate and false acceptance rate, the former be the real speaker of refusal and caused by mistake, the latter is to receive
Collect outer speaker and caused by mistake, the two is related to the setting of threshold value, the two equal value error rates such as referred to as, in existing skill
Under art is horizontal, the two can not reach minimum simultaneously, need to adjust threshold value to meet the needs of different application, such as " easy in needs
With property " in the case where, false rejection rate can be allowed lower, false acceptance rate will increase at this time, so that safety reduces;Right
In " safety " demanding situation, false acceptance rate can be allowed lower, false rejection rate will increase at this time, thus ease for use
It reduces.The former may be summarized to be " peaceful wrong not leakage ", and the latter " can rather leak not wrong ".We call the adjustment of real threshold value
" operating point " adjustment.Good system should allow freely adjusting to operating point.
The invention also discloses the monitoring methods of the credit card security monitoring method based on multiple Information Authentication, specifically include
Following steps;
S1, amount being preset by user first, carries out security information and pays a return visit service, user first can voluntarily pay, if
It needs to verify, can star more than amount and the frequency of usage service for checking credentials, paid a return visit by telephone redialing and information, return visit can be set
Determine cell-phone number, identification card number, the problem of presetting, and sound groove recognition technology in e system carries out whether comprehensive judgement verification is use
Family;
After S2, call center 1 receive the voice signal of user, carries out real-time characteristic and extract modeling, vocal print automatic identification model
Acoustic feature, lexical characteristics, prosodic features, languages, dialect and accent information and channel information can be passed through respectively to user's
Voice signal extracts identification, accurately identifies speaker's true identity, correct to distinguish the biological information really and forged, and prevents
The various counterfeit, possibility stealing or replicate;
S3, dynamic voice print database 2 can carry out News Search comparison to the user vocal feature of extraction, then pass through Application on Voiceprint Recognition
Platform 3 carries out 1:1 identity validation, while real-time voice stream can be conveyed directly to Application on Voiceprint Recognition platform 3, and Application on Voiceprint Recognition platform 3 is simultaneously
Recognition result is issued into call center 1, telephonograph 5 can the voice calls to user carry out real-time recording, and by the sound under record
Frequency signal carries out in feature extraction modeling storage to blacklist vocal print library 4, can carry out high concurrent processing to mass data, support ten
1:N seconds grade retrievals of hundred million grades of voice print databases, quasi- Que Shuai≤99%;
Recognition result can be sent to visualized O&M management platform 6 by S4, Application on Voiceprint Recognition platform 3 to divide recognition result
Analysis, if identifying strictly user, will do it prompt and assists decision, can be by the voice of user to blacklist vocal print library 4
Information removes on blacklist vocal print library 4, if identifying when not being user, visualized O&M manages platform 6 can be by black name
The data that caller's feature extraction goes out in monophone line library 4 carry out 1:n identification by Application on Voiceprint Recognition platform 3, and by identification
As a result it is sent in visualized O&M management platform 6, the safety voiceprint of credit card is monitored to realize, in more people's session operational scenarios
In accurately recognize user, isolate single speaker's audio, and identify everyone identity and speech content, vocal print is counter to cheat
System the criminal offenses case offer solution such as swindle, extorts, kidnapping by phone and network for criminal, is communicating
It is embedded in sound groove recognition technology in e in system or safety monitoring system, during monitoring, establishes dynamic vocal print black/white list library in real time,
The ultra-large comparison of 1:n is carried out, accurately identifies incoming person's true identity, and continue tracing and monitoring suspicion personnel, is social security
Handling institution provides the Application on Voiceprint Recognition existence verification solution of exclusive customization, on the basis of original social security information management system
On, using sound groove recognition technology in e, remote phone authentication is carried out, compares skilled person group for the use to information system and sets
Automated validation mode is set, for using internet relatively and having the people of threshold that semi-automatic authentication mode is arranged, uses simplicity, sexual valence
Than high, vocal print credit card authorization system can be directed to black intermediary, and identity is falsely used, and high-risk user establishes data center, establishes black name
It is single, to the direct early warning of user is matched with blacklist, intercept.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (2)
1. the credit card security monitoring method based on multiple Information Authentication, including call center (1), it is characterised in that: described to exhale
The output end at center (1) and the input terminal of dynamic voice print database (2) is made to connect, and the output end of dynamic voice print database (2)
It being connect with the input terminal of Application on Voiceprint Recognition platform (3), the Application on Voiceprint Recognition platform (3) is realized with call center (1) and is bi-directionally connected, and
The input terminal of Application on Voiceprint Recognition platform (3) is connect with the output end in blacklist vocal print library (4), blacklist vocal print library (4) it is defeated
Enter end to connect with the output end of telephonograph (5), and blacklist vocal print library (4), Application on Voiceprint Recognition platform (3) and dynamic voice print database
It realizes and is bi-directionally connected with visualized O&M management platform (6) in library (2).
2. the monitoring method of the credit card security monitoring method according to claim 1 based on multiple Information Authentication, special
Sign is: specifically including following steps;
S1, amount being preset by user first, carries out security information and pays a return visit service, user first can voluntarily pay, if
It needs to verify, can star more than amount and the frequency of usage service for checking credentials, paid a return visit by telephone redialing and information, return visit can be set
Determine cell-phone number, identification card number, the problem of presetting, and sound groove recognition technology in e system carries out whether comprehensive judgement verification is use
Family;
After S2, call center (1) receive the voice signal of user, carries out real-time characteristic and extract modeling, vocal print automatic identification mould
Type can pass through acoustic feature, lexical characteristics, prosodic features, languages, dialect and accent information and channel information to user respectively
Voice signal extract identification;
S3, dynamic voice print database (2) can carry out News Search comparison to the user vocal feature of extraction, then be known by vocal print
Other platform (3) carries out 1:1 identity validation, while real-time voice stream can be conveyed directly to Application on Voiceprint Recognition platform (3), and Application on Voiceprint Recognition is flat
Platform (3) simultaneously issues recognition result call center (1), and telephonograph (5) meeting carries out real-time recording to the voice calls of user, and
Audio signal under record is carried out in feature extraction modeling storage to blacklist vocal print library (4);
Recognition result can be sent to visualized O&M management platform (6) and can carried out to recognition result by S4, Application on Voiceprint Recognition platform (3)
Analysis, if identifying strictly user, will do it prompt and assists decision, can be by user's to blacklist vocal print library (4)
Voice messaging removes on blacklist vocal print library (4), if identifying when not being user, visualized O&M manages platform (6)
The data that the interior caller's feature extraction in blacklist vocal print library (4) goes out 1:n identity can be carried out by Application on Voiceprint Recognition platform (3) to distinguish
Recognize, and the result of identification is sent in visualized O&M management platform (6), the safety voiceprint of credit card is supervised to realize
It surveys.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811067698.3A CN108985776A (en) | 2018-09-13 | 2018-09-13 | Credit card security monitoring method based on multiple Information Authentication |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811067698.3A CN108985776A (en) | 2018-09-13 | 2018-09-13 | Credit card security monitoring method based on multiple Information Authentication |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108985776A true CN108985776A (en) | 2018-12-11 |
Family
ID=64545666
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811067698.3A Withdrawn CN108985776A (en) | 2018-09-13 | 2018-09-13 | Credit card security monitoring method based on multiple Information Authentication |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108985776A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109858917A (en) * | 2019-02-13 | 2019-06-07 | 苏州意能通信息技术有限公司 | A kind of anti-fake system and its method based on artificial intelligence |
CN110322888A (en) * | 2019-05-21 | 2019-10-11 | 平安科技(深圳)有限公司 | Credit card unlocking method, device, equipment and computer readable storage medium |
CN110334963A (en) * | 2019-07-11 | 2019-10-15 | 四川亨通网智科技有限公司 | Admission ticket order background management system |
CN110443018A (en) * | 2019-07-30 | 2019-11-12 | 深圳力维智联技术有限公司 | Method, terminal, system and readable storage medium storing program for executing based on Application on Voiceprint Recognition identity |
CN111128199A (en) * | 2019-12-27 | 2020-05-08 | 中国人民解放军陆军工程大学 | Sensitive speaker monitoring and recording control method and system based on deep learning |
CN113781059A (en) * | 2021-11-12 | 2021-12-10 | 百融至信(北京)征信有限公司 | Identity authentication anti-fraud method and system based on intelligent voice |
CN115083045A (en) * | 2022-06-24 | 2022-09-20 | 珠海格力电器股份有限公司 | Method and device for awakening unlocking function, door lock, equipment and storage medium |
WO2023124248A1 (en) * | 2021-12-28 | 2023-07-06 | 荣耀终端有限公司 | Voiceprint recognition method and apparatus |
-
2018
- 2018-09-13 CN CN201811067698.3A patent/CN108985776A/en not_active Withdrawn
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109858917A (en) * | 2019-02-13 | 2019-06-07 | 苏州意能通信息技术有限公司 | A kind of anti-fake system and its method based on artificial intelligence |
CN110322888A (en) * | 2019-05-21 | 2019-10-11 | 平安科技(深圳)有限公司 | Credit card unlocking method, device, equipment and computer readable storage medium |
CN110322888B (en) * | 2019-05-21 | 2023-05-30 | 平安科技(深圳)有限公司 | Credit card unlocking method, apparatus, device and computer readable storage medium |
CN110334963A (en) * | 2019-07-11 | 2019-10-15 | 四川亨通网智科技有限公司 | Admission ticket order background management system |
CN110443018A (en) * | 2019-07-30 | 2019-11-12 | 深圳力维智联技术有限公司 | Method, terminal, system and readable storage medium storing program for executing based on Application on Voiceprint Recognition identity |
CN111128199A (en) * | 2019-12-27 | 2020-05-08 | 中国人民解放军陆军工程大学 | Sensitive speaker monitoring and recording control method and system based on deep learning |
CN113781059A (en) * | 2021-11-12 | 2021-12-10 | 百融至信(北京)征信有限公司 | Identity authentication anti-fraud method and system based on intelligent voice |
WO2023124248A1 (en) * | 2021-12-28 | 2023-07-06 | 荣耀终端有限公司 | Voiceprint recognition method and apparatus |
CN115083045A (en) * | 2022-06-24 | 2022-09-20 | 珠海格力电器股份有限公司 | Method and device for awakening unlocking function, door lock, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108985776A (en) | Credit card security monitoring method based on multiple Information Authentication | |
Singh et al. | Applications of speaker recognition | |
Naik | Speaker verification: A tutorial | |
US9659564B2 (en) | Speaker verification based on acoustic behavioral characteristics of the speaker | |
US8209174B2 (en) | Speaker verification system | |
CN105933323B (en) | Voiceprint registration, authentication method and device | |
US20110082874A1 (en) | Multi-party conversation analyzer & logger | |
KR100406307B1 (en) | Voice recognition method and system based on voice registration method and system | |
CN102324232A (en) | Method for recognizing sound-groove and system based on gauss hybrid models | |
CN103971700A (en) | Voice monitoring method and device | |
CN101540170B (en) | Voiceprint recognition method based on biomimetic pattern recognition | |
CN110459226A (en) | A method of voice is detected by vocal print engine or machine sound carries out identity veritification | |
CN105679323B (en) | A kind of number discovery method and system | |
CN107563758A (en) | A kind of finance letter that solves examines the detection method and system that habitual offender swindles in business | |
CN113744742B (en) | Role identification method, device and system under dialogue scene | |
CN108804669A (en) | A kind of fraudulent call method for detecting based on intention understanding technology | |
KR101754954B1 (en) | Certification system and method using autograph and voice | |
KR100779242B1 (en) | Speaker recognition methods of a speech recognition and speaker recognition integrated system | |
Kekre et al. | Speaker recognition using Vector Quantization by MFCC and KMCG clustering algorithm | |
Wildermoth et al. | GMM based speaker recognition on readily available databases | |
US10957318B2 (en) | Dynamic voice authentication | |
Saleema et al. | Voice biometrics: the promising future of authentication in the internet of things | |
Maes et al. | Open sesame! Speech, password or key to secure your door? | |
Kao et al. | Voice Response Questionnaire System for Speaker Recognition Using Biometric Authentication Interface. | |
CN111091836A (en) | Intelligent voiceprint recognition method based on big data |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181211 |