CN111833068A - Identity verification system and method based on voiceprint recognition - Google Patents
Identity verification system and method based on voiceprint recognition Download PDFInfo
- Publication number
- CN111833068A CN111833068A CN202010759931.5A CN202010759931A CN111833068A CN 111833068 A CN111833068 A CN 111833068A CN 202010759931 A CN202010759931 A CN 202010759931A CN 111833068 A CN111833068 A CN 111833068A
- Authority
- CN
- China
- Prior art keywords
- voiceprint model
- sample
- voiceprint
- current
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012795 verification Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims description 26
- 238000013507 mapping Methods 0.000 claims description 13
- 230000006854 communication Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 description 3
- 238000012550 audit Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- ZRHANBBTXQZFSP-UHFFFAOYSA-M potassium;4-amino-3,5,6-trichloropyridine-2-carboxylate Chemical compound [K+].NC1=C(Cl)C(Cl)=NC(C([O-])=O)=C1Cl ZRHANBBTXQZFSP-UHFFFAOYSA-M 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Images
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
- G06Q20/40145—Biometric identity checks
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/15—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being formant information
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to the technical field of voiceprint recognition, in particular to an identity verification system and method based on voiceprint recognition, wherein the system comprises a client, a server and a background terminal, the server comprises an input module, a database, a processing module and an output module, and the identity verification system comprises: the input module is used for acquiring a current voiceprint model sent by a client in the call process; the database is used for pre-storing a sample voiceprint model of a client; the processing module is used for receiving the current voiceprint model, processing the current voiceprint model according to the sample voiceprint model, and generating first alarm information if the current voiceprint model is not matched with the sample voiceprint model; otherwise, generating verification passing prompt information; the output module is used for sending first warning information and verification passing prompt information to the background terminal; by adopting the scheme, the problem that the identity verification is time-consuming and long can be solved.
Description
Technical Field
The invention relates to the technical field of voiceprint recognition, in particular to an identity verification system and method based on voiceprint recognition.
Background
At present, in credit service credit granting and auditing of the internet, for certain specific passenger groups, besides using a model and a strategy to perform system automatic judgment, an auditor is required to perform electric audit operation on a client through a telephone, and the operation mainly comprises that the auditor performs comprehensive investigation such as identity verification, borrowing purpose verification, repayment willingness and repayment capability verification on the client according to a manual audit tactic script. However, in the manual auditing process, an auditor communicates related clients through a telephone according to a telephone script, so that the time consumption is long, the same communication process needs to be performed on each client, particularly the client identity is verified, the auditor needs to have rich experience through telephone verification, the time consumption is long, and the influence on the user experience of high-quality clients is large.
Disclosure of Invention
The invention aims to provide an identity verification system and method based on voiceprint recognition, which can solve the problem of long time consumption of identity verification.
The basic scheme provided by the invention is as follows: identity verification system based on voiceprint recognition, including client, server and backstage terminal, the server includes input module, database, processing module and output module, wherein: the input module is used for acquiring a current voiceprint model sent by a client in the call process; the database is used for pre-storing a sample voiceprint model of a client; the processing module is used for receiving the current voiceprint model, processing the current voiceprint model according to the sample voiceprint model, and generating first alarm information if the current voiceprint model is not matched with the sample voiceprint model; otherwise, generating verification passing prompt information; and the output module is used for sending the first alarm information and the verification passing prompt information to the background terminal.
The working principle and the advantages of the invention are as follows:
in the scheme, in the communication process of credit verification, the current voiceprint model of the client is obtained through the input module, and because the sample voiceprint model of the client is stored in the database in advance, the identity verification can be completed through the voiceprint of the client through comparison and comparison of the processing module; the identity information of the client does not need to be inquired by the auditor, so that the identity verification time is saved; the client who has passed the voiceprint comparison generates verification passing prompt information, so that the auditor can reduce the questions of the identity verification type problems or does not carry out the identity verification type problems, and for the client who does not pass the voiceprint identification, the auditor can be prompted by generating alarm information, and whether the client is a fraud client or not is considered in a key mode, so that the number of the identity verification type problems of the client needs to be increased, and the fraud risk is prevented.
In conclusion, the voiceprint information is judged in an auxiliary mode through the system, the judgment result is more objective, the accuracy of client identification can be improved, and the subjective judgment error of an auditor is reduced; the efficiency of manual review can also be improved, the time input of identity verification is reduced, and therefore the customer experience is improved.
Further, the output module is also used for sending specific sample text information to the client terminal in the second type account registration stage; the input module is also used for acquiring a sample voiceprint model of the text information of the sample read by the client; and the database is also used for receiving the text information and the sample voiceprint models and inputting the text information and the corresponding sample voiceprint models into a pre-established mapping relation table.
Has the advantages that: generally, one type of bank card account refers to a deposit card transacted in a bank and can be used for depositing and withdrawing money on a self-service cash dispenser, and the other type of bank card account refers to an electronic account based on a physical card; because the scheme mainly relates to credit approval of the internet credit business, the credit business can be transacted after a client applies for a second type of account, and a sequence exists; therefore, in the registration stage of the second type of account, the server sends some specific text information to enable the client to read; meanwhile, the input module captures a corresponding voiceprint model and stores the voiceprint model in a mapping relation table of a database; therefore, matching of follow-up credit granting and auditing is facilitated, the data acquisition process is optimized, the problem of complex process is avoided, and the use experience of customers is improved.
Further, the processing module is also used for processing the current voiceprint model according to a voice recognition algorithm to generate current character information; matching sample text information which is the same as the current text information and a corresponding sample voiceprint model from the mapping relation table according to a keyword matching algorithm; and if the sample voiceprint model is different from the current voiceprint model, generating first alarm information.
Has the advantages that: because the current voiceprint model is generated in the voice call in the trust auditing stage, in order to avoid requiring a client to repeat a specific utterance in the process, the scheme can acquire any statement in the call and position the same statement according to the keyword matching technology, thereby obtaining the voiceprint model which can be used for comparison; the system is more complete and humanized in function, and the customer experience can be improved.
Further, the processing module is further configured to extract feature information of the current voiceprint model and the sample voiceprint model respectively, and determine whether the current voiceprint model and the sample voiceprint model are the same according to the feature information; the characteristic information comprises formant frequency and waveform trend.
Has the advantages that: and respectively selecting obvious and stable characteristics from the two compared voiceprint models as comparison characteristics. Generally, the frequency value of the formant and the trend of the waveform thereof are the most stable characteristics, and have strong specificity and highest utilization value.
Further, the voice recognition algorithm adopts a science news flying voice recognition algorithm; the keyword matching algorithm adopts a KMP algorithm.
Has the advantages that: when the KMP algorithm is mismatched in the matching process, unnecessary matching is skipped according to information obtained in some matching processes, instead of re-matching from the next character of the original string, so that higher matching efficiency can be achieved; the time consumption of matching is shortened; the existing relatively mature science news flying voice recognition algorithm is adopted, and the development cost can be saved.
Further, the database is also used for storing the blacklist user voiceprint model; and the processing module is also used for judging the current voiceprint model according to the blacklist voiceprint model and generating second alarm information if the current voiceprint model is the same as the blacklist voiceprint model.
Has the advantages that: by adopting the scheme, the screened voiceprint model of the cheating client can be stored in a database and used as a blacklist; the current voiceprint model can be judged and checked in the identity verification process, so that the blacklist user is excluded from cheating again.
The invention also provides an identity verification method based on voiceprint recognition, which comprises the following steps:
s1, acquiring a current voiceprint model sent by the client in the call process;
s2, receiving the current voiceprint model, processing the current voiceprint model according to a sample voiceprint model prestored in a database, and generating first alarm information if the current voiceprint model is not matched with the sample voiceprint model; otherwise, generating verification passing prompt information;
and S3, sending the first alarm information and the verification passing prompt information to the background terminal.
Has the advantages that: according to the scheme, firstly, a sample voiceprint model of a client is stored in a database in advance, and then in the process of a credit verification call, the current voiceprint model of the client is adopted to be compared with the sample voiceprint model so as to complete identity verification work; the identity information of the client does not need to be inquired by the auditor, so that the identity verification time is saved; the client who has passed the voiceprint comparison generates verification passing prompt information, so that the auditor can reduce the questions of the identity verification type problems or does not carry out the identity verification type problems, and for the client who does not pass the voiceprint identification, the auditor can be prompted by generating alarm information, and whether the client is a fraud client or not is considered in a key mode, so that the number of the identity verification type problems of the client needs to be increased, and the fraud risk is prevented.
Further, step S01 is included before S1, and in the second-class account registration stage, specific sample text information is sent to the client; s02, obtaining a sample voiceprint model of the text information of the sample read by the client; and S03, receiving the text information and the sample voiceprint model, and inputting the text information and the corresponding sample voiceprint model into a pre-established mapping relation table.
Has the advantages that: aiming at the acquisition of the sample voiceprint model, the method implants the step into the second-class account registration stage, effectively utilizes the existing flow and improves the use experience of customers.
Further, the step S2 further includes a step S21 of processing the current voiceprint model according to a speech recognition algorithm to generate current text information; matching sample text information which is the same as the current text information and a corresponding sample voiceprint model from the mapping relation table according to a keyword matching algorithm; and if the sample voiceprint model is different from the current voiceprint model, generating first alarm information.
Has the advantages that: according to the scheme, any statement in the call is collected, and the same statement is positioned according to a keyword matching technology, so that a sample voiceprint model for comparison is obtained; the client does not need to read specific character information in the identity verification process, and the method is more humanized.
Further, the step S2 further includes a step S22, which extracts feature information of the current voiceprint model and the sample voiceprint model respectively, and determines whether the current voiceprint model and the sample voiceprint model are the same according to the feature information.
Has the advantages that: the frequency value of the formant and the trend of the waveform thereof are the most stable characteristics, and have strong specificity and highest utilization value; the comparison result is used as the target specificity of the comparison between the current voiceprint model and the sample voiceprint model, and an effective and accurate judgment result can be obtained.
Drawings
Fig. 1 is a system block diagram of a first embodiment of the identity verification system and method based on voiceprint recognition according to the present invention.
Detailed Description
The following is further detailed by the specific embodiments:
example one
The identity verification system based on voiceprint recognition comprises a client, a server and a background terminal, wherein the client is a Hua is a P40 mobile phone used by a client, the server adopts a PowerEdgeT30 micro-tower server of Darlian WeChat, and the background terminal is an all-in-one computer; as shown in fig. 1, the server includes an input module, a database, a processing module, and an output module, wherein: the input module is used for acquiring a current voiceprint model sent by a client in the call process; the database is used for pre-storing a sample voiceprint model of a client; the processing module is used for receiving the current voiceprint model, processing the current voiceprint model according to the sample voiceprint model, and generating first alarm information if the current voiceprint model is not matched with the sample voiceprint model; otherwise, generating verification passing prompt information; the output module is used for sending first warning information and verification passing prompt information to the background terminal; specifically, in this embodiment, for convenience of explanation, two testers (a client a and a client B) are selected, when the internet credit business is credited and audited, the auditor respectively performs voice communication with the client a and the client B to obtain two current voiceprint images about the client a and the client B, because the database stores the sample voiceprint image of the client a in advance (because "hello" is more common, a broadband spectrogram saying "hello" sound is selected in this embodiment, and in other embodiments, broadband spectrograms of other sounds can be selected), the client B intends to activate the credit business on the behalf of the client a, and intercepts the broadband spectrogram saying "hello" sound from the current voiceprint model of the client B for comparison, the sample waveform trend is in a descending shape, and the current voiceprint waveform trend is in a straight shape; then, a first warning message "the client failed voiceprint information verification, is suspected to be a fraudulent client, and is alerted! ", and display on the backstage terminal that the auditor uses, and increase the quantity to the identity verification type problem of the customer by the auditor, prevent the fraud risk; on the contrary, by acquiring the voiceprint image of the client A, intercepting the broadband spectrogram in which the 'hello' sound is said, and generating prompt information 'the voiceprint information of the client is successfully verified' according to the waveform trend of the prestored sample spectrogram, wherein the prompt information can reduce the questions of the identity verification problems or does not carry out the questions of the identity verification problems by auditors according to the prompt; by adopting the scheme, the efficiency of manual auditing can be improved, the time investment of identity verification is reduced, and the customer experience is improved.
In order to optimize the mode and the flow of sample data acquisition, the system can also send specific sample text information to the client in advance at the second-class account registration stage through the output module, so that the user can conveniently answer the call, and can directly say the bar and sorry, which can be a matter of me and can not make a call to me later; then, a sample voiceprint model of the sample text information read by the client is acquired through an input module; receiving the text information and the sample voiceprint model by the database, and inputting the text information and the corresponding sample voiceprint model into a pre-established mapping relation table; thus, during the phone check between the auditor and the customer, the auditor may ask "do i need to check specific questions with you here, ask you how convenient to answer the phone now? Acquiring a current voiceprint model of a client, processing the current voiceprint model of the client by a processing module according to a voice recognition algorithm to generate current character information, and matching sample character information which is the same as the current character information and a corresponding sample voiceprint model from a mapping relation table according to a keyword matching algorithm; specifically, the speech recognition algorithm adopts a science news communication speech recognition algorithm, and the keyword matching algorithm adopts a KMP algorithm, which are all the prior art and are not described herein again; intercepting a broadband spectrogram of 'yes' and 'convenient' sounds; respectively extracting the formant frequency and the waveform trend of the current voiceprint model and the sample voiceprint model, and judging whether the current voiceprint model is the same as the sample voiceprint model according to the formant frequency and the waveform trend; specifically, because the broadband spectrogram is similar to a oscillogram, each broadband spectrogram is input into the two-dimensional coordinate model by establishing a two-dimensional coordinate model (the horizontal axis represents time-s, and the vertical axis represents amplitude-Hz), so that the peak (extreme) point coordinate information appearing in the voiceprint, the connecting line of each extreme point reflects the waveform trend and the horizontal axis value (formant frequency value) of the broadband spectrogram, and if the waveform trend and the formant frequency value are the same, the situation is that the person is the same; if not, the description is not the same person.
The identity verification method based on voiceprint recognition is based on the system, and the embodiment specifically comprises the following steps:
s01, in the second-class account registration stage, sending specific sample text information to the client;
s02, obtaining a sample voiceprint model of the text information of the sample read by the client;
s03, receiving the text information and the sample voiceprint model, and inputting the text information and the corresponding sample voiceprint model into a pre-established mapping relation table;
s1, acquiring a current voiceprint model sent by the client in the call process;
s21, processing the current voiceprint model according to a voice recognition algorithm to generate current character information; matching sample text information which is the same as the current text information and a corresponding sample voiceprint model from the mapping relation table according to a keyword matching algorithm;
s22, respectively extracting the characteristic information of the current voiceprint model and the sample voiceprint model, judging whether the current voiceprint model and the sample voiceprint model are the same according to the characteristic information, and if so, generating verification passing prompt information; if the alarm information is different from the first alarm information, generating first alarm information;
and S3, sending the first alarm information and the verification passing prompt information to the background terminal.
Example two
Compared with the first embodiment, the difference is that the database is also used for storing the blacklist user voiceprint model; and the processing module is used for judging the current voiceprint model according to the blacklist voiceprint model and generating second alarm information if the current voiceprint model is the same as the blacklist voiceprint model. Specifically, as the client B is judged to maliciously use the identity of other people to apply for credit business, the voiceprint model of the client B is stored in the database to be used as a blacklist; the voice print model can be conveniently and directly identified and matched subsequently, and the obtained second alarm information is that the user is a blacklist user, suspected fraudulent client and vigilant! ", the auditor performs further identity verification and authentication.
EXAMPLE III
Compared with the first embodiment, the difference is that the input module is also used for acquiring short message data of the user side; the preprocessing module is also used for screening the short message data in the user side, extracting keyword information in the short message data, extracting the short message data of which the keywords comprise finance or credit, and generating a target to be verified; the processing module is also used for carrying out semantic analysis on the object to be checked, and when the result of the semantic analysis is a forward result, the result is recorded as a forward score; otherwise, recording as minus one; the output module is also used for receiving the standard scores prestored in the database, counting the scores according to the semantic analysis result and obtaining score information; if the score information is smaller than a first preset threshold value, the user is marked as a high-risk user, and user information is sent to a user terminal;
the scheme is intended to provide another means of identifying at risk users; that is, since the user usually fills in personal telephone data when performing financial loan activities, the related content of financial loan or repayment is also notified to the customer by short message. The preprocessing module screens the short messages received by the user side, specifically, the screening mode is to screen out the short messages with keywords related to finance or loan and the short messages of senders of financial institutions. In such a way, short messages related to the loan behaviors of the users can be screened out. Then, the user side carries out semantic analysis on the screened short messages, and records the result as a positive score when the result of the semantic analysis is a positive result (such as on-schedule payment, advance payment and the like); when the result of semantic analysis is a negative result (such as overdue payment), the record is negative one. And when the screening time exceeds the preset time, the user end carries out financial marking on the user. Specifically, the user side carries out score statistics, and when the statistical score is lower than a preset score, the user is marked as a problem user; otherwise, the user is marked as a normal user.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (10)
1. Identity verification system based on voiceprint recognition, including client, server and backstage terminal, its characterized in that, the server includes input module, database, processing module and output module, wherein: the input module is used for acquiring a current voiceprint model sent by a client in the call process; the database is used for pre-storing a sample voiceprint model of a client; the processing module is used for receiving the current voiceprint model, processing the current voiceprint model according to the sample voiceprint model, and generating first alarm information if the current voiceprint model is not matched with the sample voiceprint model; otherwise, generating verification passing prompt information; and the output module is used for sending the first alarm information and the verification passing prompt information to the background terminal.
2. The voiceprint recognition based identity verification system according to claim 1, wherein: the output module is also used for sending specific sample text information to the client side in the second-class account registration stage; the input module is also used for acquiring a sample voiceprint model of the text information of the sample read by the client; and the database is also used for receiving the text information and the sample voiceprint models and inputting the text information and the corresponding sample voiceprint models into a pre-established mapping relation table.
3. The voiceprint recognition based identity verification system according to claim 2, wherein: the processing module is also used for processing the current voiceprint model according to a voice recognition algorithm to generate current character information; matching sample text information which is the same as the current text information and a corresponding sample voiceprint model from the mapping relation table according to a keyword matching algorithm; and if the sample voiceprint model is different from the current voiceprint model, generating first alarm information.
4. The voiceprint recognition based identity verification system according to claim 3, wherein: the processing module is also used for respectively extracting the characteristic information of the current voiceprint model and the sample voiceprint model and judging whether the current voiceprint model and the sample voiceprint model are the same according to the characteristic information; the characteristic information comprises formant frequency and waveform trend.
5. The voiceprint recognition based identity verification system according to claim 3, wherein: the voice recognition algorithm adopts a science news communication voice recognition algorithm; the keyword matching algorithm adopts a KMP algorithm.
6. The voiceprint recognition based identity verification system according to claim 1, wherein: the database is also used for storing the voice print model of the blacklist user; and the processing module is also used for judging the current voiceprint model according to the blacklist voiceprint model and generating second alarm information if the current voiceprint model is the same as the blacklist voiceprint model.
7. The identity verification method based on voiceprint recognition is characterized by comprising the following steps of:
s1, acquiring a current voiceprint model sent by the client in the call process;
s2, receiving the current voiceprint model, processing the current voiceprint model according to the sample voiceprint model, and generating first alarm information if the current voiceprint model is not matched with the sample voiceprint model; otherwise, generating verification passing prompt information;
and S3, sending the first alarm information and the verification passing prompt information to the background terminal.
8. The voiceprint recognition based identity verification method according to claim 7, wherein: step S01 is included before S1, and specific sample text information is sent to the client side in the second type account registration stage; s02, obtaining a sample voiceprint model of the text information of the sample read by the client; and S03, receiving the text information and the sample voiceprint model, and inputting the text information and the corresponding sample voiceprint model into a pre-established mapping relation table.
9. The voiceprint recognition based identity verification method according to claim 7, wherein: the step S2 further comprises a step S21 of processing the current voiceprint model according to a speech recognition algorithm to generate current text information; matching sample text information which is the same as the current text information and a corresponding sample voiceprint model from the mapping relation table according to a keyword matching algorithm; and if the sample voiceprint model is different from the current voiceprint model, generating first alarm information.
10. The voiceprint recognition based identity verification method according to claim 9, wherein: the step S2 further includes a step S22 of extracting feature information of the current voiceprint model and the sample voiceprint model, respectively, and determining whether the current voiceprint model and the sample voiceprint model are the same according to the feature information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010759931.5A CN111833068A (en) | 2020-07-31 | 2020-07-31 | Identity verification system and method based on voiceprint recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010759931.5A CN111833068A (en) | 2020-07-31 | 2020-07-31 | Identity verification system and method based on voiceprint recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111833068A true CN111833068A (en) | 2020-10-27 |
Family
ID=72920759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010759931.5A Pending CN111833068A (en) | 2020-07-31 | 2020-07-31 | Identity verification system and method based on voiceprint recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111833068A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381512A (en) * | 2020-11-15 | 2021-02-19 | 周岳 | Verification system and verification method |
| CN113259373A (en) * | 2021-06-08 | 2021-08-13 | 支付宝(杭州)信息技术有限公司 | Resource transfer method, device and system and Internet of things equipment |
| CN114169995A (en) * | 2021-10-25 | 2022-03-11 | 中国农业银行股份有限公司福建省分行 | Method, system, equipment and medium for managing clients after credit based on voiceprint recognition technology |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104967593A (en) * | 2014-10-15 | 2015-10-07 | 腾讯科技（深圳）有限公司 | Identity verification method, apparatus and system |
| CN107221331A (en) * | 2017-06-05 | 2017-09-29 | 深圳市讯联智付网络有限公司 | A kind of personal identification method and equipment based on vocal print |
| CN107690036A (en) * | 2017-06-24 | 2018-02-13 | 平安科技（深圳）有限公司 | Electronic installation, inlet wire personal identification method and computer-readable recording medium |
| CN108133371A (en) * | 2017-06-23 | 2018-06-08 | 广东网金控股股份有限公司 | A kind of data processing method based on speech recognition, device and processing terminal |
| CN108768654A (en) * | 2018-04-09 | 2018-11-06 | 平安科技（深圳）有限公司 | Auth method, server based on Application on Voiceprint Recognition and storage medium |
| 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 |
| CN109036435A (en) * | 2018-08-15 | 2018-12-18 | 深圳平安综合金融服务有限公司上海分公司 | Authentication and recognition methods based on voiceprint |
| CN109243465A (en) * | 2018-12-06 | 2019-01-18 | 平安科技（深圳）有限公司 | Voiceprint authentication method, device, computer equipment and storage medium |
| CN109428719A (en) * | 2017-08-22 | 2019-03-05 | 阿里巴巴集团控股有限公司 | A kind of auth method, device and equipment |
| CN109450850A (en) * | 2018-09-26 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Auth method, device, computer equipment and storage medium |
| CN109473108A (en) * | 2018-12-15 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Auth method, device, equipment and storage medium based on Application on Voiceprint Recognition |
-
2020
- 2020-07-31 CN CN202010759931.5A patent/CN111833068A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104967593A (en) * | 2014-10-15 | 2015-10-07 | 腾讯科技（深圳）有限公司 | Identity verification method, apparatus and system |
| CN107221331A (en) * | 2017-06-05 | 2017-09-29 | 深圳市讯联智付网络有限公司 | A kind of personal identification method and equipment based on vocal print |
| CN108133371A (en) * | 2017-06-23 | 2018-06-08 | 广东网金控股股份有限公司 | A kind of data processing method based on speech recognition, device and processing terminal |
| CN107690036A (en) * | 2017-06-24 | 2018-02-13 | 平安科技（深圳）有限公司 | Electronic installation, inlet wire personal identification method and computer-readable recording medium |
| CN109428719A (en) * | 2017-08-22 | 2019-03-05 | 阿里巴巴集团控股有限公司 | A kind of auth method, device and equipment |
| CN108768654A (en) * | 2018-04-09 | 2018-11-06 | 平安科技（深圳）有限公司 | Auth method, server based on Application on Voiceprint Recognition and storage medium |
| 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 |
| CN109036435A (en) * | 2018-08-15 | 2018-12-18 | 深圳平安综合金融服务有限公司上海分公司 | Authentication and recognition methods based on voiceprint |
| CN109450850A (en) * | 2018-09-26 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Auth method, device, computer equipment and storage medium |
| CN109243465A (en) * | 2018-12-06 | 2019-01-18 | 平安科技（深圳）有限公司 | Voiceprint authentication method, device, computer equipment and storage medium |
| CN109473108A (en) * | 2018-12-15 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Auth method, device, equipment and storage medium based on Application on Voiceprint Recognition |
Non-Patent Citations (4)
| Title |
|---|
| 郑方等: "声纹识别技术及其应用现状", 《信息安全研究》 * |
| 郑方等: "声纹识别技术及其应用现状", 《信息安全研究》, no. 01, 5 January 2016 (2016-01-05), pages 44 - 57 * |
| 郑永红: "声纹识别技术的发展及应用策略", 《科技风》 * |
| 郑永红: "声纹识别技术的发展及应用策略", 《科技风》, no. 21, 15 November 2017 (2017-11-15), pages 9 - 10 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381512A (en) * | 2020-11-15 | 2021-02-19 | 周岳 | Verification system and verification method |
| CN113259373A (en) * | 2021-06-08 | 2021-08-13 | 支付宝(杭州)信息技术有限公司 | Resource transfer method, device and system and Internet of things equipment |
| CN114169995A (en) * | 2021-10-25 | 2022-03-11 | 中国农业银行股份有限公司福建省分行 | Method, system, equipment and medium for managing clients after credit based on voiceprint recognition technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10600055B2 (en) | Authentication and interaction tracking system and method | |
| CA2736133C (en) | Voice authentication system and methods | |
| US9240013B2 (en) | Evaluation of voice communications | |
| US8924285B2 (en) | Building whitelists comprising voiceprints not associated with fraud and screening calls using a combination of a whitelist and blacklist | |
| AU2006306790B2 (en) | System and method of subscription identity authentication utilizing multiple factors | |
| CN111833068A (en) | Identity verification system and method based on voiceprint recognition | |
| US9099085B2 (en) | Voice authentication systems and methods | |
| US20070174186A1 (en) | Authenticated and distributed transaction processing | |
| US20120284026A1 (en) | Speaker verification system | |
| CN111861732A (en) | Risk assessment system and method | |
| US20060202012A1 (en) | Secure data processing system, such as a system for detecting fraud and expediting note processing | |
| CN101311953A (en) | Network payment method and system based on voiceprint authentication | |
| CN111553701A (en) | Session-based risk transaction determination method and device | |
| CN107766868A (en) | A kind of classifier training method and device | |
| CN111401906A (en) | Transfer risk detection method and system | |
| CN113191787A (en) | Telecommunication data processing method, device electronic equipment and storage medium | |
| CN107563758A (en) | A kind of finance letter that solves examines the detection method and system that habitual offender swindles in business | |
| CN112348667A (en) | Intelligent account opening method and device based on virtual customer service | |
| CN107025558A (en) | A kind of transaction system and transaction processing method | |
| US11705134B2 (en) | Graph-based approach for voice authentication | |
| US20110044433A1 (en) | Method of generating a temporarily limited and/or usage limited means and/or status, method of obtaining a temporarily limited and/or usage limited means and/or status, corresponding system and computer readable medium | |
| AU2012200605B2 (en) | Voice authentication system and methods | |
| TW200521962A (en) | Voiceprint identification system for e-commerce | |
| CN118229405A (en) | Credit card issuing risk detection method and device | |
| CN114358790A (en) | Method and device for identifying object, computer readable storage medium and electronic equipment |
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: 20201027 |