WO2019196302A1 - Voiceprint recognition-based identity authentication method, server and storage medium - Google Patents
Voiceprint recognition-based identity authentication method, server and storage medium Download PDFInfo
- Publication number
- WO2019196302A1 WO2019196302A1 PCT/CN2018/102122 CN2018102122W WO2019196302A1 WO 2019196302 A1 WO2019196302 A1 WO 2019196302A1 CN 2018102122 W CN2018102122 W CN 2018102122W WO 2019196302 A1 WO2019196302 A1 WO 2019196302A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- verification
- answer
- type
- voiceprint
- user
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 129
- 238000012795 verification Methods 0.000 claims description 321
- 238000004422 calculation algorithm Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000013507 mapping Methods 0.000 claims description 8
- 230000004069 differentiation Effects 0.000 abstract 4
- 238000005516 engineering process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
- H04L9/3231—Biological data, e.g. fingerprint, voice or retina
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/08—Use of distortion metrics or a particular distance between probe pattern and reference templates
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/10—Multimodal systems, i.e. based on the integration of multiple recognition engines or fusion of expert 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
- G10L17/22—Interactive procedures; Man-machine interfaces
- G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3215—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a plurality of channels
Definitions
- the present application relates to the field of computer technologies, and in particular, to a voiceprint recognition based identity verification method, a server, and a computer readable storage medium.
- voiceprint verification technology to verify user identity has become an important means of authentication for major customer service companies (eg, banks, insurance companies, game companies, etc.).
- the traditional user authentication scheme using voiceprint recognition technology is: if the voiceprint verification is passed, it is determined that the identity verification is passed, or if the voiceprint verification fails, it is determined that the identity verification fails.
- the defect of this traditional voiceprint verification scheme is that the accuracy of voiceprint verification is greatly affected by the quality of voiceprint data, which may lead to incorrect identity verification results; it is susceptible to human voice intervention and sound hijacking during sound collection. It is impossible to accurately control the timeliness and authenticity of voiceprint verification, and safety cannot be guaranteed.
- the present application provides a voiceprint recognition-based identity verification method, a server, and a computer-readable storage medium, the main purpose of which is to comprehensively determine whether a user identity is verified by combining voiceprint recognition results and secondary verification results, thereby improving user identity.
- the accuracy of the verification is to comprehensively determine whether a user identity is verified by combining voiceprint recognition results and secondary verification results, thereby improving user identity.
- the present application provides a method for authenticating a voiceprint recognition based method, the method comprising:
- Receiving an identity verification request with a user identity sent by the first client collecting current voice data of the user from the first client, constructing a current voiceprint authentication vector for the current voice data, and determining the user according to the user identity identifier a standard voiceprint identification vector corresponding to the identity;
- Using a predetermined distance calculation formula calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client;
- the manual verification result is obtained from the second client
- the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result
- the present application further provides an identity verification server, where the server includes a memory and a processor, and the memory stores a voiceprint recognition-based identity verification program executable on the processor, where Any step of the voiceprint recognition based authentication method as described above is implemented when the program is executed by the processor.
- the present application further provides a computer readable storage medium having stored thereon a voiceprint recognition-based identity verification program, which is executed by a processor to implement the above Any step of the voiceprint recognition based authentication method.
- the voiceprint recognition based identity verification method, the server and the computer readable storage medium proposed by the present application use the voiceprint recognition technology to perform preliminary verification on the user identity, and then, according to the user's preset problem. Answer, the second verification of the user identity, combined with the preliminary verification results and the secondary verification results, comprehensively determine whether the user identity has passed the verification, improving the accuracy of the user identity verification.
- FIG. 1 is a schematic diagram of a preferred embodiment of a server of the present application.
- FIG. 2 is a schematic diagram of a program module of the voiceprint recognition-based identity verification program of FIG. 1;
- FIG. 3 is a flowchart of a preferred embodiment of a voiceprint recognition based identity verification method according to the present application.
- the application provides an identity verification server 1 based on voiceprint recognition.
- FIG. 1 a schematic diagram of a preferred embodiment of the identity verification server 1 of the present application is shown.
- the authentication server 1 may be a rack server, a blade server, a tower server, or a rack server.
- the authentication server 1 includes a memory 11, a processor 12, a communication bus 13, and a network interface 14.
- the memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like.
- the memory 11 may in some embodiments be an internal storage unit of the authentication server 1, such as the hard disk of the authentication server 1.
- the memory 11 may also be an external storage device of the authentication server 1 in other embodiments, such as a plug-in hard disk equipped with the smart card (SMC), a secure digital card (SMC). Secure Digital, SD) cards, flash cards, etc. Further, the memory 11 may also include both an internal storage unit of the authentication server 1 and an external storage device.
- the memory 11 can be used not only for storing application software and various types of data installed in the authentication server 1, such as the voiceprint recognition based authentication program 10, etc., but also for temporarily storing data that has been output or is to be output.
- the processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data processing chip for running program code or processing stored in the memory 11. Data, such as voiceprint recognition based authentication program 10, and the like.
- CPU Central Processing Unit
- controller microcontroller
- microprocessor or other data processing chip for running program code or processing stored in the memory 11.
- Data such as voiceprint recognition based authentication program 10, and the like.
- Communication bus 13 is used to implement connection communication between these components.
- the network interface 14 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and is generally used to establish a communication connection between the authentication server 1 and other electronic devices, and perform data transmission.
- the authentication server 1 receives the identity verification request sent by the first client (not identified in the figure) through the network interface 14, acquires voice data of the user collected by the first client, and the like; the identity verification server 1 also receives through the network interface. The verification result of the feedback from the second client (not identified in the figure).
- FIG. 1 shows only the authentication server 1 with components 11-14, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
- the authentication server 1 may further include a user interface, and the user interface may include a display, an input unit such as a keyboard, and the optional user interface may further include a standard wired interface and a wireless interface.
- the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an Organic Light-Emitting Diode (OLED) touch device.
- the display may also be referred to as a display screen or display unit for displaying information processed in the authentication server 1 and a user interface for displaying visualizations.
- a voiceprint recognition based authentication program 10 is stored in the memory 11.
- the processor 12 executes the voiceprint recognition based authentication program 10 stored in the memory 11, the following steps are implemented:
- Receiving an identity verification request with a user identity sent by the first client collecting current voice data of the user from the first client, constructing a current voiceprint authentication vector for the current voice data, and determining the user according to the user identity identifier a standard voiceprint identification vector corresponding to the identity;
- Using a predetermined distance calculation formula calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client;
- the manual verification result is obtained from the second client
- the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result
- the first client is a terminal used by the user
- the second client is a terminal used by the customer service personnel
- the terminal may be a mobile terminal or a desktop computer having a sound collection function.
- the first client collects the current voice data of the user for collecting.
- the current voice data constructs the current voiceprint discriminant vector, and the voiceprint discriminant vector is constructed according to the voice data, which is a well-known technique in the art, and will not be described herein.
- the corresponding standard voiceprint identification vector needs to be set in advance for the predetermined user identity to obtain a predetermined user identity.
- the standard voiceprint identification vector corresponding to the user identity is determined, and the current voiceprint identification is calculated by using a predetermined distance calculation formula.
- the distance between the vector and the determined standard voiceprint discrimination vector is:
- the voiceprint verification process even if the user identity corresponds to the current voiceprint authentication vector, if the current voice data is interfered by human or environment, the voice data quality is poor, and the identity verification result may be in error.
- a manual verification request is sent to the second client, and then the customer service personnel sends a preset to the first client through the second client.
- the authentication problem for example, the ID number, the name, the student number, etc., determines whether the manual verification is passed by judging whether the user's answer is consistent with the preset answer, and feeds the manual verification result to the identity verification server through the second client. .
- the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is that the manual verification fails, the user identity verification fails; when the voiceprint verification result is that the voiceprint verification is passed, and the manual verification result is manually verified, then Determine the user authentication passed.
- the user authentication result is determined by two-factor verification, and the accuracy of the authentication is improved.
- the predetermined analysis algorithm includes: if the problem of performing manual authentication on the user is that the answer is the first type of question of the first type of answer, the user is targeted to the first type of question according to the predetermined first analysis rule.
- the first type of answer is analyzed and the result of the verification analysis is output, wherein the first type of answer refers to an answer whose content is a number, for example, a date of birth, an ID number, etc.; or, if the question of manual authentication of the user is the answer is a second type of question of the second type of answer, analyzing a second type of answer of the user for the second type of question according to a predetermined second analysis rule, and outputting a verification analysis result, wherein the second type of answer means that the content is a Chinese character
- the answer for example, the name of the high school language teacher, the name of the first grade junior college counselor.
- the step of analyzing the first type of answer of the first type problem by the user according to the predetermined first analysis rule comprises: acquiring a first type of answer input by the user for the first type of question; Comparing the first type of answer with the standard answer, identifying the difference part, and determining the difference value of each preset difference type of the difference part; according to the mapping relationship between the preset preset difference type and the preset difference threshold, The difference value of each preset difference type of the difference part is compared with the corresponding preset difference threshold value, and the verification analysis result is output.
- the preset difference type includes a difference portion number, an error number of bits, an interval difference degree, and an interval matching degree.
- the first answer entered by the user is 123456789
- the standard answer is 331456789.
- the difference between the two is "123" and "331”.
- the difference between the two numbers is 1, and the number of errors in the difference is 3, the difference part does not appear outside the difference part of the number, the difference between the two numbers is 0, the difference between the two numbers can not be restored by adjusting the number of bits, the interval matching of the two numbers For infinity.
- the difference between 123456789 and 331456971 is "123" and "331", "789", and "971", and the number of difference portions between the two numbers is 2.
- the difference between 123456789 and 341456789 is “123” and “341", and the difference portion has a number "4" other than the difference portion, and the difference between the two numbers is 1.
- the difference between 123456789 and 231456789 is "123" and "231”.
- the difference between the two numbers can be restored by adjusting the number of digits.
- the number "1" in “231” can be adjusted forward 2
- the order is restored to match "123", then the interval matching of the two numbers is 2.
- the difference value of the preset difference type After determining the difference value of the preset difference type between the answer input by the user and the standard answer, respectively, determining whether the difference value of each preset difference type is less than or equal to the corresponding preset difference threshold, if all the preset difference types are The difference value is less than or equal to the corresponding preset difference threshold, and the verification analysis is determined to pass; if the difference value of the preset difference type is greater than the corresponding difference threshold, it is determined that the verification analysis fails.
- the user-generated data is 123456789 and the standard answer is 331456789.
- the difference between the two is "123" and "331".
- the difference between the difference portion, the number of errors, the interval difference, and the interval matching degree are four.
- the difference values of the preset types are: 1, 3, 0, ⁇ , assuming that the preset difference thresholds corresponding to the difference values of the four preset types are: 1, 1, 0, 1, respectively, and all presets are not satisfied.
- the difference value of the difference type is less than or equal to the condition of the corresponding difference threshold. Therefore, it is determined that the verification analysis fails.
- the step of analyzing a second type of answer of the user for the second type of question according to the predetermined second analysis rule comprises:
- the answer string is compared and analyzed to generate a corresponding second type of answer difference value; if the generated second type of answer difference value is greater than the preset answer difference value threshold, it is determined that the verification analysis fails, or if the generated second type of answer is generated If the difference value is less than or equal to the preset answer difference value threshold, it is determined that the verification analysis is passed.
- the predetermined second type of answer difference value analysis algorithm includes: splitting the converted string word by word, recombining to generate a user second type answer word package; and recombining the generated user second type
- the answer word package is matched with the predetermined standard answer word package to generate a corresponding letter matching set value; the set difference value between the generated letter matching set value and the standard set value is calculated according to a predetermined calculation formula, and The set difference value is used as the second type of answer difference value.
- the second type of answer input by the user is 'Xiao Ming'
- the two answers are respectively converted into strings: 'xiaoming' and 'xiaoqiang'
- the result of word-by-word splitting is "'x','i','a','o','m','i','n','g'" and ''x','i','a','o' , 'q', 'i', 'a', 'n', 'g'
- the generated user type 2 answer package can be counted as ⁇ 'x', 'i', 'a', 'o' ⁇ , ⁇ 'm','i','n','g' ⁇
- the standard answer word package can be counted as ⁇ 'x', 'i', 'a', 'o' ⁇ , ⁇ 'q', 'i',
- a set difference value between the set of difference values is the second type of answer difference value.
- the predetermined calculation formula may be a cosine formula, an Euclidean distance calculation formula, or the like.
- the verification analysis result is passed by the verification analysis, that is, the user identity verification is determined; otherwise, the verification analysis result is determined as the verification analysis failure, that is, the user identity is determined. verification failed.
- the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is manually verified
- one or more questions are selected from the additional questions predetermined by the user, to the first client. Raising the question, for example, the name of the best friend of junior high school, and obtaining the user's additional answer to the additional question from the first client; comparing the obtained additional answer with the predetermined standard additional answer; The additional answer (for example, Zhang San) is consistent with the predetermined standard additional answer (for example, Zhang San), then the user's identity verification is passed; if the additional answer obtained (for example, Zhang San) and the predetermined standard additional answer ( For example, if Li Si) is inconsistent, it is judged that the user authentication failed.
- the identity verification server 1 proposed by the foregoing embodiment uses the voiceprint recognition technology to perform preliminary verification on the user identity, and then, according to the user's response to the preset question, performs secondary verification on the user identity, combined with the preliminary verification result and the secondary verification. As a result, comprehensively determining whether the user identity passes the verification improves the accuracy of the user identity verification.
- the voiceprint recognition based authentication program 10 may also be partitioned into one or more modules, one or more modules being stored in the memory 11 and processed by one or more
- the present invention is implemented by the processor (this embodiment is the processor 12) to accomplish the present application.
- module refers to a series of computer program instructions that are capable of performing a particular function.
- FIG. 2 it is a schematic diagram of a program module of the voiceprint recognition-based identity verification program 10 in FIG. 1.
- the voiceprint recognition-based identity verification program 10 can be divided into a vector acquisition module 110, and a sound.
- the pattern verification module 120, the manual verification module 130, the secondary analysis module 140, and the identity verification module 150, the functions or operation steps implemented by the modules 110-150 are similar to the above, and are not described in detail herein, exemplarily , for example:
- the vector acquisition module 110 is configured to receive an identity verification request with a user identity sent by the first client, collect current voice data of the user from the first client, and construct a current voiceprint identification vector for the current voice data, according to The user identity identifies a standard voiceprint identification vector corresponding to the user identity identifier;
- the voiceprint verification module 120 is configured to calculate a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector by using a predetermined distance calculation formula, analyze whether the voiceprint verification is performed according to the calculated distance, and generate a voiceprint verification result. Sent to the first client;
- the manual verification module 130 is configured to obtain a manual verification result from the second client when the voiceprint verification result is that the voiceprint verification is passed;
- the secondary analysis module 140 is configured to analyze the user identity again according to a predetermined analysis algorithm when the manual verification result is a manual verification failure, and generate a verification analysis result;
- the authentication module 150 is configured to determine that the user identity verification is passed when the verification analysis result is passed by the verification analysis, or to determine that the user identity verification fails when the verification analysis result is that the verification analysis fails.
- the present application also provides an identity verification method based on voiceprint recognition.
- FIG. 3 it is a flowchart of a preferred embodiment of the voiceprint recognition based identity verification method of the present application. The method can be performed by a device that can be implemented by software and/or hardware.
- the voiceprint recognition based identity verification method includes steps S1-S5:
- Step S1 Receive an identity verification request with a user identity sent by the first client, collect current voice data of the user from the first client, and construct a current voiceprint authentication vector for the current voice data, and determine according to the user identity identifier. a standard voiceprint identification vector corresponding to the user identity;
- Step S2 using a predetermined distance calculation formula, calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client end;
- Step S3 when the voiceprint verification result is that the voiceprint verification is passed, the manual verification result is obtained from the second client;
- Step S4 when the manual verification result is a manual verification failure, the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result;
- step S5 when the verification analysis result is that the verification analysis passes, it is determined that the user identity verification is passed, or when the verification analysis result is that the verification analysis fails, it is determined that the user identity verification fails.
- the first client is a terminal used by the user
- the second client is a terminal used by the customer service personnel
- the terminal may be a mobile terminal or a desktop computer having a sound collection function.
- the first client collects the current voice data of the user for collecting.
- the current voice data constructs the current voiceprint discriminant vector, and the voiceprint discriminant vector is constructed according to the voice data, which is a well-known technique in the art, and will not be described herein.
- the corresponding standard voiceprint identification vector needs to be set in advance for the predetermined user identity to obtain a predetermined user identity.
- the standard voiceprint identification vector corresponding to the user identity is determined, and the current voiceprint identification is calculated by using a predetermined distance calculation formula.
- the distance between the vector and the determined standard voiceprint discrimination vector is:
- the voiceprint verification process even if the user identity corresponds to the current voiceprint authentication vector, if the current voice data is interfered by human or environment, the voice data quality is poor, and the identity verification result may be in error.
- a manual verification request is sent to the second client, and then the customer service personnel sends a preset to the first client through the second client.
- the authentication problem for example, the ID number, the name, the student number, etc., determines whether the manual verification is passed by judging whether the user's answer is consistent with the preset answer, and feeds the manual verification result to the identity verification server through the second client. .
- the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is that the manual verification fails, the user identity verification fails; when the voiceprint verification result is that the voiceprint verification is passed, and the manual verification result is manually verified, then Determine the user authentication passed.
- the user authentication result is determined by two-factor verification, and the accuracy of the authentication is improved.
- the predetermined analysis algorithm includes: if the problem of performing manual authentication on the user is that the answer is the first type of question of the first type of answer, the user is targeted to the first type of question according to the predetermined first analysis rule.
- the first type of answer is analyzed and the result of the verification analysis is output, wherein the first type of answer refers to an answer whose content is a number, for example, a date of birth, an ID number, etc.; or, if the question of manual authentication of the user is the answer is a second type of question of the second type of answer, analyzing a second type of answer of the user for the second type of question according to a predetermined second analysis rule, and outputting a verification analysis result, wherein the second type of answer means that the content is a Chinese character
- the answer for example, the name of the high school language teacher, the name of the first grade junior college counselor.
- the step of analyzing the first type of answer of the first type problem by the user according to the predetermined first analysis rule comprises: acquiring a first type of answer input by the user for the first type of question; Comparing the first type of answer with the standard answer, identifying the difference part, and determining the difference value of each preset difference type of the difference part; according to the mapping relationship between the preset preset difference type and the preset difference threshold, The difference value of each preset difference type of the difference part is compared with the corresponding preset difference threshold value, and the verification analysis result is output.
- the preset difference type includes a difference portion number, an error number of bits, an interval difference degree, and an interval matching degree.
- the first answer entered by the user is 123456789
- the standard answer is 331456789.
- the difference between the two is "123" and "331”.
- the difference between the two numbers is 1, and the number of errors in the difference is 3, the difference part does not appear outside the difference part of the number, the difference between the two numbers is 0, the difference between the two numbers can not be restored by adjusting the number of bits, the interval matching of the two numbers For infinity.
- the difference between 123456789 and 331456971 is "123" and "331", "789", and "971", and the number of difference portions between the two numbers is 2.
- the difference between 123456789 and 341456789 is “123” and “341", and the difference portion has a number "4" other than the difference portion, and the difference between the two numbers is 1.
- the difference between 123456789 and 231456789 is "123" and "231”.
- the difference between the two numbers can be restored by adjusting the number of digits.
- the number "1" in “231” can be adjusted forward 2
- the order is restored to match "123", then the interval matching of the two numbers is 2.
- the difference value of the preset difference type After determining the difference value of the preset difference type between the answer input by the user and the standard answer, respectively, determining whether the difference value of each preset difference type is less than or equal to the corresponding preset difference threshold, if all the preset difference types are The difference value is less than or equal to the corresponding preset difference threshold, and the verification analysis is determined to pass; if the difference value of the preset difference type is greater than the corresponding difference threshold, it is determined that the verification analysis fails.
- the user-generated data is 123456789 and the standard answer is 331456789.
- the difference between the two is "123" and "331".
- the difference between the difference, the number of errors, the interval difference, and the interval matching degree are four.
- the difference values of the preset types are: 1, 3, 0, ⁇ , assuming that the preset difference thresholds corresponding to the difference values of the four preset types are: 1, 1, 0, 1, respectively, and all presets are not satisfied.
- the difference value of the difference type is less than or equal to the condition of the corresponding difference threshold. Therefore, it is determined that the verification analysis fails.
- the step of analyzing a second type of answer of the user for the second type of question according to the predetermined second analysis rule comprises:
- the answer string is compared and analyzed to generate a corresponding second type of answer difference value; if the generated second type of answer difference value is greater than the preset answer difference value threshold, it is determined that the verification analysis fails, or if the generated second type of answer is generated If the difference value is less than or equal to the preset answer difference value threshold, it is determined that the verification analysis is passed.
- the predetermined second type of answer difference value analysis algorithm includes: splitting the converted string word by word, recombining to generate a user second type answer word package; and recombining the generated user second type
- the answer word package is matched with the predetermined standard answer word package to generate a corresponding letter matching set value; the set difference value between the generated letter matching set value and the standard set value is calculated according to a predetermined calculation formula, and The set difference value is used as the second type of answer difference value.
- the second type of answer input by the user is 'Xiao Ming'
- the two answers are respectively converted into strings: 'xiaoming' and 'xiaoqiang'
- the result of word-by-word splitting is "'x','i','a','o','m','i','n','g'" and ''x','i','a','o' , 'q', 'i', 'a', 'n', 'g'
- the generated user type 2 answer package can be counted as ⁇ 'x', 'i', 'a', 'o' ⁇ , ⁇ 'm','i','n','g' ⁇
- the standard answer word package can be counted as ⁇ 'x', 'i', 'a', 'o' ⁇ , ⁇ 'q', 'i',
- a set difference value between the set of difference values is the second type of answer difference value.
- the predetermined calculation formula may be a cosine formula, an Euclidean distance calculation formula, or the like.
- the verification analysis result is passed by the verification analysis, that is, the user identity verification is determined; otherwise, the verification analysis result is determined as the verification analysis failure, that is, the user identity is determined. verification failed.
- the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is manually verified
- one or more questions are selected from the additional questions predetermined by the user, to the first client. Raising the question, for example, the name of the best friend of junior high school, and obtaining the user's additional answer to the additional question from the first client; comparing the obtained additional answer with the predetermined standard additional answer; The additional answer (for example, Zhang San) is consistent with the predetermined standard additional answer (for example, Zhang San), then the user's identity verification is passed; if the additional answer obtained (for example, Zhang San) and the predetermined standard additional answer ( For example, if Li Si) is inconsistent, it is judged that the user authentication failed.
- the voiceprint recognition-based identity verification method proposed in the above embodiment uses the voiceprint recognition technology to perform preliminary verification on the user identity, and then, according to the user's response to the preset question, performs secondary verification on the user identity, combined with the preliminary verification result. And the results of the second verification, comprehensively determine whether the user identity has passed the verification, and improve the accuracy of the user identity verification.
- the embodiment of the present application further provides a computer readable storage medium, where the voiceprint recognition based identity verification program 10 is stored, and when the program is executed by the processor, the following operations are implemented:
- Receiving an identity verification request with a user identity sent by the first client collecting current voice data of the user from the first client, constructing a current voiceprint authentication vector for the current voice data, and determining the user according to the user identity identifier a standard voiceprint identification vector corresponding to the identity;
- Using a predetermined distance calculation formula calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client;
- the manual verification result is obtained from the second client
- the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result
- the specific embodiment of the computer readable storage medium of the present application is substantially the same as the embodiments of the voiceprint recognition based authentication method described above, and will not be described herein.
- the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM as described above). , a disk, an optical disk, including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the various embodiments of the present application.
- a terminal device which may be a mobile phone, a computer, a server, or a network device, etc.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Telephonic Communication Services (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Provided in the present application are a voiceprint recognition-based identity authentication method, the method comprising: collecting current voice data of a user, constructing a current voiceprint differentiation vector, and determining a corresponding standard voiceprint differentiation vector; calculating the distance between the current voiceprint differentiation vector and the standard voiceprint differentiation vector, and analyzing whether voiceprint authentication is successful; when the voiceprint authentication is successful, acquiring a manual authentication result; when manual authentication fails, analyzing the identity of the user again, and generating an authentication analysis result; and when the authentication analysis is successful, determining that the identity authentication of the user is successful, or, when the authentication analysis fails, determining that the identity authentication of the user fails. Further provided in the present application are an identity authentication server and a computer-readable storage medium. According to the present application, whether the identity of a user passes authentication is determined comprehensively by combining a voiceprint recognition result and a secondary authentication result, thereby improving the accuracy of the identity authentication of a user.
Description
本申请基于巴黎公约申明享有2018年4月9日递交的申请号为CN 2018103110872、名称为“基于声纹识别的身份验证方法、服务器及存储介质”的中国专利申请的优先权,该中国专利申请的整体内容以参考的方式结合在本申请中。The present application is based on the priority of a Chinese patent application filed on April 9, 2018, with the application number CN 2018103110872, entitled "Voice Recognition Based Identification Method, Server and Storage Medium", which is filed on April 9, 2018. The overall content is incorporated herein by reference.
本申请涉及计算机技术领域,尤其涉及一种基于声纹识别的身份验证方法、服务器及计算机可读存储介质。The present application relates to the field of computer technologies, and in particular, to a voiceprint recognition based identity verification method, a server, and a computer readable storage medium.
目前,随着声纹识别技术的不断发展,利用声纹验证技术实现用户身份的验证,已经成为各大客户服务公司(例如,银行、保险公司、游戏公司等)的重要鉴权手段。At present, with the continuous development of voiceprint recognition technology, the use of voiceprint verification technology to verify user identity has become an important means of authentication for major customer service companies (eg, banks, insurance companies, game companies, etc.).
传统的利用声纹识别技术实现用户身份验证方案是:若声纹验证通过,即判定身份验证通过,或者,若声纹验证不通过,即判定身份验证不通过。The traditional user authentication scheme using voiceprint recognition technology is: if the voiceprint verification is passed, it is determined that the identity verification is passed, or if the voiceprint verification fails, it is determined that the identity verification fails.
然后,这种传统的声纹验证方案的缺陷在于:声纹验证的准确性受到声纹数据质量好坏影响过大,容易导致身份验证结果错误;在声音采集时容易受到人为声音干预和声音劫持,无法对声纹验证时效和真实性做到精确的控制,安全性得不到保证。Then, the defect of this traditional voiceprint verification scheme is that the accuracy of voiceprint verification is greatly affected by the quality of voiceprint data, which may lead to incorrect identity verification results; it is susceptible to human voice intervention and sound hijacking during sound collection. It is impossible to accurately control the timeliness and authenticity of voiceprint verification, and safety cannot be guaranteed.
发明内容Summary of the invention
本申请提供一种基于声纹识别的身份验证方法、服务器及计算机可读存储介质,其主要目的在于通过结合声纹识别结果及二次验证结果,综合判断用户身份是否通过验证,提高了用户身份验证的准确性。The present application provides a voiceprint recognition-based identity verification method, a server, and a computer-readable storage medium, the main purpose of which is to comprehensively determine whether a user identity is verified by combining voiceprint recognition results and secondary verification results, thereby improving user identity. The accuracy of the verification.
为实现上述目的,本申请提供一种基于声纹识别的身份验证方法,该方法包括:To achieve the above objective, the present application provides a method for authenticating a voiceprint recognition based method, the method comprising:
接收第一客户端发送的带有用户身份标识的身份验证请求,从第一客户端采集用户的当前语音数据,为所述当前语音数据构建当前声纹鉴别向量, 根据用户身份标识确定所述用户身份标识对应的标准声纹鉴别向量;Receiving an identity verification request with a user identity sent by the first client, collecting current voice data of the user from the first client, constructing a current voiceprint authentication vector for the current voice data, and determining the user according to the user identity identifier a standard voiceprint identification vector corresponding to the identity;
利用预先确定的距离计算公式,计算当前声纹鉴别向量与标准声纹鉴别向量之间的距离,根据计算的距离分析是否通过声纹验证,并生成声纹验证结果发送给第一客户端;Using a predetermined distance calculation formula, calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client;
当声纹验证结果为声纹验证通过时,从第二客户端获取人工验证结果;When the voiceprint verification result is that the voiceprint verification is passed, the manual verification result is obtained from the second client;
当人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分析结果;及When the manual verification result is a manual verification failure, the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result;
当验证分析结果为验证分析通过时,判断用户身份验证通过,或者,当验证分析结果为验证分析失败时,判断用户身份验证失败。When the verification analysis result is that the verification analysis passes, it is judged that the user identity verification is passed, or when the verification analysis result is that the verification analysis fails, it is judged that the user identity verification fails.
此外,为实现上述目的,本申请还提供一种身份验证服务器,该服务器包括存储器、处理器,所述存储器上存储有可在所述处理器上运行的基于声纹识别的身份验证程序,该程序被处理器执行时实现如上所述的基于声纹识别的身份验证方法的任意步骤。In addition, in order to achieve the above object, the present application further provides an identity verification server, where the server includes a memory and a processor, and the memory stores a voiceprint recognition-based identity verification program executable on the processor, where Any step of the voiceprint recognition based authentication method as described above is implemented when the program is executed by the processor.
此外,为实现上述目的,本申请还提供一种计算机可读存储介质,所述计算机可读存储介质上存储有基于声纹识别的身份验证程序,该程序被处理器执行时实现如上所述的基于声纹识别的身份验证方法的任意步骤。In addition, in order to achieve the above object, the present application further provides a computer readable storage medium having stored thereon a voiceprint recognition-based identity verification program, which is executed by a processor to implement the above Any step of the voiceprint recognition based authentication method.
相较于现有技术,本申请提出的基于声纹识别的身份验证方法、服务器及计算机可读存储介质,利用声纹识别技术,对用户身份进行初步验证,然后,根据用户针对预设问题的回答,对用户身份进行二次验证,结合初步验证结果及二次验证结果,综合判断用户身份是否通过验证,提高了用户身份验证的准确性。Compared with the prior art, the voiceprint recognition based identity verification method, the server and the computer readable storage medium proposed by the present application use the voiceprint recognition technology to perform preliminary verification on the user identity, and then, according to the user's preset problem. Answer, the second verification of the user identity, combined with the preliminary verification results and the secondary verification results, comprehensively determine whether the user identity has passed the verification, improving the accuracy of the user identity verification.
图1为本申请服务器较佳实施例的示意图;1 is a schematic diagram of a preferred embodiment of a server of the present application;
图2为图1中基于声纹识别的身份验证程序的程序模块示意图;2 is a schematic diagram of a program module of the voiceprint recognition-based identity verification program of FIG. 1;
图3为本申请基于声纹识别的身份验证方法较佳实施例的流程图。FIG. 3 is a flowchart of a preferred embodiment of a voiceprint recognition based identity verification method according to the present application.
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步 说明。The implementation, functional features, and advantages of the present application will be further described with reference to the accompanying drawings.
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.
本申请提供一种基于声纹识别的身份验证服务器1。参照图1所示,为本申请身份验证服务器1较佳实施例的示意图。The application provides an identity verification server 1 based on voiceprint recognition. Referring to FIG. 1, a schematic diagram of a preferred embodiment of the identity verification server 1 of the present application is shown.
在本实施例中,身份验证服务器1可以是机架式服务器、刀片式服务器、塔式服务器或机柜式服务器。In this embodiment, the authentication server 1 may be a rack server, a blade server, a tower server, or a rack server.
该身份验证服务器1包括存储器11、处理器12,通信总线13,以及网络接口14。The authentication server 1 includes a memory 11, a processor 12, a communication bus 13, and a network interface 14.
其中,存储器11至少包括一种类型的可读存储介质,所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如,SD或DX存储器等)、磁性存储器、磁盘、光盘等。存储器11在一些实施例中可以是所述身份验证服务器1的内部存储单元,例如该身份验证服务器1的硬盘。存储器11在另一些实施例中也可以是所述身份验证服务器1的外部存储设备,例如该身份验证服务器1上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,存储器11还可以既包括该身份验证服务器1的内部存储单元也包括外部存储设备。存储器11不仅可以用于存储安装于该身份验证服务器1的应用软件及各类数据,例如基于声纹识别的身份验证程序10、等,还可以用于暂时地存储已经输出或者将要输出的数据。The memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 11 may in some embodiments be an internal storage unit of the authentication server 1, such as the hard disk of the authentication server 1. The memory 11 may also be an external storage device of the authentication server 1 in other embodiments, such as a plug-in hard disk equipped with the smart card (SMC), a secure digital card (SMC). Secure Digital, SD) cards, flash cards, etc. Further, the memory 11 may also include both an internal storage unit of the authentication server 1 and an external storage device. The memory 11 can be used not only for storing application software and various types of data installed in the authentication server 1, such as the voiceprint recognition based authentication program 10, etc., but also for temporarily storing data that has been output or is to be output.
处理器12在一些实施例中可以是一中央处理器(Central Processing Unit,CPU)、控制器、微控制器、微处理器或其他数据处理芯片,用于运行存储器11中存储的程序代码或处理数据,例如基于声纹识别的身份验证程序10等。The processor 12, in some embodiments, may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data processing chip for running program code or processing stored in the memory 11. Data, such as voiceprint recognition based authentication program 10, and the like.
通信总线13用于实现这些组件之间的连接通信。 Communication bus 13 is used to implement connection communication between these components.
网络接口14可选的可以包括标准的有线接口、无线接口(如WI-FI接口),通常用于在该身份验证服务器1与其他电子设备之间建立通信连接,并进行数据传输。例如,身份验证服务器1通过网络接口14接收第一客户端(图中未标识)发送的身份验证请求,获取第一客户端采集到的用户的语音数据等; 身份验证服务器1还通过网络接口接收第二客户端(图中未标识)反馈的验证结果等。The network interface 14 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and is generally used to establish a communication connection between the authentication server 1 and other electronic devices, and perform data transmission. For example, the authentication server 1 receives the identity verification request sent by the first client (not identified in the figure) through the network interface 14, acquires voice data of the user collected by the first client, and the like; the identity verification server 1 also receives through the network interface. The verification result of the feedback from the second client (not identified in the figure).
图1仅示出了具有组件11-14的身份验证服务器1,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。Figure 1 shows only the authentication server 1 with components 11-14, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
可选地,该身份验证服务器1还可以包括用户接口,用户接口可以包括显示器(Display)、输入单元比如键盘(Keyboard),可选的用户接口还可以包括标准的有线接口、无线接口。Optionally, the authentication server 1 may further include a user interface, and the user interface may include a display, an input unit such as a keyboard, and the optional user interface may further include a standard wired interface and a wireless interface.
可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及有机发光二极管(Organic Light-Emitting Diode,OLED)触摸器等。其中,显示器也可以称为显示屏或显示单元,用于显示在身份验证服务器1中处理的信息以及用于显示可视化的用户界面。Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an Organic Light-Emitting Diode (OLED) touch device. The display may also be referred to as a display screen or display unit for displaying information processed in the authentication server 1 and a user interface for displaying visualizations.
在图1所示的实施例中,存储器11中存储有基于声纹识别的身份验证程序10。处理器12执行存储器11中存储的基于声纹识别的身份验证程序10时实现如下步骤:In the embodiment shown in FIG. 1, a voiceprint recognition based authentication program 10 is stored in the memory 11. When the processor 12 executes the voiceprint recognition based authentication program 10 stored in the memory 11, the following steps are implemented:
接收第一客户端发送的带有用户身份标识的身份验证请求,从第一客户端采集用户的当前语音数据,为所述当前语音数据构建当前声纹鉴别向量,根据用户身份标识确定所述用户身份标识对应的标准声纹鉴别向量;Receiving an identity verification request with a user identity sent by the first client, collecting current voice data of the user from the first client, constructing a current voiceprint authentication vector for the current voice data, and determining the user according to the user identity identifier a standard voiceprint identification vector corresponding to the identity;
利用预先确定的距离计算公式,计算当前声纹鉴别向量与标准声纹鉴别向量之间的距离,根据计算的距离分析是否通过声纹验证,并生成声纹验证结果发送给第一客户端;Using a predetermined distance calculation formula, calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client;
当声纹验证结果为声纹验证通过时,从第二客户端获取人工验证结果;When the voiceprint verification result is that the voiceprint verification is passed, the manual verification result is obtained from the second client;
当人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分析结果;及When the manual verification result is a manual verification failure, the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result;
当验证分析结果为验证分析通过时,判断用户身份验证通过,或者,当验证分析结果为验证分析失败时,判断用户身份验证失败。When the verification analysis result is that the verification analysis passes, it is judged that the user identity verification is passed, or when the verification analysis result is that the verification analysis fails, it is judged that the user identity verification fails.
在本实施例中,第一客户端为用户使用的终端,第二客户端为客服人员使用的终端,且终端可以为具有声音采集功能的移动终端或台式计算机等。当需要对用户身份进行审核时,接收第一客户端发送来的带有用户身份标识(例如,身份证号)的身份验证请求后,利用第一客户端采集用户的当前语 音数据,为采集的当前语音数据构建出当前声纹鉴别向量,鉴于语音数据构建声纹鉴别向量为本领域人员习知的技术,在此不作赘述。可以理解的是,为了确定当前声纹鉴别向量是否与第一用户端发送来的身份标识相对应,需预先为预先确定的用户身份标识设置对应的标准声纹鉴别向量,得到预先确定的用户身份标识与标准声纹鉴别向量的映射关系。In this embodiment, the first client is a terminal used by the user, the second client is a terminal used by the customer service personnel, and the terminal may be a mobile terminal or a desktop computer having a sound collection function. When the user identity needs to be audited, after receiving the identity verification request sent by the first client with the user identity (for example, the ID number), the first client collects the current voice data of the user for collecting. The current voice data constructs the current voiceprint discriminant vector, and the voiceprint discriminant vector is constructed according to the voice data, which is a well-known technique in the art, and will not be described herein. It can be understood that, in order to determine whether the current voiceprint authentication vector corresponds to the identity sent by the first user, the corresponding standard voiceprint identification vector needs to be set in advance for the predetermined user identity to obtain a predetermined user identity. The mapping relationship between the logo and the standard voiceprint discrimination vector.
然后,根据身份验证请求中的用户身份标识,以及用户身份标识与标准声纹鉴别向量的映射关系,确定用户身份标识对应的标准声纹鉴别向量,利用预先确定的距离计算公式计算当前声纹鉴别向量与确定的标准声纹鉴别向量之间的距离。具体地,预先确定的距离计算公式为:Then, according to the user identity in the identity verification request, and the mapping relationship between the user identity and the standard voiceprint authentication vector, the standard voiceprint identification vector corresponding to the user identity is determined, and the current voiceprint identification is calculated by using a predetermined distance calculation formula. The distance between the vector and the determined standard voiceprint discrimination vector. Specifically, the predetermined distance calculation formula is:
其中,
代表标准声纹鉴别向量,
代表当前声纹鉴别向量。
among them, Represents the standard voiceprint discrimination vector, Represents the current voiceprint discrimination vector.
当计算的距离小于或者等于预设的距离阈值时,确定通过验证,否则,确定验证失败。When the calculated distance is less than or equal to the preset distance threshold, it is determined to pass the verification, otherwise, the verification fails.
需要说明的是,声纹验证过程中,即使用户身份标识与当前声纹鉴别向量对应,如果当前语音数据因受人为或环境干扰,导致语音数据质量较差,也会出现身份验证结果出错的情况,为了保证用户身份验证的准确性,即使声纹验证结果为声纹验证通过,也要向第二客户端发送人工验证请求,然后,客服人员通过第二客户端向第一客户端发送预设的身份验证问题,例如,身份证号码、姓名、学号等,通过判断用户的答案是否与预设的答案一致判断人工验证是否通过,并通过第二客户端将人工验证结果反馈至身份验证服务器。It should be noted that, in the voiceprint verification process, even if the user identity corresponds to the current voiceprint authentication vector, if the current voice data is interfered by human or environment, the voice data quality is poor, and the identity verification result may be in error. In order to ensure the accuracy of the user authentication, even if the voiceprint verification result is passed through the voiceprint verification, a manual verification request is sent to the second client, and then the customer service personnel sends a preset to the first client through the second client. The authentication problem, for example, the ID number, the name, the student number, etc., determines whether the manual verification is passed by judging whether the user's answer is consistent with the preset answer, and feeds the manual verification result to the identity verification server through the second client. .
当声纹验证结果为声纹验证失败,且人工验证结果为人工验证失败时,则判断用户身份验证失败;当声纹验证结果为声纹验证通过,且人工验证结果为人工验证通过时,则判断用户身份验证通过。通过双重验证确定用户身份验证结果,提高了身份验证的准确性。When the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is that the manual verification fails, the user identity verification fails; when the voiceprint verification result is that the voiceprint verification is passed, and the manual verification result is manually verified, then Determine the user authentication passed. The user authentication result is determined by two-factor verification, and the accuracy of the authentication is improved.
进一步地,当声纹验证结果为声纹验证通过,而人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分析结果。其中,所述预先确定的分析算法包括:若对用户进行人工身份验证的问题是答案为第一类型答案的第一类型问题,根据预先确定的第一分析规则对用户针对该第一类型问题的第一类型答案进行分析,并输出验证分析结 果,其中,第一类型答案指内容为数字的答案,例如,出生日期、身份证号码等;或者,若对用户进行人工身份验证的问题是答案为第二类型答案的第二类型问题,根据预先确定的第二分析规则对用户针对该第二类型问题的第二类型答案进行分析,并输出验证分析结果,其中,第二类型答案指内容为汉字的答案,例如,高一语文老师的姓名、大学一年级的年级辅导员的姓名等。Further, when the voiceprint verification result is that the voiceprint verification is passed, and the manual verification result is the manual verification failure, the user identity is analyzed again according to the predetermined analysis algorithm, and the verification analysis result is generated. The predetermined analysis algorithm includes: if the problem of performing manual authentication on the user is that the answer is the first type of question of the first type of answer, the user is targeted to the first type of question according to the predetermined first analysis rule. The first type of answer is analyzed and the result of the verification analysis is output, wherein the first type of answer refers to an answer whose content is a number, for example, a date of birth, an ID number, etc.; or, if the question of manual authentication of the user is the answer is a second type of question of the second type of answer, analyzing a second type of answer of the user for the second type of question according to a predetermined second analysis rule, and outputting a verification analysis result, wherein the second type of answer means that the content is a Chinese character The answer, for example, the name of the high school language teacher, the name of the first grade junior college counselor.
作为一种实施方式,所述根据预先确定的第一分析规则对用户针对该第一类型问题的第一类型答案进行分析的步骤具体包括:获取用户针对第一类型问题输入的第一类型答案;将第一类型答案和标准答案进行比对,识别出差异的部分,并确定差异部分的各个预设差异类型的差异数值;根据预先定义的预设差异类型与预设差异阈值的映射关系,将差异部分的各个预设差异类型的差异数值与对应的预设差异阈值进行比对分析,输出验证分析结果。In an embodiment, the step of analyzing the first type of answer of the first type problem by the user according to the predetermined first analysis rule comprises: acquiring a first type of answer input by the user for the first type of question; Comparing the first type of answer with the standard answer, identifying the difference part, and determining the difference value of each preset difference type of the difference part; according to the mapping relationship between the preset preset difference type and the preset difference threshold, The difference value of each preset difference type of the difference part is compared with the corresponding preset difference threshold value, and the verification analysis result is output.
所述预设差异类型包括差异部分数量、错误位数、区间差异度、区间匹配度。例如,用户输入的第一答案为123456789、标准答案为331456789,两者之间的差异部分是“123”和“331”,这两个数字的差异部分数量是1,差异部分的错误位数是3,差异部分没有出现过差异部分以外的数字,这两个数字的区间差异度为0,这两个数字的差异部分无法通过调整位数的形式进行还原匹配,这两个数字的区间匹配度为无穷大。再例如,123456789与331456971的差异部分是“123”和“331”、“789”和“971”,这两个数字的差异部分数量是2。再例如,123456789与341456789的差异部分是“123”和“341”,差异部分出现了差异部分以外的数字“4”,这两个数字的区间差异度为1。再例如,123456789与231456789的差异部分是“123”和“231”,这两个数字的差异部分可以通过调整位数的形式进行还原,可以将“231”中的数字“1”向前调整2个顺序进行还原以与“123”匹配,则这两个数字的区间匹配度为2。The preset difference type includes a difference portion number, an error number of bits, an interval difference degree, and an interval matching degree. For example, the first answer entered by the user is 123456789, and the standard answer is 331456789. The difference between the two is "123" and "331". The difference between the two numbers is 1, and the number of errors in the difference is 3, the difference part does not appear outside the difference part of the number, the difference between the two numbers is 0, the difference between the two numbers can not be restored by adjusting the number of bits, the interval matching of the two numbers For infinity. For another example, the difference between 123456789 and 331456971 is "123" and "331", "789", and "971", and the number of difference portions between the two numbers is 2. For another example, the difference between 123456789 and 341456789 is "123" and "341", and the difference portion has a number "4" other than the difference portion, and the difference between the two numbers is 1. For another example, the difference between 123456789 and 231456789 is "123" and "231". The difference between the two numbers can be restored by adjusting the number of digits. The number "1" in "231" can be adjusted forward 2 The order is restored to match "123", then the interval matching of the two numbers is 2.
确定了用户输入的答案与标准答案之间的预设差异类型的差异数值后,分别判断每个预设差异类型的差异数值是否小于或等于对应的预设差异阈值,若所有预设差异类型的差异数值小于或者等于对应的预设差异阈值,确定验证分析通过;若有一个预设差异类型的差异数值大于对应的差异阈值,则确定验证分析失败。例如,用户生成的数据为123456789、标准答案为331456789,两者之间的差异部分是“123”和“331”,差异部分的差异部分数量、错误位数、 区间差异度、区间匹配度这四个预设类型的差异数值分别为:1、3、0、∞,假设这四个预设类型的差异数值对应的预设差异阈值分别为:1、1、0、1,不满足所有预设差异类型的差异数值小于或者等于对应的差异阈值的条件,因此,确定验证分析失败,After determining the difference value of the preset difference type between the answer input by the user and the standard answer, respectively, determining whether the difference value of each preset difference type is less than or equal to the corresponding preset difference threshold, if all the preset difference types are The difference value is less than or equal to the corresponding preset difference threshold, and the verification analysis is determined to pass; if the difference value of the preset difference type is greater than the corresponding difference threshold, it is determined that the verification analysis fails. For example, the user-generated data is 123456789 and the standard answer is 331456789. The difference between the two is "123" and "331". The difference between the difference portion, the number of errors, the interval difference, and the interval matching degree are four. The difference values of the preset types are: 1, 3, 0, ∞, assuming that the preset difference thresholds corresponding to the difference values of the four preset types are: 1, 1, 0, 1, respectively, and all presets are not satisfied. The difference value of the difference type is less than or equal to the condition of the corresponding difference threshold. Therefore, it is determined that the verification analysis fails.
上述步骤仅适用于分析人工身份验证问题的答案为数字答案的情况,当人工身份验证问题的答案为文字答案时,需要利用第二分析规则进行分析。The above steps are only applicable to the case where the answer to the manual authentication question is a digital answer. When the answer to the manual authentication question is a text answer, the second analysis rule needs to be used for analysis.
作为一种实施方式,所述根据预先确定的第二分析规则对用户针对该第二类型问题的第二类型答案进行分析的步骤包括:As an implementation manner, the step of analyzing a second type of answer of the user for the second type of question according to the predetermined second analysis rule comprises:
获取用户针对第二类型问题输入的第二类型答案,将第二类型答案转换成字符串;根据预先确定的第二类型答案差异值分析算法将转换的第二类型答案字符串与预先确定的标准答案字符串进行比对分析,生成对应的第二类型答案差异值;若生成的第二类型答案差异值大于预设答案差异值阈值,则确定验证分析失败,或者,若生成的第二类型答案差异值小于或者等于预设答案差异值阈值,则确定验证分析通过。Obtaining a second type of answer entered by the user for the second type of question, converting the second type of answer into a string; converting the second type of answer string to a predetermined criterion according to a predetermined second type of answer difference value analysis algorithm The answer string is compared and analyzed to generate a corresponding second type of answer difference value; if the generated second type of answer difference value is greater than the preset answer difference value threshold, it is determined that the verification analysis fails, or if the generated second type of answer is generated If the difference value is less than or equal to the preset answer difference value threshold, it is determined that the verification analysis is passed.
具体地,所述预先确定的第二类型答案差异值分析算法包括:将转换的字符串逐字进行字母拆分,重新组合生成用户第二类型答案词包;将重新组合生成的用户第二类型答案词包与预先确定的标准答案词包进行字符匹配,生成对应的字母匹配集合值;根据预先确定的计算公式计算出生成的字母匹配集合值与标准集合值之间的集合差异值,并将该集合差异值作为所述第二类型答案差异值。Specifically, the predetermined second type of answer difference value analysis algorithm includes: splitting the converted string word by word, recombining to generate a user second type answer word package; and recombining the generated user second type The answer word package is matched with the predetermined standard answer word package to generate a corresponding letter matching set value; the set difference value between the generated letter matching set value and the standard set value is calculated according to a predetermined calculation formula, and The set difference value is used as the second type of answer difference value.
例如,用户输入的第二类型答案为‘小明’,标准答案若为‘小强’,则将两个答案分别转换成字符串:‘xiaoming’和‘xiaoqiang’,逐字进行字母拆分结果分别为“‘x’,‘i’,‘a’,‘o’,‘m’,‘i’,‘n’,‘g’”和“‘x’,‘i’,‘a’,‘o’,‘q’,‘i’,‘a’,‘n’,‘g’”,生成的用户第二类型答案词包可以计为{‘x’,‘i’,‘a’,‘o’},{‘m’,‘i’,‘n’,‘g’},标准答案词包可以计为{‘x’,‘i’,‘a’,‘o’},{‘q’,‘i’,‘a’,‘n’,‘g’};标准答案词包{‘x’,‘i’,‘a’,‘o’}与第二类型答案词包{‘x’,‘i’,‘a’,‘o’}每个字符均相同,则{‘x’,‘i’,‘a’,‘o’}对应的字母匹配集合值可以为[1,1,1,1];标准答案词包{‘q’,‘i’,‘a’,‘n’,‘g’}与第二类型答案词包{‘m’,‘i’,‘n’,‘g’}中有三个字符不相同,其对应的字母匹配集合值可以为[0,1,0,1,1]),根据预先确定的计算公式计算出生成的字母匹配集合值([1,1,1,1][0,1,0,1,1])与标准集 合值([1,1,1,1][1,1,1,1,1])之间的集合差异值,该集合差异值即为所述第二类型答案差异值。在本实施例中,所述预先确定的计算公式可以是余弦公式,欧氏距离计算公式等。For example, the second type of answer input by the user is 'Xiao Ming', and if the standard answer is 'Xiaoqiang', the two answers are respectively converted into strings: 'xiaoming' and 'xiaoqiang', and the result of word-by-word splitting is "'x','i','a','o','m','i','n','g'" and ''x','i','a','o' , 'q', 'i', 'a', 'n', 'g'", the generated user type 2 answer package can be counted as {'x', 'i', 'a', 'o' },{'m','i','n','g'}, the standard answer word package can be counted as {'x', 'i', 'a', 'o'}, {'q', 'i', 'a', 'n', 'g'}; standard answer words {'x', 'i', 'a', 'o'} and the second type of answer word package {'x', 'i', 'a', 'o'} each character is the same, then the letter matching set value corresponding to {'x', 'i', 'a', 'o'} can be [1, 1, 1 , 1]; standard answer word package {'q', 'i', 'a', 'n', 'g'} and the second type of answer word package {'m', 'i , 'n', 'g'} have three characters that are different, and the corresponding letter matching set value can be [0, 1, 0, 1, 1]), and the generated letter matching is calculated according to a predetermined calculation formula. Set value ([1,1,1,1][0,1,0,1,1]) and standard set value ([1,1,1,1][1,1,1,1,1]) A set difference value between the set of difference values is the second type of answer difference value. In this embodiment, the predetermined calculation formula may be a cosine formula, an Euclidean distance calculation formula, or the like.
当计算的第二类型答案差异值小于或者等于汉字答案差异值阈值时,确定验证分析结果为验证分析通过,即判断用户身份验证通过;否则,确定验证分析结果为验证分析失败,即判断用户身份验证失败。When the calculated second type of answer difference value is less than or equal to the Chinese character answer difference value threshold, it is determined that the verification analysis result is passed by the verification analysis, that is, the user identity verification is determined; otherwise, the verification analysis result is determined as the verification analysis failure, that is, the user identity is determined. verification failed.
进一步地,还存在一种情况:当声纹验证结果为声纹验证失败,且人工验证结果为人工验证通过,则从用户预先确定的附加问题中选择一个或多个问题,向第一客户端提出该问题,比如,初中最好的朋友的名字,并从第一客户端获取用户针对所述附加问题的附加答案;将获取的附加答案与预先确定的标准附加答案进行比对分析;若获取的附加答案(例如,张三)与预先确定的标准附加答案(例如,张三)一致,则判断用户身份验证通过;若获取的附加答案(例如,张三)与预先确定的标准附加答案(例如,李四)不一致,则判断用户身份验证失败。Further, there is a case that when the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is manually verified, one or more questions are selected from the additional questions predetermined by the user, to the first client. Raising the question, for example, the name of the best friend of junior high school, and obtaining the user's additional answer to the additional question from the first client; comparing the obtained additional answer with the predetermined standard additional answer; The additional answer (for example, Zhang San) is consistent with the predetermined standard additional answer (for example, Zhang San), then the user's identity verification is passed; if the additional answer obtained (for example, Zhang San) and the predetermined standard additional answer ( For example, if Li Si) is inconsistent, it is judged that the user authentication failed.
上述实施例提出的身份验证服务器1,利用声纹识别技术,对用户身份进行初步验证,然后,根据用户针对预设问题的回答,对用户身份进行二次验证,结合初步验证结果及二次验证结果,综合判断用户身份是否通过验证,提高了用户身份验证的准确性。The identity verification server 1 proposed by the foregoing embodiment uses the voiceprint recognition technology to perform preliminary verification on the user identity, and then, according to the user's response to the preset question, performs secondary verification on the user identity, combined with the preliminary verification result and the secondary verification. As a result, comprehensively determining whether the user identity passes the verification improves the accuracy of the user identity verification.
可选地,在其他的实施例中,基于声纹识别的身份验证程序10还可以被分割为一个或者多个模块,一个或者多个模块被存储于存储器11中,并由一个或多个处理器(本实施例为处理器12)所执行,以完成本申请,本申请所称的模块是指能够完成特定功能的一系列计算机程序指令段。例如,参照图2所示,为图1中基于声纹识别的身份验证程序10的程序模块示意图,该实施例中,基于声纹识别的身份验证程序10可以被分割为向量获取模块110、声纹验证模块120、人工验证模块130、二次分析模块140及身份验证模块150,所述模块110-150所实现的功能或操作步骤均与上文类似,此处不再详述,示例性地,例如其中:Alternatively, in other embodiments, the voiceprint recognition based authentication program 10 may also be partitioned into one or more modules, one or more modules being stored in the memory 11 and processed by one or more The present invention is implemented by the processor (this embodiment is the processor 12) to accomplish the present application. The term "module" as used herein refers to a series of computer program instructions that are capable of performing a particular function. For example, referring to FIG. 2, it is a schematic diagram of a program module of the voiceprint recognition-based identity verification program 10 in FIG. 1. In this embodiment, the voiceprint recognition-based identity verification program 10 can be divided into a vector acquisition module 110, and a sound. The pattern verification module 120, the manual verification module 130, the secondary analysis module 140, and the identity verification module 150, the functions or operation steps implemented by the modules 110-150 are similar to the above, and are not described in detail herein, exemplarily , for example:
向量获取模块110,用于接收第一客户端发送的带有用户身份标识的身份验证请求,从第一客户端采集用户的当前语音数据,为所述当前语音数据构 建当前声纹鉴别向量,根据用户身份标识确定所述用户身份标识对应的标准声纹鉴别向量;The vector acquisition module 110 is configured to receive an identity verification request with a user identity sent by the first client, collect current voice data of the user from the first client, and construct a current voiceprint identification vector for the current voice data, according to The user identity identifies a standard voiceprint identification vector corresponding to the user identity identifier;
声纹验证模块120,用于利用预先确定的距离计算公式,计算当前声纹鉴别向量与标准声纹鉴别向量之间的距离,根据计算的距离分析是否通过声纹验证,并生成声纹验证结果发送给第一客户端;The voiceprint verification module 120 is configured to calculate a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector by using a predetermined distance calculation formula, analyze whether the voiceprint verification is performed according to the calculated distance, and generate a voiceprint verification result. Sent to the first client;
人工验证模块130,用于当声纹验证结果为声纹验证通过时,从第二客户端获取人工验证结果;The manual verification module 130 is configured to obtain a manual verification result from the second client when the voiceprint verification result is that the voiceprint verification is passed;
二次分析模块140,用于当人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分析结果;及The secondary analysis module 140 is configured to analyze the user identity again according to a predetermined analysis algorithm when the manual verification result is a manual verification failure, and generate a verification analysis result;
身份验证模块150,用于当验证分析结果为验证分析通过时,判断用户身份验证通过,或者,当验证分析结果为验证分析失败时,判断用户身份验证失败。The authentication module 150 is configured to determine that the user identity verification is passed when the verification analysis result is passed by the verification analysis, or to determine that the user identity verification fails when the verification analysis result is that the verification analysis fails.
此外,本申请还提供一种基于声纹识别的身份验证方法。参照图3所示,为本申请基于声纹识别的身份验证方法较佳实施例的流程图。该方法可以由一个装置执行,该装置可以由软件和/或硬件实现。In addition, the present application also provides an identity verification method based on voiceprint recognition. Referring to FIG. 3, it is a flowchart of a preferred embodiment of the voiceprint recognition based identity verification method of the present application. The method can be performed by a device that can be implemented by software and/or hardware.
在本实施例中,基于声纹识别的身份验证方法包括步骤S1-S5:In this embodiment, the voiceprint recognition based identity verification method includes steps S1-S5:
步骤S1,接收第一客户端发送的带有用户身份标识的身份验证请求,从第一客户端采集用户的当前语音数据,为所述当前语音数据构建当前声纹鉴别向量,根据用户身份标识确定所述用户身份标识对应的标准声纹鉴别向量;Step S1: Receive an identity verification request with a user identity sent by the first client, collect current voice data of the user from the first client, and construct a current voiceprint authentication vector for the current voice data, and determine according to the user identity identifier. a standard voiceprint identification vector corresponding to the user identity;
步骤S2,利用预先确定的距离计算公式,计算当前声纹鉴别向量与标准声纹鉴别向量之间的距离,根据计算的距离分析是否通过声纹验证,并生成声纹验证结果发送给第一客户端;Step S2, using a predetermined distance calculation formula, calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client end;
步骤S3,当声纹验证结果为声纹验证通过时,从第二客户端获取人工验证结果;Step S3, when the voiceprint verification result is that the voiceprint verification is passed, the manual verification result is obtained from the second client;
步骤S4,当人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分析结果;及Step S4, when the manual verification result is a manual verification failure, the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result;
步骤S5,当验证分析结果为验证分析通过时,判断用户身份验证通过,或者,当验证分析结果为验证分析失败时,判断用户身份验证失败。In step S5, when the verification analysis result is that the verification analysis passes, it is determined that the user identity verification is passed, or when the verification analysis result is that the verification analysis fails, it is determined that the user identity verification fails.
在本实施例中,第一客户端为用户使用的终端,第二客户端为客服人员 使用的终端,终端可以为具有声音采集功能的移动终端或台式计算机等。当需要对用户身份进行审核时,接收第一客户端发送来的带有用户身份标识(例如,身份证号)的身份验证请求后,利用第一客户端采集用户的当前语音数据,为采集的当前语音数据构建出当前声纹鉴别向量,鉴于语音数据构建声纹鉴别向量为本领域人员习知的技术,在此不作赘述。可以理解的是,为了确定当前声纹鉴别向量是否与第一用户端发送来的身份标识相对应,需预先为预先确定的用户身份标识设置对应的标准声纹鉴别向量,得到预先确定的用户身份标识与标准声纹鉴别向量的映射关系。In this embodiment, the first client is a terminal used by the user, and the second client is a terminal used by the customer service personnel, and the terminal may be a mobile terminal or a desktop computer having a sound collection function. When the user identity needs to be audited, after receiving the identity verification request sent by the first client with the user identity (for example, the ID number), the first client collects the current voice data of the user for collecting. The current voice data constructs the current voiceprint discriminant vector, and the voiceprint discriminant vector is constructed according to the voice data, which is a well-known technique in the art, and will not be described herein. It can be understood that, in order to determine whether the current voiceprint authentication vector corresponds to the identity sent by the first user, the corresponding standard voiceprint identification vector needs to be set in advance for the predetermined user identity to obtain a predetermined user identity. The mapping relationship between the logo and the standard voiceprint discrimination vector.
然后,根据身份验证请求中的用户身份标识,以及用户身份标识与标准声纹鉴别向量的映射关系,确定用户身份标识对应的标准声纹鉴别向量,利用预先确定的距离计算公式计算当前声纹鉴别向量与确定的标准声纹鉴别向量之间的距离。具体地,预先确定的距离计算公式为:Then, according to the user identity in the identity verification request, and the mapping relationship between the user identity and the standard voiceprint authentication vector, the standard voiceprint identification vector corresponding to the user identity is determined, and the current voiceprint identification is calculated by using a predetermined distance calculation formula. The distance between the vector and the determined standard voiceprint discrimination vector. Specifically, the predetermined distance calculation formula is:
其中,
代表标准声纹鉴别向量,
代表当前声纹鉴别向量。
among them, Represents the standard voiceprint discrimination vector, Represents the current voiceprint discrimination vector.
当计算的距离小于或者等于预设的距离阈值时,确定通过验证,否则,确定验证失败。When the calculated distance is less than or equal to the preset distance threshold, it is determined to pass the verification, otherwise, the verification fails.
需要说明的是,声纹验证过程中,即使用户身份标识与当前声纹鉴别向量对应,如果当前语音数据因受人为或环境干扰,导致语音数据质量较差,也会出现身份验证结果出错的情况,为了保证用户身份验证的准确性,即使声纹验证结果为声纹验证通过,也要向第二客户端发送人工验证请求,然后,客服人员通过第二客户端向第一客户端发送预设的身份验证问题,例如,身份证号码、姓名、学号等,通过判断用户的答案是否与预设的答案一致判断人工验证是否通过,并通过第二客户端将人工验证结果反馈至身份验证服务器。It should be noted that, in the voiceprint verification process, even if the user identity corresponds to the current voiceprint authentication vector, if the current voice data is interfered by human or environment, the voice data quality is poor, and the identity verification result may be in error. In order to ensure the accuracy of the user authentication, even if the voiceprint verification result is passed through the voiceprint verification, a manual verification request is sent to the second client, and then the customer service personnel sends a preset to the first client through the second client. The authentication problem, for example, the ID number, the name, the student number, etc., determines whether the manual verification is passed by judging whether the user's answer is consistent with the preset answer, and feeds the manual verification result to the identity verification server through the second client. .
当声纹验证结果为声纹验证失败,且人工验证结果为人工验证失败时,则判断用户身份验证失败;当声纹验证结果为声纹验证通过,且人工验证结果为人工验证通过时,则判断用户身份验证通过。通过双重验证确定用户身份验证结果,提高了身份验证的准确性。When the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is that the manual verification fails, the user identity verification fails; when the voiceprint verification result is that the voiceprint verification is passed, and the manual verification result is manually verified, then Determine the user authentication passed. The user authentication result is determined by two-factor verification, and the accuracy of the authentication is improved.
进一步地,当声纹验证结果为声纹验证通过,而人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分 析结果。其中,所述预先确定的分析算法包括:若对用户进行人工身份验证的问题是答案为第一类型答案的第一类型问题,根据预先确定的第一分析规则对用户针对该第一类型问题的第一类型答案进行分析,并输出验证分析结果,其中,第一类型答案指内容为数字的答案,例如,出生日期、身份证号码等;或者,若对用户进行人工身份验证的问题是答案为第二类型答案的第二类型问题,根据预先确定的第二分析规则对用户针对该第二类型问题的第二类型答案进行分析,并输出验证分析结果,其中,第二类型答案指内容为汉字的答案,例如,高一语文老师的姓名、大学一年级的年级辅导员的姓名等。Further, when the voiceprint verification result is that the voiceprint verification is passed, and the manual verification result is the manual verification failure, the user identity is analyzed again according to the predetermined analysis algorithm, and the verification analysis result is generated. The predetermined analysis algorithm includes: if the problem of performing manual authentication on the user is that the answer is the first type of question of the first type of answer, the user is targeted to the first type of question according to the predetermined first analysis rule. The first type of answer is analyzed and the result of the verification analysis is output, wherein the first type of answer refers to an answer whose content is a number, for example, a date of birth, an ID number, etc.; or, if the question of manual authentication of the user is the answer is a second type of question of the second type of answer, analyzing a second type of answer of the user for the second type of question according to a predetermined second analysis rule, and outputting a verification analysis result, wherein the second type of answer means that the content is a Chinese character The answer, for example, the name of the high school language teacher, the name of the first grade junior college counselor.
作为一种实施方式,所述根据预先确定的第一分析规则对用户针对该第一类型问题的第一类型答案进行分析的步骤具体包括:获取用户针对第一类型问题输入的第一类型答案;将第一类型答案和标准答案进行比对,识别出差异的部分,并确定差异部分的各个预设差异类型的差异数值;根据预先定义的预设差异类型与预设差异阈值的映射关系,将差异部分的各个预设差异类型的差异数值与对应的预设差异阈值进行比对分析,输出验证分析结果。In an embodiment, the step of analyzing the first type of answer of the first type problem by the user according to the predetermined first analysis rule comprises: acquiring a first type of answer input by the user for the first type of question; Comparing the first type of answer with the standard answer, identifying the difference part, and determining the difference value of each preset difference type of the difference part; according to the mapping relationship between the preset preset difference type and the preset difference threshold, The difference value of each preset difference type of the difference part is compared with the corresponding preset difference threshold value, and the verification analysis result is output.
所述预设差异类型包括差异部分数量、错误位数、区间差异度、区间匹配度。例如,用户输入的第一答案为123456789、标准答案为331456789,两者之间的差异部分是“123”和“331”,这两个数字的差异部分数量是1,差异部分的错误位数是3,差异部分没有出现过差异部分以外的数字,这两个数字的区间差异度为0,这两个数字的差异部分无法通过调整位数的形式进行还原匹配,这两个数字的区间匹配度为无穷大。再例如,123456789与331456971的差异部分是“123”和“331”、“789”和“971”,这两个数字的差异部分数量是2。再例如,123456789与341456789的差异部分是“123”和“341”,差异部分出现了差异部分以外的数字“4”,这两个数字的区间差异度为1。再例如,123456789与231456789的差异部分是“123”和“231”,这两个数字的差异部分可以通过调整位数的形式进行还原,可以将“231”中的数字“1”向前调整2个顺序进行还原以与“123”匹配,则这两个数字的区间匹配度为2。The preset difference type includes a difference portion number, an error number of bits, an interval difference degree, and an interval matching degree. For example, the first answer entered by the user is 123456789, and the standard answer is 331456789. The difference between the two is "123" and "331". The difference between the two numbers is 1, and the number of errors in the difference is 3, the difference part does not appear outside the difference part of the number, the difference between the two numbers is 0, the difference between the two numbers can not be restored by adjusting the number of bits, the interval matching of the two numbers For infinity. For another example, the difference between 123456789 and 331456971 is "123" and "331", "789", and "971", and the number of difference portions between the two numbers is 2. For another example, the difference between 123456789 and 341456789 is "123" and "341", and the difference portion has a number "4" other than the difference portion, and the difference between the two numbers is 1. For another example, the difference between 123456789 and 231456789 is "123" and "231". The difference between the two numbers can be restored by adjusting the number of digits. The number "1" in "231" can be adjusted forward 2 The order is restored to match "123", then the interval matching of the two numbers is 2.
确定了用户输入的答案与标准答案之间的预设差异类型的差异数值后,分别判断每个预设差异类型的差异数值是否小于或等于对应的预设差异阈值,若所有预设差异类型的差异数值小于或者等于对应的预设差异阈值,确定验 证分析通过;若有一个预设差异类型的差异数值大于对应的差异阈值,则确定验证分析失败。例如,用户生成的数据为123456789、标准答案为331456789,两者之间的差异部分是“123”和“331”,差异部分的差异部分数量、错误位数、区间差异度、区间匹配度这四个预设类型的差异数值分别为:1、3、0、∞,假设这四个预设类型的差异数值对应的预设差异阈值分别为:1、1、0、1,不满足所有预设差异类型的差异数值小于或者等于对应的差异阈值的条件,因此,确定验证分析失败,After determining the difference value of the preset difference type between the answer input by the user and the standard answer, respectively, determining whether the difference value of each preset difference type is less than or equal to the corresponding preset difference threshold, if all the preset difference types are The difference value is less than or equal to the corresponding preset difference threshold, and the verification analysis is determined to pass; if the difference value of the preset difference type is greater than the corresponding difference threshold, it is determined that the verification analysis fails. For example, the user-generated data is 123456789 and the standard answer is 331456789. The difference between the two is "123" and "331". The difference between the difference, the number of errors, the interval difference, and the interval matching degree are four. The difference values of the preset types are: 1, 3, 0, ∞, assuming that the preset difference thresholds corresponding to the difference values of the four preset types are: 1, 1, 0, 1, respectively, and all presets are not satisfied. The difference value of the difference type is less than or equal to the condition of the corresponding difference threshold. Therefore, it is determined that the verification analysis fails.
上述步骤仅适用于分析人工身份验证问题的答案为数字答案的情况,当人工身份验证问题的答案为文字答案时,需要利用第二分析规则进行分析。The above steps are only applicable to the case where the answer to the manual authentication question is a digital answer. When the answer to the manual authentication question is a text answer, the second analysis rule needs to be used for analysis.
作为一种实施方式,所述根据预先确定的第二分析规则对用户针对该第二类型问题的第二类型答案进行分析的步骤包括:As an implementation manner, the step of analyzing a second type of answer of the user for the second type of question according to the predetermined second analysis rule comprises:
获取用户针对第二类型问题输入的第二类型答案,将第二类型答案转换成字符串;根据预先确定的第二类型答案差异值分析算法将转换的第二类型答案字符串与预先确定的标准答案字符串进行比对分析,生成对应的第二类型答案差异值;若生成的第二类型答案差异值大于预设答案差异值阈值,则确定验证分析失败,或者,若生成的第二类型答案差异值小于或者等于预设答案差异值阈值,则确定验证分析通过。Obtaining a second type of answer entered by the user for the second type of question, converting the second type of answer into a string; converting the second type of answer string to a predetermined criterion according to a predetermined second type of answer difference value analysis algorithm The answer string is compared and analyzed to generate a corresponding second type of answer difference value; if the generated second type of answer difference value is greater than the preset answer difference value threshold, it is determined that the verification analysis fails, or if the generated second type of answer is generated If the difference value is less than or equal to the preset answer difference value threshold, it is determined that the verification analysis is passed.
具体地,所述预先确定的第二类型答案差异值分析算法包括:将转换的字符串逐字进行字母拆分,重新组合生成用户第二类型答案词包;将重新组合生成的用户第二类型答案词包与预先确定的标准答案词包进行字符匹配,生成对应的字母匹配集合值;根据预先确定的计算公式计算出生成的字母匹配集合值与标准集合值之间的集合差异值,并将该集合差异值作为所述第二类型答案差异值。Specifically, the predetermined second type of answer difference value analysis algorithm includes: splitting the converted string word by word, recombining to generate a user second type answer word package; and recombining the generated user second type The answer word package is matched with the predetermined standard answer word package to generate a corresponding letter matching set value; the set difference value between the generated letter matching set value and the standard set value is calculated according to a predetermined calculation formula, and The set difference value is used as the second type of answer difference value.
例如,用户输入的第二类型答案为‘小明’,标准答案若为‘小强’,则将两个答案分别转换成字符串:‘xiaoming’和‘xiaoqiang’,逐字进行字母拆分结果分别为“‘x’,‘i’,‘a’,‘o’,‘m’,‘i’,‘n’,‘g’”和“‘x’,‘i’,‘a’,‘o’,‘q’,‘i’,‘a’,‘n’,‘g’”,生成的用户第二类型答案词包可以计为{‘x’,‘i’,‘a’,‘o’},{‘m’,‘i’,‘n’,‘g’},标准答案词包可以计为{‘x’,‘i’,‘a’,‘o’},{‘q’,‘i’,‘a’,‘n’,‘g’};标准答案词包{‘x’,‘i’,‘a’,‘o’}与第二类型答案词包{‘x’,‘i’,‘a’,‘o’}每个字符均相同,则{‘x’,‘i’,‘a’,‘o’}对应的字母匹配集合值可以为[1,1,1,1]; 标准答案词包{‘q’,‘i’,‘a’,‘n’,‘g’}与第二类型答案词包{‘m’,‘i’,‘n’,‘g’}中有三个字符不相同,其对应的字母匹配集合值可以为[0,1,0,1,1]),根据预先确定的计算公式计算出生成的字母匹配集合值([1,1,1,1][0,1,0,1,1])与标准集合值([1,1,1,1][1,1,1,1,1])之间的集合差异值,该集合差异值即为所述第二类型答案差异值。在本实施例中,所述预先确定的计算公式可以是余弦公式,欧氏距离计算公式等。For example, the second type of answer input by the user is 'Xiao Ming', and if the standard answer is 'Xiaoqiang', the two answers are respectively converted into strings: 'xiaoming' and 'xiaoqiang', and the result of word-by-word splitting is "'x','i','a','o','m','i','n','g'" and ''x','i','a','o' , 'q', 'i', 'a', 'n', 'g'", the generated user type 2 answer package can be counted as {'x', 'i', 'a', 'o' },{'m','i','n','g'}, the standard answer word package can be counted as {'x', 'i', 'a', 'o'}, {'q', 'i', 'a', 'n', 'g'}; standard answer words {'x', 'i', 'a', 'o'} and the second type of answer word package {'x', 'i', 'a', 'o'} each character is the same, then the letter matching set value corresponding to {'x', 'i', 'a', 'o'} can be [1, 1, 1 , 1]; standard answer word package {'q', 'i', 'a', 'n', 'g'} and the second type of answer word package {'m', 'i , 'n', 'g'} have three characters that are different, and the corresponding letter matching set value can be [0, 1, 0, 1, 1]), and the generated letter matching is calculated according to a predetermined calculation formula. Set value ([1,1,1,1][0,1,0,1,1]) and standard set value ([1,1,1,1][1,1,1,1,1]) A set difference value between the set of difference values is the second type of answer difference value. In this embodiment, the predetermined calculation formula may be a cosine formula, an Euclidean distance calculation formula, or the like.
当计算的第二类型答案差异值小于或者等于汉字答案差异值阈值时,确定验证分析结果为验证分析通过,即判断用户身份验证通过;否则,确定验证分析结果为验证分析失败,即判断用户身份验证失败。When the calculated second type of answer difference value is less than or equal to the Chinese character answer difference value threshold, it is determined that the verification analysis result is passed by the verification analysis, that is, the user identity verification is determined; otherwise, the verification analysis result is determined as the verification analysis failure, that is, the user identity is determined. verification failed.
进一步地,还存在一种情况:当声纹验证结果为声纹验证失败,且人工验证结果为人工验证通过,则从用户预先确定的附加问题中选择一个或多个问题,向第一客户端提出该问题,比如,初中最好的朋友的名字,并从第一客户端获取用户针对所述附加问题的附加答案;将获取的附加答案与预先确定的标准附加答案进行比对分析;若获取的附加答案(例如,张三)与预先确定的标准附加答案(例如,张三)一致,则判断用户身份验证通过;若获取的附加答案(例如,张三)与预先确定的标准附加答案(例如,李四)不一致,则判断用户身份验证失败。Further, there is a case that when the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is manually verified, one or more questions are selected from the additional questions predetermined by the user, to the first client. Raising the question, for example, the name of the best friend of junior high school, and obtaining the user's additional answer to the additional question from the first client; comparing the obtained additional answer with the predetermined standard additional answer; The additional answer (for example, Zhang San) is consistent with the predetermined standard additional answer (for example, Zhang San), then the user's identity verification is passed; if the additional answer obtained (for example, Zhang San) and the predetermined standard additional answer ( For example, if Li Si) is inconsistent, it is judged that the user authentication failed.
上述实施例提出的基于声纹识别的身份验证方法,利用声纹识别技术,对用户身份进行初步验证,然后,根据用户针对预设问题的回答,对用户身份进行二次验证,结合初步验证结果及二次验证结果,综合判断用户身份是否通过验证,提高了用户身份验证的准确性。The voiceprint recognition-based identity verification method proposed in the above embodiment uses the voiceprint recognition technology to perform preliminary verification on the user identity, and then, according to the user's response to the preset question, performs secondary verification on the user identity, combined with the preliminary verification result. And the results of the second verification, comprehensively determine whether the user identity has passed the verification, and improve the accuracy of the user identity verification.
此外,本申请实施例还提出一种计算机可读存储介质,所述计算机可读存储介质上存储有基于声纹识别的身份验证程序10,该程序被处理器执行时实现如下操作:In addition, the embodiment of the present application further provides a computer readable storage medium, where the voiceprint recognition based identity verification program 10 is stored, and when the program is executed by the processor, the following operations are implemented:
接收第一客户端发送的带有用户身份标识的身份验证请求,从第一客户端采集用户的当前语音数据,为所述当前语音数据构建当前声纹鉴别向量,根据用户身份标识确定所述用户身份标识对应的标准声纹鉴别向量;Receiving an identity verification request with a user identity sent by the first client, collecting current voice data of the user from the first client, constructing a current voiceprint authentication vector for the current voice data, and determining the user according to the user identity identifier a standard voiceprint identification vector corresponding to the identity;
利用预先确定的距离计算公式,计算当前声纹鉴别向量与标准声纹鉴别向量之间的距离,根据计算的距离分析是否通过声纹验证,并生成声纹验证 结果发送给第一客户端;Using a predetermined distance calculation formula, calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client;
当声纹验证结果为声纹验证通过时,从第二客户端获取人工验证结果;When the voiceprint verification result is that the voiceprint verification is passed, the manual verification result is obtained from the second client;
当人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分析结果;及When the manual verification result is a manual verification failure, the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result;
当验证分析结果为验证分析通过时,判断用户身份验证通过,或者,当验证分析结果为验证分析失败时,判断用户身份验证失败。When the verification analysis result is that the verification analysis passes, it is judged that the user identity verification is passed, or when the verification analysis result is that the verification analysis fails, it is judged that the user identity verification fails.
本申请计算机可读存储介质具体实施方式与上述基于声纹识别的身份验证方法的各实施例基本相同,在此不作累述。The specific embodiment of the computer readable storage medium of the present application is substantially the same as the embodiments of the voiceprint recognition based authentication method described above, and will not be described herein.
需要说明的是,上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。并且本文中的术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、装置、物品或者方法不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、装置、物品或者方法所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、装置、物品或者方法中还存在另外的相同要素。It should be noted that the foregoing serial numbers of the embodiments of the present application are merely for the description, and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising", or any other variations thereof are intended to encompass a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a plurality of elements includes not only those elements but also Other elements listed, or elements that are inherent to such a process, device, item, or method. An element that is defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, the device, the item, or the method that comprises the element.
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,或者网络设备等)执行本申请各个实施例所述的方法。Through the description of the above embodiments, those skilled in the art can clearly understand that the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better. Implementation. Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM as described above). , a disk, an optical disk, including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the various embodiments of the present application.
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。The above is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent application, and the equivalent structure or equivalent process transformations made by the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of this application.
Claims (20)
- 一种基于声纹识别的身份验证方法,其特征在于,该方法包括:An authentication method based on voiceprint recognition, characterized in that the method comprises:接收第一客户端发送的带有用户身份标识的身份验证请求,从第一客户端采集用户的当前语音数据,为所述当前语音数据构建当前声纹鉴别向量,根据用户身份标识确定所述用户身份标识对应的标准声纹鉴别向量;Receiving an identity verification request with a user identity sent by the first client, collecting current voice data of the user from the first client, constructing a current voiceprint authentication vector for the current voice data, and determining the user according to the user identity identifier a standard voiceprint identification vector corresponding to the identity;利用预先确定的距离计算公式,计算当前声纹鉴别向量与标准声纹鉴别向量之间的距离,根据计算的距离分析是否通过声纹验证,并生成声纹验证结果发送给第一客户端;Using a predetermined distance calculation formula, calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client;当声纹验证结果为声纹验证通过时,从第二客户端获取人工验证结果;When the voiceprint verification result is that the voiceprint verification is passed, the manual verification result is obtained from the second client;当人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分析结果;及When the manual verification result is a manual verification failure, the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result;当验证分析结果为验证分析通过时,判断用户身份验证通过,或者,当验证分析结果为验证分析失败时,判断用户身份验证失败。When the verification analysis result is that the verification analysis passes, it is judged that the user identity verification is passed, or when the verification analysis result is that the verification analysis fails, it is judged that the user identity verification fails.
- 如权利要求1所述的基于声纹识别的身份验证方法,其特征在于,该方法还包括:The voiceprint recognition-based authentication method according to claim 1, wherein the method further comprises:当声纹验证结果为声纹验证通过,且人工验证结果为人工验证通过时,判断用户身份验证通过;或When the voiceprint verification result is that the voiceprint verification is passed, and the manual verification result is manually verified, the user identity verification is determined to pass; or当声纹验证结果为声纹验证失败,且人工验证结果为人工验证失败时,判断用户身份验证失败。When the voiceprint verification result is that voiceprint verification fails, and the manual verification result is manual verification failure, it is determined that the user identity verification fails.
- 如权利要求1或2所述的基于声纹识别的身份验证方法,其特征在于,所述“根据预先确定的分析算法再次对用户身份进行分析”的步骤具体包括:The voiceprint recognition-based identity verification method according to claim 1 or 2, wherein the step of "analyzing the user identity again according to a predetermined analysis algorithm" comprises:若对用户进行人工身份验证的问题是答案为第一类型答案的第一类型问题,根据预先确定的第一分析规则对用户针对该第一类型问题的第一类型答案进行分析,输出验证分析结果;或If the problem of manual authentication for the user is that the answer is the first type of question of the first type of answer, the first type of answer for the first type of question is analyzed by the user according to the predetermined first analysis rule, and the result of the verification analysis is output. ;or若对用户进行人工身份验证的问题是答案为第二类型答案的第二类型问题,根据预先确定的第二分析规则对用户针对该第二类型问题的第二类型答案进行分析,输出验证分析结果。If the problem of manual authentication for the user is that the answer is the second type of question of the second type of answer, the second type of answer of the user for the second type of question is analyzed according to a predetermined second analysis rule, and the result of the verification analysis is output. .
- 如权利要求3所述的基于声纹识别的身份验证方法,其特征在于,所述“根据预先确定的第一分析规则对用户针对该第一类型问题的第一类型答案进行分析”的步骤具体包括:The voiceprint recognition-based identity verification method according to claim 3, wherein said step of "analysing a first type of answer of the user for the first type of question according to a predetermined first analysis rule" is specific include:获取用户针对第一类型问题输入的第一类型答案,将第一类型答案和标准答案进行比对,识别出差异部分,并确定该差异部分的各个预设差异类型的差异数值;及Obtaining a first type of answer input by the user for the first type of question, comparing the first type of the answer with the standard answer, identifying the difference part, and determining the difference value of each preset difference type of the difference part;根据预先定义的预设差异类型与预设差异阈值的映射关系,将所述差异部分的各个预设差异类型的差异数值与对应的预设差异阈值进行比对分析,输出验证分析结果。According to a mapping relationship between the preset preset difference type and the preset difference threshold, the difference value of each preset difference type of the difference part is compared with the corresponding preset difference threshold, and the verification analysis result is output.
- 如权利要求4所述的基于声纹识别的身份验证方法,其特征在于,所述预设差异类型包括差异部分数量、错误位数、区间差异度、区间匹配度。The voiceprint recognition-based identity verification method according to claim 4, wherein the preset difference type includes a difference portion number, an error number of bits, an interval difference degree, and an interval matching degree.
- 如权利要求3所述的基于声纹识别的身份验证方法,其特征在于,所述“根据预先确定的第二分析规则对用户针对该第二类型问题的第二类型答案进行分析”的步骤具体包括:The voiceprint recognition-based identity verification method according to claim 3, wherein said step of "analysing a second type of answer of the user for the second type of question according to a predetermined second analysis rule" is specific include:获取用户针对第二类型问题输入的第二类型答案,将该第二类型答案转换成字符串;Obtaining a second type of answer input by the user for the second type of question, converting the second type of answer into a string;根据预先确定的第二类型答案差异值分析算法将所述字符串与预先确定的标准答案字符串进行比对分析,生成对应的第二类型答案差异值;及Comparing the character string with a predetermined standard answer string according to a predetermined second type of answer difference value analysis algorithm to generate a corresponding second type of answer difference value; and当所述第二类型答案差异值小于或者等于预设汉字答案阈值时,确定验证分析通过,或者,当所述第二类型答案差异值大于预设的第二类型答案差异值阈值时,确定验证分析失败。Determining that the verification analysis passes when the second type of answer difference value is less than or equal to the preset Chinese character answer threshold, or determining verification when the second type of answer difference value is greater than a preset second type of answer difference value threshold Analysis failed.
- 如权利要求6所述的基于声纹识别的身份验证方法,其特征在于,所述“根据预先确定的第二类型答案差异值分析算法将所述字符串与预先确定的标准答案字符串进行比对分析,生成对应的第二类型答案差异值”的步骤具体包括:The voiceprint recognition-based identity verification method according to claim 6, wherein said "comprising said character string with a predetermined standard answer string according to a predetermined second type of answer difference value analysis algorithm The step of generating a corresponding second type of answer difference value for the analysis includes:将转换的字符串逐字进行字母拆分,重新组合生成第二类型答案词包;Splitting the converted string word by word and recombining to generate a second type of answer word package;将所述第二类型答案词包与预先确定的标准答案词包进行字符匹配,生成对应的字母匹配集合值;及Matching the second type of answer word package with a predetermined standard answer word package to generate a corresponding letter matching set value; and根据预先确定的计算公式计算所述字母匹配集合值与标准集合值之间的集合差异值,并将该集合差异值作为所述第二类型答案差异值。Calculating a set difference value between the letter matching set value and the standard set value according to a predetermined calculation formula, and using the set difference value as the second type answer difference value.
- 如权利要求1所述的基于声纹识别的身份验证方法,其特征在于,该方法还包括:The voiceprint recognition-based authentication method according to claim 1, wherein the method further comprises:当声纹验证结果为声纹验证失败,且人工验证结果为人工验证通过时, 向第一客户端提出预先确定的附加问题,并从第一客户端获取用户针对所述附件问题的附加答案;When the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is manual verification, the predetermined additional problem is raised to the first client, and the user's additional answer to the attachment problem is obtained from the first client;将获取的附加答案与预先确定的标准附加答案进行比对分析;及Comparing the obtained additional answers with predetermined standard additional answers; and当所述附加答案与所述标准附加答案一致时,判断用户身份验证通过,或者,当所述附加答案与所述标准附加答案不一致时,判断用户身份验证失败。When the additional answer is consistent with the standard additional answer, it is determined that the user identity verification is passed, or when the additional answer is inconsistent with the standard additional answer, it is determined that the user identity verification fails.
- 一种身份验证服务器,其特征在于,该服务器包括:存储器、处理器,所述存储器上存储有可在所述处理器上运行的基于声纹识别的身份验证程序,该程序被所述处理器执行时实现如下步骤:An authentication server, characterized in that the server comprises: a memory, a processor, and a memoryprint recognition-based identity verification program executable on the processor, the program being stored by the processor The following steps are implemented during execution:接收第一客户端发送的带有用户身份标识的身份验证请求,从第一客户端采集用户的当前语音数据,为所述当前语音数据构建当前声纹鉴别向量,根据用户身份标识确定所述用户身份标识对应的标准声纹鉴别向量;Receiving an identity verification request with a user identity sent by the first client, collecting current voice data of the user from the first client, constructing a current voiceprint authentication vector for the current voice data, and determining the user according to the user identity identifier a standard voiceprint identification vector corresponding to the identity;利用预先确定的距离计算公式,计算当前声纹鉴别向量与标准声纹鉴别向量之间的距离,根据计算的距离分析是否通过声纹验证,并生成声纹验证结果发送给第一客户端;Using a predetermined distance calculation formula, calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client;当声纹验证结果为声纹验证通过时,从第二客户端获取人工验证结果;When the voiceprint verification result is that the voiceprint verification is passed, the manual verification result is obtained from the second client;当人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分析结果;及When the manual verification result is a manual verification failure, the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result;当验证分析结果为验证分析通过时,判断用户身份验证通过,或者,当验证分析结果为验证分析失败时,判断用户身份验证失败。When the verification analysis result is that the verification analysis passes, it is judged that the user identity verification is passed, or when the verification analysis result is that the verification analysis fails, it is judged that the user identity verification fails.
- 如权利要求9所述的身份验证服务器,其特征在于,该程序被所述处理器执行时还实现如下步骤:The identity verification server according to claim 9, wherein the program is further executed as follows when the program is executed by the processor:当声纹验证结果为声纹验证通过,且人工验证结果为人工验证通过时,判断用户身份验证通过;或When the voiceprint verification result is that the voiceprint verification is passed, and the manual verification result is manually verified, the user identity verification is determined to pass; or当声纹验证结果为声纹验证失败,且人工验证结果为人工验证失败时,判断用户身份验证失败。When the voiceprint verification result is that voiceprint verification fails, and the manual verification result is manual verification failure, it is determined that the user identity verification fails.
- 如权利要求9或10所述的身份验证服务器,其特征在于,所述“根据预先确定的分析算法再次对用户身份进行分析”的步骤具体包括:The authentication server according to claim 9 or 10, wherein the step of "analysing the user identity again according to the predetermined analysis algorithm" comprises:若对用户进行人工身份验证的问题是答案为第一类型答案的第一类型问题,根据预先确定的第一分析规则对用户针对该第一类型问题的第一类型答 案进行分析,输出验证分析结果;或If the problem of manual authentication for the user is that the answer is the first type of question of the first type of answer, the first type of answer for the first type of question is analyzed by the user according to the predetermined first analysis rule, and the result of the verification analysis is output. ;or若对用户进行人工身份验证的问题是答案为第二类型答案的第二类型问题,根据预先确定的第二分析规则对用户针对该第二类型问题的第二类型答案进行分析,输出验证分析结果。If the problem of manual authentication for the user is that the answer is the second type of question of the second type of answer, the second type of answer of the user for the second type of question is analyzed according to a predetermined second analysis rule, and the result of the verification analysis is output. .
- 如权利要求11所述的身份验证服务器,其特征在于,所述“根据预先确定的第一分析规则对用户针对该第一类型问题的第一类型答案进行分析”的步骤具体包括:The authentication server according to claim 11, wherein the step of: analyzing the first type of answer of the user for the first type of question according to the predetermined first analysis rule comprises:获取用户针对第一类型问题输入的第一类型答案,将第一类型答案和标准答案进行比对,识别出差异部分,并确定该差异部分的各个预设差异类型的差异数值;及Obtaining a first type of answer input by the user for the first type of question, comparing the first type of the answer with the standard answer, identifying the difference part, and determining the difference value of each preset difference type of the difference part;根据预先定义的预设差异类型与预设差异阈值的映射关系,将所述差异部分的各个预设差异类型的差异数值与对应的预设差异阈值进行比对分析,输出验证分析结果。According to a mapping relationship between the preset preset difference type and the preset difference threshold, the difference value of each preset difference type of the difference part is compared with the corresponding preset difference threshold, and the verification analysis result is output.
- 如权利要求12所述的身份验证服务器,其特征在于,所述预设差异类型包括差异部分数量、错误位数、区间差异度、区间匹配度。The identity verification server according to claim 12, wherein the preset difference type includes a difference portion number, an error number of bits, an interval difference degree, and an interval matching degree.
- 如权利要求11所述的身份验证服务器,其特征在于,所述“根据预先确定的第二分析规则对用户针对该第二类型问题的第二类型答案进行分析”的步骤具体包括:The authentication server according to claim 11, wherein the step of: analyzing the second type of answer of the user for the second type of question according to the predetermined second analysis rule comprises:获取用户针对第二类型问题输入的第二类型答案,将该第二类型答案转换成字符串;Obtaining a second type of answer input by the user for the second type of question, converting the second type of answer into a string;根据预先确定的第二类型答案差异值分析算法将所述字符串与预先确定的标准答案字符串进行比对分析,生成对应的第二类型答案差异值;及Comparing the character string with a predetermined standard answer string according to a predetermined second type of answer difference value analysis algorithm to generate a corresponding second type of answer difference value; and当所述第二类型答案差异值小于或者等于预设汉字答案阈值时,确定验证分析通过,或者,当所述第二类型答案差异值大于预设的第二类型答案差异值阈值时,确定验证分析失败。Determining that the verification analysis passes when the second type of answer difference value is less than or equal to the preset Chinese character answer threshold, or determining verification when the second type of answer difference value is greater than a preset second type of answer difference value threshold Analysis failed.
- 如权利要求14所述的身份验证服务器,其特征在于,所述“根据预先确定的第二类型答案差异值分析算法将所述字符串与预先确定的标准答案字符串进行比对分析,生成对应的第二类型答案差异值”的步骤具体包括:The identity verification server according to claim 14, wherein said "comparing said character string with a predetermined standard answer string according to a predetermined second type of answer difference value analysis algorithm to generate a correspondence The steps of the second type of answer difference value include:将转换的字符串逐字进行字母拆分,重新组合生成第二类型答案词包;Splitting the converted string word by word and recombining to generate a second type of answer word package;将所述第二类型答案词包与预先确定的标准答案词包进行字符匹配,生 成对应的字母匹配集合值;及Matching the second type of answer word package with a predetermined standard answer word package to generate a corresponding letter matching set value; and根据预先确定的计算公式计算所述字母匹配集合值与标准集合值之间的集合差异值,并将该集合差异值作为所述第二类型答案差异值。Calculating a set difference value between the letter matching set value and the standard set value according to a predetermined calculation formula, and using the set difference value as the second type answer difference value.
- 如权利要求9所述的身份验证服务器,其特征在于,该程序被所述处理器执行时还实现如下步骤:The identity verification server according to claim 9, wherein the program is further executed as follows when the program is executed by the processor:当声纹验证结果为声纹验证失败,且人工验证结果为人工验证通过时,向第一客户端提出预先确定的附加问题,并从第一客户端获取用户针对所述附件问题的附加答案;When the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is manual verification, the predetermined additional problem is raised to the first client, and the user's additional answer to the attachment problem is obtained from the first client;将获取的附加答案与预先确定的标准附加答案进行比对分析;及Comparing the obtained additional answers with predetermined standard additional answers; and当所述附加答案与所述标准附加答案一致时,判断用户身份验证通过,或者,当所述附加答案与所述标准附加答案不一致时,判断用户身份验证失败。When the additional answer is consistent with the standard additional answer, it is determined that the user identity verification is passed, or when the additional answer is inconsistent with the standard additional answer, it is determined that the user identity verification fails.
- 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储有基于声纹识别的身份验证程序,该程序被处理器执行时实现如下步骤:A computer readable storage medium, characterized in that the computer readable storage medium stores an identity verification program based on voiceprint recognition, and when the program is executed by the processor, the following steps are implemented:接收第一客户端发送的带有用户身份标识的身份验证请求,从第一客户端采集用户的当前语音数据,为所述当前语音数据构建当前声纹鉴别向量,根据用户身份标识确定所述用户身份标识对应的标准声纹鉴别向量;Receiving an identity verification request with a user identity sent by the first client, collecting current voice data of the user from the first client, constructing a current voiceprint authentication vector for the current voice data, and determining the user according to the user identity identifier a standard voiceprint identification vector corresponding to the identity;利用预先确定的距离计算公式,计算当前声纹鉴别向量与标准声纹鉴别向量之间的距离,根据计算的距离分析是否通过声纹验证,并生成声纹验证结果发送给第一客户端;Using a predetermined distance calculation formula, calculating a distance between the current voiceprint discrimination vector and the standard voiceprint discrimination vector, analyzing whether the voiceprint verification is performed according to the calculated distance, and generating a voiceprint verification result and transmitting the result to the first client;当声纹验证结果为声纹验证通过时,从第二客户端获取人工验证结果;When the voiceprint verification result is that the voiceprint verification is passed, the manual verification result is obtained from the second client;当人工验证结果为人工验证失败时,根据预先确定的分析算法再次对用户身份进行分析,生成验证分析结果;及When the manual verification result is a manual verification failure, the user identity is analyzed again according to a predetermined analysis algorithm to generate a verification analysis result;当验证分析结果为验证分析通过时,判断用户身份验证通过,或者,当验证分析结果为验证分析失败时,判断用户身份验证失败。When the verification analysis result is that the verification analysis passes, it is judged that the user identity verification is passed, or when the verification analysis result is that the verification analysis fails, it is judged that the user identity verification fails.
- 如权利要求17所述的计算机可读存储介质,其特征在于,该程序被所述处理器执行时还实现如下步骤:The computer readable storage medium of claim 17, wherein the program, when executed by the processor, further implements the following steps:当声纹验证结果为声纹验证通过,且人工验证结果为人工验证通过时,判断用户身份验证通过;或When the voiceprint verification result is that the voiceprint verification is passed, and the manual verification result is manually verified, the user identity verification is determined to pass; or当声纹验证结果为声纹验证失败,且人工验证结果为人工验证失败时,判断用户身份验证失败。When the voiceprint verification result is that voiceprint verification fails, and the manual verification result is manual verification failure, it is determined that the user identity verification fails.
- 如权利要求18所述的计算机可读存储介质,其特征在于,所述“根据预先确定的分析算法再次对用户身份进行分析”的步骤具体包括:The computer readable storage medium according to claim 18, wherein the step of "analyzing the user identity again according to a predetermined analysis algorithm" comprises:若对用户进行人工身份验证的问题是答案为第一类型答案的第一类型问题,根据预先确定的第一分析规则对用户针对该第一类型问题的第一类型答案进行分析,输出验证分析结果;或If the problem of manual authentication for the user is that the answer is the first type of question of the first type of answer, the first type of answer for the first type of question is analyzed by the user according to the predetermined first analysis rule, and the result of the verification analysis is output. ;or若对用户进行人工身份验证的问题是答案为第二类型答案的第二类型问题,根据预先确定的第二分析规则对用户针对该第二类型问题的第二类型答案进行分析,输出验证分析结果。If the problem of manual authentication for the user is that the answer is the second type of question of the second type of answer, the second type of answer of the user for the second type of question is analyzed according to a predetermined second analysis rule, and the result of the verification analysis is output. .
- 如权利要求19所述的计算机可读存储介质,其特征在于,该程序被所述处理器执行时还实现如下步骤:The computer readable storage medium of claim 19, wherein the program, when executed by the processor, further implements the following steps:当声纹验证结果为声纹验证失败,且人工验证结果为人工验证通过时,向第一客户端提出预先确定的附加问题,并从第一客户端获取用户针对所述附件问题的附加答案;When the voiceprint verification result is that the voiceprint verification fails, and the manual verification result is manual verification, the predetermined additional problem is raised to the first client, and the user's additional answer to the attachment problem is obtained from the first client;将获取的附加答案与预先确定的标准附加答案进行比对分析;及当所述附加答案与所述标准附加答案一致时,判断用户身份验证通过,或者,当所述附加答案与所述标准附加答案不一致时,判断用户身份验证失败。Comparing the obtained additional answer with a predetermined standard additional answer; and when the additional answer is consistent with the standard additional answer, determining that the user identity is verified, or when the additional answer is attached to the standard When the answers are inconsistent, it is judged that the user authentication failed.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810311087.2A CN108768654B (en) | 2018-04-09 | 2018-04-09 | Identity verification method based on voiceprint recognition, server and storage medium |
CN201810311087.2 | 2018-04-09 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019196302A1 true WO2019196302A1 (en) | 2019-10-17 |
Family
ID=63981529
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2018/102122 WO2019196302A1 (en) | 2018-04-09 | 2018-08-24 | Voiceprint recognition-based identity authentication method, server and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108768654B (en) |
WO (1) | WO2019196302A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115565539A (en) * | 2022-11-21 | 2023-01-03 | 中网道科技集团股份有限公司 | Data processing method for realizing self-help correction terminal anti-counterfeiting identity verification |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109522693A (en) * | 2018-11-19 | 2019-03-26 | 中国银行股份有限公司 | Information processing method, device, electronic equipment and readable storage medium storing program for executing |
CN111199742A (en) * | 2018-11-20 | 2020-05-26 | 阿里巴巴集团控股有限公司 | Identity verification method and device and computing equipment |
CN111462760B (en) * | 2019-01-21 | 2023-09-26 | 阿里巴巴集团控股有限公司 | Voiceprint recognition system, voiceprint recognition method, voiceprint recognition device and electronic equipment |
CN109994118B (en) * | 2019-04-04 | 2022-10-11 | 平安科技(深圳)有限公司 | Voice password verification method and device, storage medium and computer equipment |
CN110111796B (en) * | 2019-06-24 | 2021-09-17 | 秒针信息技术有限公司 | Identity recognition method and device |
CN110472579A (en) * | 2019-08-16 | 2019-11-19 | 中国银行股份有限公司 | Identity checking method, device, equipment and readable storage medium storing program for executing in business processing |
CN110808053B (en) * | 2019-10-09 | 2022-05-03 | 深圳市声扬科技有限公司 | Driver identity verification method and device and electronic equipment |
CN111181981A (en) * | 2019-12-31 | 2020-05-19 | 联想(北京)有限公司 | Processing method and device and computer equipment |
CN111833068A (en) * | 2020-07-31 | 2020-10-27 | 重庆富民银行股份有限公司 | Identity verification system and method based on voiceprint recognition |
CN113242331B (en) * | 2021-05-11 | 2023-05-09 | 鸬鹚科技(深圳)有限公司 | Different types of address conversion method, device, computer equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160132866A1 (en) * | 2014-03-13 | 2016-05-12 | Tencent Technology (Shenzhen) Company Limited | Device, system, and method for creating virtual credit card |
CN105740683A (en) * | 2016-01-20 | 2016-07-06 | 北京信安盟科技有限公司 | Multi-factor, multi-engine and human-computer combined identity verification method and system |
CN105844246A (en) * | 2016-03-25 | 2016-08-10 | 杭州信鸽金融信息服务股份有限公司 | Face recognition and second-generation ID card identification system with single camera cabinet machine |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090305667A1 (en) * | 2007-04-24 | 2009-12-10 | Schultz Michael J | Method and system for mobile identity verification and security |
CN101494540A (en) * | 2009-03-04 | 2009-07-29 | 北京英立讯科技有限公司 | Remote voice identification authentication system and method |
US20110260832A1 (en) * | 2010-04-27 | 2011-10-27 | Joe Ross | Secure voice biometric enrollment and voice alert delivery system |
CN102737634A (en) * | 2012-05-29 | 2012-10-17 | 百度在线网络技术(北京)有限公司 | Authentication method and device based on voice |
CN105323218A (en) * | 2014-06-30 | 2016-02-10 | 腾讯科技(深圳)有限公司 | Identity verifying method and device |
CN107068154A (en) * | 2017-03-13 | 2017-08-18 | 平安科技(深圳)有限公司 | The method and system of authentication based on Application on Voiceprint Recognition |
-
2018
- 2018-04-09 CN CN201810311087.2A patent/CN108768654B/en active Active
- 2018-08-24 WO PCT/CN2018/102122 patent/WO2019196302A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160132866A1 (en) * | 2014-03-13 | 2016-05-12 | Tencent Technology (Shenzhen) Company Limited | Device, system, and method for creating virtual credit card |
CN105740683A (en) * | 2016-01-20 | 2016-07-06 | 北京信安盟科技有限公司 | Multi-factor, multi-engine and human-computer combined identity verification method and system |
CN105844246A (en) * | 2016-03-25 | 2016-08-10 | 杭州信鸽金融信息服务股份有限公司 | Face recognition and second-generation ID card identification system with single camera cabinet machine |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115565539A (en) * | 2022-11-21 | 2023-01-03 | 中网道科技集团股份有限公司 | Data processing method for realizing self-help correction terminal anti-counterfeiting identity verification |
CN115565539B (en) * | 2022-11-21 | 2023-02-07 | 中网道科技集团股份有限公司 | Data processing method for realizing self-help correction terminal anti-counterfeiting identity verification |
Also Published As
Publication number | Publication date |
---|---|
CN108768654B (en) | 2020-04-21 |
CN108768654A (en) | 2018-11-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019196302A1 (en) | Voiceprint recognition-based identity authentication method, server and storage medium | |
US11308189B2 (en) | Remote usage of locally stored biometric authentication data | |
WO2019179036A1 (en) | Deep neural network model, electronic device, identity authentication method, and storage medium | |
WO2019196303A1 (en) | User identity authentication method, server and storage medium | |
US7676069B2 (en) | Method and apparatus for rolling enrollment for signature verification | |
WO2019227578A1 (en) | Voice acquisition method and apparatus, computer device and storage medium | |
US20160014120A1 (en) | Method, server, client and system for verifying verification codes | |
AU2019203697A1 (en) | Intelligent data extraction | |
WO2018090641A1 (en) | Method, apparatus and device for identifying insurance policy number, and computer-readable storage medium | |
CN108053545B (en) | Certificate verification method and device, server and storage medium | |
US10109215B2 (en) | Academic integrity protection | |
CN106549973A (en) | A kind of client and its method of work based on living things feature recognition | |
US8752144B1 (en) | Targeted biometric challenges | |
CN110288755A (en) | The invoice method of inspection, server and storage medium based on text identification | |
CN113837113B (en) | Document verification method, device, equipment and medium based on artificial intelligence | |
WO2021212874A1 (en) | Palm print mismatching point elimination method, apparatus, and device, and storage medium | |
CN114386013A (en) | Automatic student status authentication method and device, computer equipment and storage medium | |
WO2015032303A1 (en) | Character radical-based method for online handwriting authentication and template expansion | |
CN111767543A (en) | Method, device and equipment for determining replay attack vulnerability and readable storage medium | |
CN107615299A (en) | For assessing the method and system of fingerprint template | |
CN112308070B (en) | Identification method and device for certificate information, equipment and computer readable storage medium | |
US11934498B2 (en) | Method and system of user identification | |
CN107896208A (en) | A kind of identity identifying method and system | |
CN113868210A (en) | Validity verification method, system, equipment and storage medium for imported data | |
CN109961154A (en) | A kind of flag data generation method of artificial intelligence learning database |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18914357 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 20/01/2021) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18914357 Country of ref document: EP Kind code of ref document: A1 |