CN104717219B - Vocal print login method and device based on artificial intelligence - Google Patents
Vocal print login method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN104717219B CN104717219B CN201510125684.2A CN201510125684A CN104717219B CN 104717219 B CN104717219 B CN 104717219B CN 201510125684 A CN201510125684 A CN 201510125684A CN 104717219 B CN104717219 B CN 104717219B
- Authority
- CN
- China
- Prior art keywords
- login
- user
- pseudorandom
- character string
- string
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000001755 vocal effect Effects 0.000 title claims abstract description 79
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 32
- 239000000284 extract Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Machine Translation (AREA)
- Information Transfer Between Computers (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of vocal print login method and device based on artificial intelligence, wherein, method includes:S1, the logging request of receive user;S2, according to logging request generate pseudorandom log in character string;S3, by pseudorandom login character string provide to user, and receive user read pseudorandom log in character string voice messaging;And S4, login authentication is carried out to user according to voice messaging.The vocal print login method based on artificial intelligence of the embodiment of the present invention and device, by the logging request of receive user, pseudorandom is generated according to logging request and logs in character string, pseudorandom login character string is provided to user, and receive user reads the voice messaging that pseudorandom logs in character string, and login authentication is carried out to user according to voice messaging, it is effectively improved the success rate of vocal print login, improve performance, and improve the availability of vocal print login, multiformity ensure that will not be cheated by recording, so as to improve the safety of vocal print login.
Description
Technical field
A kind of the present invention relates to technical field of voice recognition, more particularly to vocal print login method and dress based on artificial intelligence
Put.
Background technology
Application on Voiceprint Recognition is one kind of biological identification technology, can be known according to the pronunciation physiology of speaker and behavior characteristicss
Do not verify, so that it is determined that the identity of speaker.At present, increasing application begins to use vocal print login system, relative to biography
The login mode of system, vocal print is difficult imitated, and therefore safe coefficient is higher.
At present, existing vocal print is logged in:The first obtains user for generating random character string
The vocal print produced during random string is read, is then verified and is logged in;For generating fixed character string, obtain and use for second
The vocal print produced during fixed character string is read at family, is then verified and is logged in.
But, first method uses random string, does not account for the impact for cooperateing with sounding when people continuously read aloud,
Cause to login successfully rate step-down, performance is not good;Second method uses fixed character string, although avoid the shadow of collaboration sounding
Ring, but lack change, easily cheated by recording.
Content of the invention
It is contemplated that at least solving one of technical problem in correlation technique to a certain extent.For this purpose, the present invention
One purpose is to propose a kind of vocal print login method based on artificial intelligence, the method be effectively improved vocal print login into
Power, improves performance, and improves the availability that vocal print is logged in, and multiformity ensure that will not be cheated by recording, so as to improve
The safety that vocal print is logged in.
Second object of the present invention is to propose a kind of vocal print entering device based on artificial intelligence.
It is that embodiment proposes a kind of vocal print based on artificial intelligence and logs according to a first aspect of the present invention up to above-mentioned purpose
Method, including:S1, the logging request of receive user;S2, according to the logging request generate pseudorandom log in character string;S3, general
The pseudorandom logs in character string and provides to the user, and receives the language that the user reads the pseudorandom login character string
Message ceases;And S4, login authentication is carried out to the user according to the voice messaging.
The vocal print login method based on artificial intelligence of the embodiment of the present invention, by the logging request of receive user, according to
Logging request generates pseudorandom and logs in character string, and pseudorandom login character string is provided to user, and receive user read pseudo- with
Machine logs in the voice messaging of character string, and carries out login authentication according to voice messaging to user, is effectively improved vocal print and steps on
The success rate of record, improves performance, and improves the availability that vocal print is logged in, and multiformity ensure that will not be cheated by recording, from
And improve the safety of vocal print login.
It is that embodiment proposes a kind of vocal print based on artificial intelligence and logs according to a second aspect of the present invention up to above-mentioned purpose
Device, including:Receiver module, for the logging request of receive user;Generation module, pseudo- for being generated according to the logging request
Random login character string;First provides module, for providing pseudorandom login character string to the user, and receives institute
State user and read the voice messaging that the pseudorandom logs in character string;And authentication module, for according to the voice messaging pair
The user carries out login authentication.
The vocal print entering device based on artificial intelligence of the embodiment of the present invention, by the logging request of receive user, according to
Logging request generates pseudorandom and logs in character string, and pseudorandom login character string is provided to user, and receive user read pseudo- with
Machine logs in the voice messaging of character string, and carries out login authentication according to voice messaging to user, is effectively improved vocal print and steps on
The success rate of record, improves performance, and improves the availability that vocal print is logged in, and multiformity ensure that will not be cheated by recording, from
And improve the safety of vocal print login.
The additional aspect and advantage of the present invention will be set forth in part in the description, and partly will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Description of the drawings
Fig. 1 is the flow chart of the vocal print login method based on artificial intelligence according to one embodiment of the invention.
Fig. 2 is the flow chart of the vocal print login method based on artificial intelligence according to another embodiment of the present invention.
Fig. 3 is the structural representation one of the vocal print entering device based on artificial intelligence according to one embodiment of the invention.
Fig. 4 is the structural representation two of the vocal print entering device based on artificial intelligence according to one embodiment of the invention.
Specific embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from start to finish
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and be not considered as limiting the invention.
Below with reference to the accompanying drawings the vocal print login method based on artificial intelligence and device of the embodiment of the present invention are described.
Fig. 1 is the flow chart of the vocal print login method based on artificial intelligence according to one embodiment of the invention.
As shown in figure 1, should be included based on the vocal print login method of artificial intelligence:
S1, the logging request of receive user.
As an example it is assumed that the vocal print login method of the artificial intelligence of the embodiment of the present invention is applied to website log system
In, when user opens website to be prepared to log in, user can pass through client and send logging request to login system.
S2, according to logging request generate pseudorandom log in character string.
After logging request is received, pseudorandom can be generated according to logging request and log in character string.Wherein, pseudorandom is stepped on
Record character string is arranged in a combination by character is regular, and not completely random is generated.Pseudorandom logs in character string and seems
It is randomly generated, but actually meets certain rule.Pseudorandom logs in character string and may include but be not limited to numeral.
Specifically, generating pseudorandom login character string may include following steps:
S21, multigroup two characters of acquisition, wherein, two characters are made up of two adjacent characters.
As an example it is assumed that it is eight-digit number word that pseudorandom logs in character string, then, in 0 to 9 this ten numerals, can constitute
01st, 12,23,34,45,56,67,78,89,900 groups of two digits, can therefrom randomly select four groups.
S22, multigroup two characters are carried out random alignment combination, character string is logged in generate pseudorandom.
Example is connected, permutation and combination is carried out to the four groups of two digits for randomly selecting, character string is logged in generate pseudorandom, such as
When removing 0 and 5 " 67341289 ", " 12346789 " for obtaining etc., or remove obtain when 1 and 6 " 23457890 ",
" 78239045 " etc..
S3, by pseudorandom login character string provide to user, and receive user read pseudorandom log in character string voice
Information.
After pseudorandom login character string is generated, pseudorandom login character string can be provided to user.User is seeing this
After pseudorandom logs in character string, the pseudorandom can be read and log in character string, so as to generate corresponding voice messaging.Then can receive
User reads the voice messaging that the pseudorandom logs in text string generation.
S4, login authentication is carried out to user according to voice messaging.
Specifically, carrying out login authentication to user may include following steps:
S41, carry out speech recognition to obtain the corresponding text message of voice messaging to voice messaging.
For example, what user read is " 67341289 ", then can carry out speech recognition to the voice messaging, and be converted to corresponding
Text " 67341289 ".
S42, text message and pseudorandom are logged in character string mated.
Example is connected, and user is read the text " 67341289 " after conversion and character string is logged in the pseudorandom provided to user
Mated.
S43, such as consistent, then voice print matching is carried out to voice messaging further.
If consistent both above-mentioned, voice print matching can be carried out to voice messaging further.If both are inconsistent, can
Can user misread when reading or recognize mistake during speech recognition.
If S44 voice print matchings pass through, judge that user passes through login authentication.
After voice print matching being carried out to voice messaging, if voice print matching passes through, can determine that user by login authentication,
User successfully can be logged in.If voice print matching does not pass through, user cannot be logged in.
The vocal print login method based on artificial intelligence of the embodiment of the present invention, by the logging request of receive user, according to
Logging request generates pseudorandom and logs in character string, and pseudorandom login character string is provided to user, and receive user read pseudo- with
Machine logs in the voice messaging of character string, and carries out login authentication according to voice messaging to user, is effectively improved vocal print and steps on
The success rate of record, improves performance, and improves the availability that vocal print is logged in, and multiformity ensure that will not be cheated by recording, from
And improve the safety of vocal print login.
Fig. 2 is the flow chart of the vocal print login method based on artificial intelligence according to another embodiment of the present invention.
As shown in Fig. 2 should be included based on the vocal print login method of artificial intelligence:
S5, the registration request of receive user, generate M login-string according to registration request, and by M login-string
There is provided to user.
As an example it is assumed that the vocal print login method of the artificial intelligence of the embodiment of the present invention is applied to website log system
In, when user opens website prepares registration, user can pass through client and send registration request to login system.Wherein,
Login-string is also pseudorandom, is arranged in a combination by character is regular, and not completely random is generated.Registered word
Symbol string may include but be not limited to numeral.
After the registration request of receive user, M login-string can be generated according to registration request, be comprised the following steps that:
S51, acquisition N two characters of group, wherein, two characters are made up of two adjacent characters.
S52, two characters of N groups are carried out random alignment combination, generate M login-string.
As an example it is assumed that login-string is eight-digit number word, then in 0 to 9 this ten numerals, 01 can be constituted, 12,
23rd, 34,45,56,67,78,89,900 groups of two digits, can therefrom randomly select four groups of two digits, and permutation and combination generates eight
The login-string of position.In order that login-string can travel through all sample spaces, need to remove different numerals one by one,
And numeral can not repeat in each numeric string, that is, 10 groups of two digits are traveled through, generate 5 numeric strings.Specifically, first
Individual numeric string removes 0 and 5, uses " 12 ", " 34 ", " 67 ", " 89 " four groups of two digits to constitute numeric string at random, such as
“12673489”.Second digit string removes 1 and 6, uses " 23 ", " 45 ", " 78 ", " 90 " four groups of two digits to constitute number at random
Word string, such as " 78452390 ".Third digit string remove 2 and 7, use " 01 ", " 34 ", " 56 ", " 78 " four groups of two digits with
Machine constitutes numeric string, such as " 78563401 ".Fourth digit string removes 3 and 8, uses " 12 ", " 45 ", " 67 ", four group two of " 90 "
Bit digital constitutes numeric string at random, such as " 90124567 ".5th numeric string removes 4 and 9, use " 01 ", " 23 ", " 56 ",
" 78 " four groups of two digits constitute numeric string at random, such as " 78015623 ".Above-mentioned 5 numeric strings do not repeat, and 0 to 9
Ten numerals occur in 5 numeric strings 4 times.
After login-string is generated, user can be provided to, so that user is carried out after seeing above-mentioned login-string
Read.
S6, receive user read the voice messaging of M login-string, and extract the vocal print of user.
After user reads the login-string for providing, corresponding voice messaging can be received, then extract the vocal print of user,
So that user is when logging in, the vocal print of user is mated.
S1, the logging request of receive user.
As an example it is assumed that the vocal print login method of the artificial intelligence of the embodiment of the present invention is applied to website log system
In, when user opens website to be prepared to log in, user can pass through client and send logging request to login system.
S2, according to logging request generate pseudorandom log in character string.
After logging request is received, pseudorandom can be generated according to logging request and log in character string.Wherein, pseudorandom is stepped on
Record character string is arranged in a combination by character is regular, and not completely random is generated.Pseudorandom logs in character string and seems
It is randomly generated, but actually meets certain rule.Pseudorandom logs in character string and may include but be not limited to numeral.
Specifically, generating pseudorandom login character string may include following steps:
S21, multigroup two characters of acquisition, wherein, two characters are made up of two adjacent characters.
As an example it is assumed that it is eight-digit number word that pseudorandom logs in character string, then, in 0 to 9 this ten numerals, can constitute
01st, 12,23,34,45,56,67,78,89,900 groups of two digits, can therefrom randomly select four groups.
S22, multigroup two characters are carried out random alignment combination, character string is logged in generate pseudorandom.
Example is connected, permutation and combination is carried out to the four groups of two digits for randomly selecting, character string is logged in generate pseudorandom, such as
When removing 0 and 5 " 67341289 ", " 12346789 " for obtaining etc., or remove obtain when 1 and 6 " 23457890 ",
" 78239045 " etc.
S3, by pseudorandom login character string provide to user, and receive user read pseudorandom log in character string voice
Information.
After pseudorandom login character string is generated, pseudorandom login character string can be provided to user.User is seeing this
After pseudorandom logs in character string, the pseudorandom can be read and log in character string, so as to generate corresponding voice messaging.Then life is received
Into voice messaging.
S4, login authentication is carried out to user according to voice messaging.
Specifically, carrying out login authentication to user may include following steps:
S41, carry out speech recognition to obtain the corresponding text message of voice messaging to voice messaging.
For example, what user read is " 67341289 ", then can carry out speech recognition to the voice messaging, and be converted to corresponding
Text " 67341289 ".
S42, text message and pseudorandom are logged in character string mated.
Example is connected, and user is read the text " 67341289 " after conversion and character string is logged in the pseudorandom provided to user
Mated.
S43, such as consistent, then voice print matching is carried out to voice messaging further.
If consistent both above-mentioned, voice print matching can be carried out to voice messaging further.If both are inconsistent, can
Can user misread when reading or recognize mistake during speech recognition.
If S44 voice print matchings pass through, judge that user passes through login authentication.
After voice print matching being carried out to voice messaging, if voice print matching passes through, can determine that user by login authentication,
User successfully can be logged in.If voice print matching does not pass through, user cannot be logged in.
The vocal print login method based on artificial intelligence of the embodiment of the present invention, by the logging request of receive user, according to
Logging request generates pseudorandom and logs in character string, and pseudorandom login character string is provided to user, and receive user read pseudo- with
Machine logs in the voice messaging of character string, and carries out login authentication according to voice messaging to user, is effectively improved vocal print and steps on
The success rate of record, improves performance, and improves the availability that vocal print is logged in, and multiformity ensure that will not be cheated by recording.This
Outward, by generating pseudorandom login-string, the impact of collaboration sounding has been taken into full account so that vocal print is more filled when logging in modeling
Point, checking log in when more reasonable, it is ensured that vocal print log in when safety.
In order to realize that above-described embodiment, the present invention also propose a kind of vocal print entering device based on artificial intelligence.
Fig. 3 is the structural representation of the vocal print entering device based on artificial intelligence according to one embodiment of the invention.
As shown in figure 3, should be included based on the vocal print entering device of artificial intelligence:Receiver module 110, generation module 120,
One provides module 130 and authentication module 140.Wherein, generation module 120 may include acquiring unit 121 and signal generating unit 122.
Authentication module 140 may include recognition unit 141, the first matching unit 142, the second matching unit 143 and authentication unit 144.
Specifically, receiver module 110 is used for the logging request of receive user.
As an example it is assumed that the vocal print login method of the artificial intelligence of the embodiment of the present invention is applied to website log system
In, when user opens website to be prepared to log in, user can pass through client and send logging request to login system.
Generation module 120 is used for generating pseudorandom login character string according to logging request.
After receiver module 110 receives logging request, pseudorandom can be generated according to logging request and log in character string.Its
In, pseudorandom logs in character string and is arranged in a combination by character is regular, and not completely random is generated.Pseudorandom is logged in
Character string is seemed and is randomly generated, but actually meets certain rule.Pseudorandom logs in character string and may include but do not limit
In numeral.
Specifically, generation module 120 may include acquiring unit 121 and signal generating unit 122.
Acquiring unit 121 is used for obtaining multigroup two characters, and wherein, two characters are made up of two adjacent characters.
Signal generating unit 122 is used for for multigroup two characters carrying out random alignment combination, logs in character string to generate pseudorandom.
As an example it is assumed that it is eight-digit number word that pseudorandom logs in character string, then, in 0 to 9 this ten numerals, can constitute
01st, 12,23,34,45,56,67,78,89,900 groups of two digits, can therefrom randomly select four groups.Then to randomly selecting
Four groups of two digits carry out permutation and combination, log in character string to generate pseudorandom, " 67341289 " obtained when such as removing 0 and 5,
" 23457890 ", " 78239045 " obtained when " 12346789 " etc., or removal 1 and 6 etc..
First offer module 130 is used for providing pseudorandom login character string to user, and receive user reads pseudorandom
Log in the voice messaging of character string.
After generation module 120 generates pseudorandom login character string, pseudorandom can be logged in character by the first offer module 130
String is provided to user.User after seeing that the pseudorandom logs in character string can read the pseudorandom and log in character string, so as to generate
Corresponding voice messaging.Then the first offer module 130 can receive user read the voice that the pseudorandom logs in text string generation
Information.
Authentication module 140 is used for carrying out login authentication according to voice messaging to user.
Authentication module 140 may include that recognition unit 141, the first matching unit 142, the second matching unit 143 and checking are single
Unit 144.
Recognition unit 141 is used for carrying out speech recognition to obtain the corresponding text message of voice messaging to voice messaging.
First matching unit 142 is used for being mated text message and pseudorandom login character string.
Second matching unit 143 is used for when text message and pseudorandom log in string matching success, further to language
Message breath carries out voice print matching.
Authentication unit 144 is used for, when voice print matching passes through, judging that user passes through login authentication.
For example, what user read is " 67341289 ", and recognition unit 141 can carry out voice knowledge to the voice messaging
Not, and corresponding text " 67341289 " is converted to.User is read first matching unit 142 text after conversion
" 67341289 " log in character string with the pseudorandom provided to user and are mated.If both consistent, second couplings above-mentioned
Unit 143 further can carry out voice print matching to voice messaging.If both are inconsistent, possible user read when misread or
Mistake is recognized during person's speech recognition.After the second matching unit 143 carries out voice print matching to voice messaging, if voice print matching is logical
Cross, then authentication unit 144 can determine that user by login authentication, and user successfully can be logged in.If voice print matching is not
Pass through, then user cannot be logged in.
Additionally, as shown in figure 4, may also include the second offer module 150 based on the vocal print entering device of artificial intelligence and carry
Delivery block 160.
Second provides the registration request that module 150 is used for receive user, generates M login-string according to registration request,
And provide M login-string to user.
As an example it is assumed that the vocal print login method of the artificial intelligence of the embodiment of the present invention is applied to website log system
In, when user opens website prepares registration, user can pass through client and send registration request to login system.Wherein,
Login-string is also pseudorandom, is arranged in a combination by character is regular, and not completely random is generated.Registered word
Symbol string may include but be not limited to numeral.
Specifically, the second offer module 150 is used for obtaining two characters of N groups, then arranges two characters of N groups at random
Row combination, generates M login-string.Wherein, two characters are made up of two adjacent characters.
As an example it is assumed that login-string is eight-digit number word, then in 0 to 9 this ten numerals, 01 can be constituted, 12,
23rd, 34,45,56,67,78,89,900 groups of two digits, can therefrom randomly select four groups of two digits, and permutation and combination generates eight
The login-string of position.In order that login-string can travel through all sample spaces, need to remove different numerals one by one,
And numeral can not repeat in each numeric string, that is, 10 groups of two digits are traveled through, generate 5 numeric strings.Specifically, first
Individual numeric string removes 0 and 5, uses " 12 ", " 34 ", " 67 ", " 89 " four groups of two digits to constitute numeric string at random, such as
“12673489”.Second digit string removes 1 and 6, uses " 23 ", " 45 ", " 78 ", " 90 " four groups of two digits to constitute number at random
Word string, such as " 78452390 ".Third digit string remove 2 and 7, use " 01 ", " 34 ", " 56 ", " 78 " four groups of two digits with
Machine constitutes numeric string, such as " 78563401 ".Fourth digit string removes 3 and 8, uses " 12 ", " 45 ", " 67 ", four group two of " 90 "
Bit digital constitutes numeric string at random, such as " 90124567 ".5th numeric string removes 4 and 9, use " 01 ", " 23 ", " 56 ",
" 78 " four groups of two digits constitute numeric string at random, such as " 78015623 ".Above-mentioned 5 numeric strings do not repeat, and 0 to 9
Ten numerals occur in 5 numeric strings 4 times.
After M login-string is generated, the second offer module 150 can provide M login-string to user
Extraction module 160 is used for the voice messaging that receive user reads M login-string, and extracts the vocal print of user.
After user reads the second login-string for providing the offer of module 150, extraction module 160 can receive corresponding language
Message ceases, and then extracts the vocal print of user, so that user is when logging in, the vocal print of user is mated.
The vocal print entering device based on artificial intelligence of the embodiment of the present invention, by the logging request of receive user, according to
Logging request generates pseudorandom and logs in character string, and pseudorandom login character string is provided to user, and receive user read pseudo- with
Machine logs in the voice messaging of character string, and carries out login authentication according to voice messaging to user, is effectively improved vocal print and steps on
The success rate of record, improves performance, and improves the availability that vocal print is logged in, and multiformity ensure that will not be cheated by recording, from
And improve the safety of vocal print login.Additionally, by generating pseudorandom login-string, having taken into full account collaboration sounding
Affect so that it is more reasonable when logging in that vocal print logs in more abundant during modeling, checking, it is ensured that safety when vocal print is logged in.
Additionally, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or
Implicitly include at least one this feature.In describing the invention, " multiple " are meant that at least two, such as two, three
Individual etc., unless otherwise expressly limited specifically.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy described with reference to the embodiment or example
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be with office
Combined in one or more embodiments or example in an appropriate manner.Additionally, in the case of not conflicting, the skill of this area
The feature of the different embodiments or example described in this specification and different embodiments or example can be tied by art personnel
Close and combine.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (10)
1. a kind of vocal print login method based on artificial intelligence, it is characterised in that comprise the following steps:
S1, the logging request of receive user;
S2, according to the logging request generate pseudorandom log in character string;
S3, pseudorandom login character string is provided to the user, and receive the user and read the pseudorandom and log in
The voice messaging of character string;And
S4, login authentication is carried out to the user according to the voice messaging;
Wherein, the generation pseudorandom logs in character string, specifically includes:
S21, multigroup two characters of acquisition, wherein, two characters are made up of two adjacent characters;
S22, multigroup two characters are carried out random alignment combination, character string is logged in generate the pseudorandom.
2. the vocal print login method based on artificial intelligence as claimed in claim 1, it is characterised in that described according to the voice
Information carries out login authentication to the user, specifically includes:
S41, carry out speech recognition to obtain the corresponding text message of the voice messaging to the voice messaging;
S42, the text message and the pseudorandom are logged in character string mated;
S43, such as consistent, then voice print matching is carried out to the voice messaging further;And
If S44 voice print matchings pass through, judge that the user passes through login authentication.
3. the vocal print login method based on artificial intelligence as claimed in claim 1, it is characterised in that step S1 it
Before, also include:
S5, the registration request for receiving the user, generate M login-string according to the registration request, and by M registered word
Symbol string is provided to the user;And
S6, the voice messaging for receiving the M login-string of user's reading, and extract the vocal print of the user.
4. the vocal print login method based on artificial intelligence as claimed in claim 3, it is characterised in that described according to the registration
Request generates M login-string, specifically includes:
S51, acquisition N two characters of group, wherein, two characters are made up of two adjacent characters;
S52, two characters of the N groups are carried out random alignment combination, to generate the M login-string.
5. the vocal print login method based on artificial intelligence as described in any one of claim 1-4, it is characterised in that described pseudo- with
Machine logs in character string and the login-string for numeral.
6. a kind of vocal print entering device based on artificial intelligence, it is characterised in that include:
Receiver module, for the logging request of receive user;
Generation module, logs in character string for generating pseudorandom according to the logging request;
First provides module, for providing pseudorandom login character string to the user, and receives user's reading
The pseudorandom logs in the voice messaging of character string;And
Authentication module, for carrying out login authentication according to the voice messaging to the user;
Wherein, the generation module, specifically includes:
Acquiring unit, for obtaining multigroup two characters, wherein, two characters are made up of two adjacent characters;
Signal generating unit, for multigroup two characters are carried out random alignment combination, logs in character to generate the pseudorandom
String.
7. the vocal print entering device based on artificial intelligence as claimed in claim 6, it is characterised in that the authentication module, tool
Body includes:
Recognition unit, for carrying out speech recognition to obtain the corresponding text message of the voice messaging to the voice messaging;
First matching unit, is mated for the text message and the pseudorandom are logged in character string;
Second matching unit, for when the text message and the pseudorandom log in string matching success, further right
The voice messaging carries out voice print matching;And
Authentication unit, for when voice print matching passes through, judging that the user passes through login authentication.
8. the vocal print entering device based on artificial intelligence as claimed in claim 6, it is characterised in that described device, also includes:
Second provides module, for receiving the registration request of the user, generates M registration character according to the registration request
String, and M login-string is provided to the user;And
Extraction module, reads the voice messaging of the M login-string, and extracts the user's for receiving the user
Vocal print.
9. the vocal print entering device based on artificial intelligence as claimed in claim 8, it is characterised in that described second provides mould
Block, specifically for:
N two characters of group are obtained, and two characters of the N groups are carried out random alignment combination, generate the M registration character
String, wherein, two characters are made up of two adjacent characters.
10. the vocal print entering device based on artificial intelligence as described in any one of claim 6-9, it is characterised in that the puppet
Random character string and the login-string of logging in is for numeral.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510125684.2A CN104717219B (en) | 2015-03-20 | 2015-03-20 | Vocal print login method and device based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510125684.2A CN104717219B (en) | 2015-03-20 | 2015-03-20 | Vocal print login method and device based on artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104717219A CN104717219A (en) | 2015-06-17 |
CN104717219B true CN104717219B (en) | 2017-03-15 |
Family
ID=53416181
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510125684.2A Active CN104717219B (en) | 2015-03-20 | 2015-03-20 | Vocal print login method and device based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104717219B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105139857B (en) * | 2015-09-02 | 2019-03-22 | 中山大学 | For the countercheck of voice deception in a kind of automatic Speaker Identification |
CN105225664B (en) * | 2015-09-24 | 2019-12-06 | 百度在线网络技术(北京)有限公司 | Information verification method and device and sound sample generation method and device |
CN105450665B (en) * | 2015-12-30 | 2018-11-06 | 宇龙计算机通信科技(深圳)有限公司 | Safe login method and device, terminal |
CN105933272A (en) * | 2015-12-30 | 2016-09-07 | 中国银联股份有限公司 | Voiceprint recognition method capable of preventing recording attack, server, terminal, and system |
CN106057206B (en) * | 2016-06-01 | 2019-05-03 | 腾讯科技(深圳)有限公司 | Sound-groove model training method, method for recognizing sound-groove and device |
CN106531171B (en) * | 2016-10-13 | 2020-02-11 | 普强信息技术(北京)有限公司 | Method for realizing dynamic voiceprint password system |
CN107967526A (en) * | 2017-10-31 | 2018-04-27 | 厦门快商通信息技术有限公司 | A kind of hotel reservation management method and system |
CN107919961A (en) * | 2017-12-07 | 2018-04-17 | 广州势必可赢网络科技有限公司 | Identity authentication protocol and server based on dynamic code and dynamic voiceprint update |
CN109242492A (en) * | 2018-09-02 | 2019-01-18 | 珠海横琴现联盛科技发展有限公司 | The Application on Voiceprint Recognition payment information method for anti-counterfeit imitated for sound |
CN111385272B (en) * | 2018-12-29 | 2024-06-21 | 北京奇虎科技有限公司 | Weak password detection method and device |
CN111833882A (en) * | 2019-03-28 | 2020-10-27 | 阿里巴巴集团控股有限公司 | Voiceprint information management method, device and system, computing equipment and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6799163B2 (en) * | 2002-06-05 | 2004-09-28 | Vas International, Inc. | Biometric identification system |
CN101685635A (en) * | 2008-09-23 | 2010-03-31 | 吕共欣 | Identity authentication system and method |
CN102314877A (en) * | 2010-07-08 | 2012-01-11 | 盛乐信息技术(上海)有限公司 | Voiceprint identification method for character content prompt |
CN104331652A (en) * | 2014-10-08 | 2015-02-04 | 无锡指网生物识别科技有限公司 | Dynamic cipher generation method for electronic equipment for fingerprint and voice recognition |
-
2015
- 2015-03-20 CN CN201510125684.2A patent/CN104717219B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN104717219A (en) | 2015-06-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104717219B (en) | Vocal print login method and device based on artificial intelligence | |
CN106782572A (en) | The authentication method and system of speech cipher | |
CN107395352B (en) | Personal identification method and device based on vocal print | |
CN106713370B (en) | A kind of identity identifying method, server and mobile terminal | |
CN106961418A (en) | Identity identifying method and identity authorization system | |
CN106790054A (en) | Interactive authentication system and method based on recognition of face and Application on Voiceprint Recognition | |
CN103607282B (en) | A kind of identity fusion authentication method based on biological characteristic | |
CN105913850B (en) | Text correlation vocal print method of password authentication | |
CN104598796A (en) | Method and system for identifying identity | |
CN109241330A (en) | The method, apparatus, equipment and medium of key phrase in audio for identification | |
CN105095415B (en) | The determination method and apparatus of network mood | |
CN110751698A (en) | Text-to-image generation method based on hybrid network model | |
CN105867633A (en) | Intelligent robot oriented information processing method and system | |
CN106448685A (en) | System and method for identifying voice prints based on phoneme information | |
CN104951807B (en) | The determination method and apparatus of stock market's mood | |
CN103279764A (en) | Real-name network authentication system based on face identification | |
CN104331652A (en) | Dynamic cipher generation method for electronic equipment for fingerprint and voice recognition | |
CN102413101A (en) | Voice-print authentication system having voice-print password voice prompting function and realization method thereof | |
CN105991290B (en) | Pseudorandom vocal print cryptogram generation method and system | |
CN103294959A (en) | Text information hiding method resistant to statistic analysis | |
CN106375336A (en) | Login information storage and providing method and device | |
CN107679031A (en) | Based on the advertisement blog article recognition methods for stacking the self-editing ink recorder of noise reduction | |
CN102222502A (en) | Effective way for voice verification by Chinese text-prompted mode | |
CN106600283A (en) | Method and system for identifying the name nationalities as well as method and system for determining transaction risk | |
CN104951930A (en) | Electronic cipher ticket method and system based on bio-information identity verification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |