CN110322888B - Credit card unlocking method, apparatus, device and computer readable storage medium - Google Patents
Credit card unlocking method, apparatus, device and computer readable storage medium Download PDFInfo
- Publication number
- CN110322888B CN110322888B CN201910424278.4A CN201910424278A CN110322888B CN 110322888 B CN110322888 B CN 110322888B CN 201910424278 A CN201910424278 A CN 201910424278A CN 110322888 B CN110322888 B CN 110322888B
- Authority
- CN
- China
- Prior art keywords
- voice
- credit card
- recognition
- user side
- recognition result
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000004044 response Effects 0.000 claims description 61
- 238000012795 verification Methods 0.000 claims description 42
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000001514 detection method Methods 0.000 claims description 14
- 230000004048 modification Effects 0.000 claims description 14
- 238000012986 modification Methods 0.000 claims description 14
- 230000008014 freezing Effects 0.000 claims description 10
- 238000007710 freezing Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Lock And Its Accessories (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and discloses a credit card unlocking method, a credit card unlocking device, a credit card unlocking equipment and a credit card computer readable storage medium, wherein the credit card unlocking method comprises the following steps: and establishing call connection with the user end corresponding to the credit card with the transaction password locked, outputting preset voice to the user end, receiving voice reply from the client end, outputting corresponding voice to the user end according to the recognition result of the voice reply, or executing corresponding processing steps until the processing flow is finished. The invention provides credit card password unlocking service for users in a voice self-service mode, reduces the labor cost of banks and provides service quality.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a credit card unlocking method, apparatus, device, and computer readable storage medium.
Background
Because of the convenience of credit cards, more and more people's consumption patterns depend on credit cards, and the credit card market is still one of the fastest growing product lines in today's personal financial services markets.
To ensure the security of the user's card, banks are provided with various security mechanisms, such as a card locking mechanism. That is, when using the credit card, if the password is continuously input for three times, the credit card transaction password is automatically locked, and after 24 hours, the password is automatically unlocked. The cardholder can dial a bank manual client to perform manual unlocking. However, in this way, a bank is required to employ a plurality of personnel to provide manual service for users, on one hand, the labor cost of the bank is increased, and on the other hand, the customer service level of the bank cannot be well ensured due to uneven customer service level, so that poor service experience is brought to the users.
Disclosure of Invention
The invention mainly aims to provide a credit card unlocking method, a credit card unlocking device, credit card unlocking equipment and a credit card unlocking computer readable storage medium, and aims to solve the technical problems that in the prior art, unlocking service is provided for a user in a manual service mode, the labor cost is high, and the service quality cannot be guaranteed.
In order to achieve the above object, the present invention provides a credit card unlocking method, comprising the steps of:
establishing call connection with a user terminal corresponding to the credit card with the transaction password locked, and outputting a first voice question to the user terminal;
Receiving a first voice response fed back by the user side based on the first voice question, and performing voice recognition on the first voice response to obtain a first recognition result;
detecting whether the first recognition result is of affirmative type;
if the first recognition result is of affirmative type, outputting a second voice question to the user side;
receiving a second voice response fed back by the user side based on the second voice question, and performing voice recognition on the second voice response to obtain a second recognition result;
detecting whether the second recognition result is of affirmative type;
if the second identification result is of a positive type, outputting verification information to acquire a voice prompt to the user side;
receiving a third voice response fed back by the user side based on the verification information, and performing voice recognition on the third voice response to obtain a third recognition result;
detecting whether the third identification result is legal verification information or not;
if the third identification result is legal verification information, outputting a password modification voice prompt to the user side;
receiving a fourth voice response fed back by the user side based on the password modification voice prompt, and performing voice recognition on the fourth voice response to obtain a fourth recognition result;
Detecting whether the fourth identification result accords with a preset password setting rule;
and if the fourth identification result accords with a preset password setting rule, unlocking the credit card with the locked transaction password, and updating the transaction password of the credit card into the fourth identification result.
Optionally, before the step of establishing a call connection with the user end corresponding to the credit card with the transaction password locked and outputting the first voice question to the user end, the method further includes:
when the fact that the credit card transaction password is locked is detected, contact information of a user side corresponding to the credit card with the locked transaction password is obtained;
and sending a call request to a user side corresponding to the credit card with the locked transaction password based on the contact information so as to establish call connection with the user side.
Optionally, the step of outputting a second voice question to the user side if the first recognition result is of affirmative type includes:
if the first identification result is of a positive type, acquiring voiceprint feature information of the first voice reply and preset voiceprint feature information corresponding to the credit card with the transaction password locked;
Detecting whether the voiceprint feature information is matched with the preset voiceprint feature information;
and if the voiceprint feature information is matched with the preset voiceprint feature information, outputting a second voice question to the user side.
Optionally, if the first recognition result is of affirmative type, the step of obtaining voiceprint feature information of the first voice response and preset voiceprint feature information corresponding to the credit card with the transaction password locked includes:
if the first recognition result is of a positive type, acquiring a preset feature matrix corresponding to the credit card with the transaction password locked from a preset memory, and extracting to obtain a feature matrix to be recognized based on the first voice reply by an extraction method of a Mel cepstrum coefficient;
the step of detecting whether the voiceprint feature information is matched with the preset voiceprint feature information comprises the following steps:
calculating the similarity between the preset feature matrix and the feature matrix to be identified through MATLAB analysis;
and if the similarity is larger than or equal to a preset threshold, judging that the voiceprint feature information is matched with the preset voiceprint feature information, and if the similarity is smaller than the preset threshold, judging that the voiceprint feature information is not matched with the preset voiceprint feature information.
Optionally, after the step of detecting whether the second recognition result is of affirmative type, the method further includes:
if the second recognition result is of a negative type, outputting a third voice question to the user side;
receiving a fifth voice response fed back by the user side based on the third voice question, and performing voice recognition on the fifth voice response to obtain a fifth recognition result;
detecting whether the fifth recognition result belongs to a negative type;
and if the fifth identification result is of a negative type, freezing the credit card with the transaction password locked, and disconnecting the call connection.
Optionally, after the step of detecting whether the third identification result is legal verification information, the method further includes:
and if the third identification result is illegal verification information, freezing the credit card with the transaction password locked, and disconnecting the call connection.
Optionally, after the step of detecting whether the first recognition result is of affirmative type, the method further includes:
and if the first recognition result is of a negative type, outputting a transfer voice prompt and disconnecting the call connection.
In addition, in order to achieve the above object, the present invention also provides a credit card unlocking device, including:
the first questioning module is used for establishing call connection with a user side corresponding to the credit card with the transaction password locked, and outputting a first voice questioning to the user side;
the first recognition module is used for receiving a first voice response fed back by the user side based on the first voice question, and carrying out voice recognition on the first voice response to obtain a first recognition result;
the first detection module is used for detecting whether the first identification result belongs to an affirmative type;
the second questioning module is used for outputting a second voice questioning to the user side if the first recognition result is of a positive type;
the second recognition module is used for receiving a second voice response fed back by the user side based on the second voice question, and carrying out voice recognition on the second voice response to obtain a second recognition result;
the second detection module is used for detecting whether the second identification result belongs to an affirmative type;
the first prompt module is used for outputting verification information to acquire a voice prompt to the user side if the second identification result belongs to a positive type;
The third recognition module is used for receiving a third voice response fed back by the voice prompt acquired by the user terminal based on the verification information, and carrying out voice recognition on the third voice response to acquire a third recognition result;
the third detection module is used for detecting whether the third identification result is legal verification information or not;
the second prompting module is used for outputting a password modification voice prompt to the user side if the third identification result is legal verification information;
the fourth recognition module is used for receiving a fourth voice response fed back by the user side based on the password modification voice prompt, and carrying out voice recognition on the fourth voice response to obtain a fourth recognition result;
the fourth detection module is used for detecting whether the fourth identification result accords with a preset password setting rule;
and the unlocking module is used for unlocking the credit card with the transaction password locked if the fourth identification result accords with a preset password setting rule, and updating the transaction password of the credit card into the fourth identification result.
Further, the credit card unlocking device further includes:
the system comprises a contact information acquisition module, a transaction information acquisition module and a transaction information acquisition module, wherein the contact information acquisition module is used for acquiring contact information of a user side corresponding to a credit card with a locked transaction password when the credit card transaction password is detected to be locked;
And the call module is used for sending a call request to a user side corresponding to the credit card with the transaction password locked based on the contact information so as to establish call connection with the user side.
Further, the second question module includes:
the voiceprint obtaining unit is used for obtaining voiceprint characteristic information of the first voice reply and preset voiceprint characteristic information corresponding to the credit card with the transaction password locked if the first identification result is of an affirmative type;
the voiceprint detection unit is used for detecting whether the voiceprint characteristic information is matched with the preset voiceprint characteristic information or not;
and the second question unit is used for outputting a second voice question to the user terminal if the voiceprint characteristic information is matched with the preset voiceprint characteristic information.
Further, the voiceprint acquisition unit includes:
the feature matrix acquisition subunit is used for acquiring a preset feature matrix corresponding to the credit card with the transaction password locked from a preset memory if the first identification result is of an affirmative type, and extracting to obtain a feature matrix to be identified based on the first voice reply by an extraction method of a mel cepstrum coefficient;
The voiceprint detection unit includes:
the similarity calculation subunit is used for calculating the similarity between the preset feature matrix and the feature matrix to be identified through MATLAB analysis;
and the matching judging subunit is used for judging that the voiceprint characteristic information is matched with the preset voiceprint characteristic information if the similarity is larger than or equal to a preset threshold value, and judging that the voiceprint characteristic information is not matched with the preset voiceprint characteristic information if the similarity is smaller than the preset threshold value.
Further, the credit card unlocking device further includes:
the third question module is used for outputting a third voice question to the user side if the second recognition result belongs to a negative type;
the fifth recognition module is used for receiving a fifth voice response fed back by the user side based on the third voice question, and carrying out voice recognition on the fifth voice response to obtain a fifth recognition result;
a fifth detection module, configured to detect whether the fifth recognition result belongs to a negative type;
and the freezing module is used for freezing the credit card with the locked transaction password and disconnecting the call connection if the fifth identification result is of a negative type.
And the freezing module is further used for freezing the credit card with the locked transaction password and disconnecting the call connection if the third identification result is illegal verification information.
Further, the credit card unlocking device further includes:
and the third prompting module is used for outputting a transfer voice prompt and disconnecting the call connection if the first recognition result belongs to a negative type.
In addition, to achieve the above object, the present invention also provides a credit card unlocking apparatus comprising: the system comprises a memory, a processor and a credit card unlocking program stored on the memory and capable of running on the processor, wherein the credit card unlocking program realizes the steps of the credit card unlocking method when being executed by the processor.
In addition, in order to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a credit card unlocking program which, when executed by a processor, implements the steps of the credit card unlocking method as described above.
In the invention, a call connection is established with a user end corresponding to the credit card with the transaction password locked, a preset voice is output to the user end, then a voice reply from the client end is received, and according to a recognition result of the voice reply, a corresponding voice is output to the user end, or a corresponding processing step is executed until the processing flow is finished. The invention provides credit card password unlocking service for users in a voice self-service mode, reduces the labor cost of banks and provides service quality.
Drawings
FIG. 1 is a schematic diagram of a credit card unlocking device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart of a credit card unlocking method according to a first embodiment of the present invention;
FIG. 3 is a schematic diagram of a refinement flow chart of step S40 in FIG. 2;
fig. 4 is a schematic functional block diagram of a first embodiment of a credit card unlocking apparatus according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a credit card unlocking device of a hardware running environment according to an embodiment of the present invention.
The credit card unlocking device in the embodiment of the invention can be a PC, a smart phone, a server and other terminal devices.
As shown in fig. 1, the credit card unlocking apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the credit card unlocking device structure shown in fig. 1 is not limiting of the credit card unlocking device, and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a credit card unlocking program may be included in a memory 1005, which is a type of computer storage medium.
In the credit card unlocking device shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be used to invoke a credit card unlocking program stored in the memory 1005 and to perform the steps of the various embodiments of the credit card unlocking method below.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of a credit card unlocking method according to the present invention.
In a first embodiment of the credit card unlocking method of the present invention, the credit card unlocking method includes:
step S10, a call connection is established with a user terminal corresponding to the credit card with the transaction password locked, and a first voice question is output to the user terminal;
In this embodiment, a call connection may be established between the user terminal and the external call or the answering call, and then the first voice question is output to the user terminal. Wherein the first voice question is a voice of an owner who inquires whether the user is a credit card with a transaction password locked. For example, the first voice question may be "please ask you if you are XXX", "you are XXX, etc., where" XXX "is the name of the user who is transacting the credit card in the banking system reserved when the credit card is transacted.
Step S20, receiving a first voice response fed back by the user side based on the first voice question, and performing voice recognition on the first voice response to obtain a first recognition result;
in this embodiment, after the first voice question is output, the voice signal from the user terminal is received, and the obtained voice signal is used as the first voice reply fed back by the user terminal based on the first voice question. Specifically, after the first voice question is output, the voice signal received from the user side within 5 seconds (the duration is set according to the actual needs) may be used as the first voice reply. And performing voice recognition on the first voice reply in a voice recognition mode to obtain a first recognition result. For example, the first voice reply is subjected to voice recognition by the existing voice recognition system, so as to obtain a first recognition result.
Step S30, detecting whether the first identification result belongs to a positive type;
in this embodiment, the first voice question may specifically be "please ask you if you are XXX", "do you are XXX". The corresponding first voice response generally includes the cases "yes", "i am yes", "not", "i am not". The replies indicating the determined meanings such as "yes", "i am yes" are classified into affirmative types, and the replies indicating the negative meanings such as "not", "i am not" are classified into negative types. If the first recognition result comprises one of "yes" and "I are", the first recognition result is of affirmative type; if the first recognition result includes one of "not yes", "i am not", the first recognition result is of a negative type.
Step S40, if the first recognition result is of affirmative type, outputting a second voice question to the user side;
in this embodiment, if the first recognition result is of affirmative type, the speaker of the current user terminal is determined to be the person to whom the credit card belongs, and a second voice question is output to the user terminal. Wherein the second voice question is a voice asking the user if he/she uses the card. For example, the second voice question may be in the form of "the current transaction password has been locked, please be your own with the credit card".
Step S50, receiving a second voice response fed back by the user side based on the second voice question, and performing voice recognition on the second voice response to obtain a second recognition result;
in this embodiment, after outputting the second voice question, the voice signal from the user terminal is received, and the obtained voice signal is used as the second voice reply fed back by the user terminal based on the second voice question. Specifically, after the second voice question is output, the voice signal received from the user side within 5 seconds (the duration is set according to the actual needs) may be used as the second voice reply. And performing voice recognition on the second voice reply in a voice recognition mode to obtain a second recognition result. For example, the second voice reply is subjected to voice recognition through the existing voice recognition system, so that a second recognition result is obtained.
Step S60, detecting whether the second recognition result belongs to a positive type;
in this embodiment, since the second voice question is a voice asking the user whether he/she is using the card, the second voice reply is generally "yes", "is self-use", "is not self-use", or the like. Thus, answers such as "yes", "yes-me-in-use", etc. are summarized as affirmative types, and answers such as "no", "no-me-in-use", etc. are summarized as negative types, depending on the contents to which the user may reply. If the second identification result comprises one of "yes" and "is self-use", the second identification result is of a positive type; if the second recognition result includes one of "not yes", "not me in use", the second recognition result is of a negative type.
Step S70, if the second recognition result is of affirmative type, outputting verification information to acquire a voice prompt to the user side;
in this embodiment, if the second recognition result is of affirmative type, the password modification process is entered. In order to improve the security, further authentication needs to be performed on the user identity, so that verification information is output to obtain a voice prompt to the user side. The verification information acquisition voice prompt is voice for requesting verification information from a user. Specifically, the method can be "please speak the identification card number of the person to whom the credit card belongs", "please speak the verification code reserved when the credit card is transacted", and the like.
Step S80, receiving a third voice response fed back by the user side based on the verification information, and performing voice recognition on the third voice response to obtain a third recognition result;
in this embodiment, after the verification information is output to obtain the voice prompt, the voice signal from the user side is received, and the obtained voice signal is used as a third voice response fed back by the user side to obtain the voice prompt based on the verification information. Specifically, after the verification information is output and the voice prompt is obtained, the voice signal received from the user side within 15 seconds (the duration is set according to the actual needs) is used as the third voice reply. And carrying out voice recognition on the third voice reply in a voice recognition mode to obtain a third recognition result. For example, the third voice reply is subjected to voice recognition by the existing voice recognition system, so as to obtain a third recognition result.
Step S90, detecting whether the third identification result is legal verification information;
in this embodiment, if the verification information obtaining voice prompt is specifically "please speak the identification card number of the person to whom the credit card belongs", the continuous 18-bit number in the identification result for the third voice reply is used as the third identification result, and the third identification result is compared with the identification card number reserved in the bank system when the credit card is handled, and if the identification result is completely consistent, the third identification result is legal verification information. If the 18 continuous digits in the identification result are inconsistent with the identification card number reserved in the bank system when the credit card is transacted, or if the 18 continuous digits do not exist in the identification result, the third identification result is illegal verification information.
Step S100, if the third recognition result is legal verification information, outputting a password modification voice prompt to the user side;
in this embodiment, if the third recognition result is legal verification information, it is determined that the speaker at the user terminal has authority to change the password, and a password-modifying voice prompt is output to the user terminal. The password-modifying voice prompt can be specifically "please set a new password", "please reset the password", etc.
Step S110, receiving a fourth voice response fed back by the user terminal based on the password modification voice prompt, and performing voice recognition on the fourth voice response to obtain a fourth recognition result;
in this embodiment, after outputting the password-modified voice prompt, the voice signal from the user terminal is received, and the obtained voice signal is used as a fourth voice reply fed back by the user terminal based on the password-modified voice prompt. Specifically, after the password modification voice prompt is output, the voice signal received from the user side within 10 seconds (the duration is set according to the actual needs) is taken as the fourth voice reply. And carrying out voice recognition on the fourth voice reply in a voice recognition mode to obtain a fourth recognition result. For example, the fourth voice reply is subjected to voice recognition by the existing voice recognition system, so that the continuous 6-bit digits in the recognition result are used as the fourth recognition result.
Step S120, detecting whether the fourth identification result accords with a preset password setting rule;
in this embodiment, in order to secure the user card, the password is required to be too simple to be set, for example, the password in the form of "AAAAAA" (6 digits are the same), "123456" or the like cannot be set. Therefore, it is necessary to detect whether the fourth recognition result belongs to one of "AAAAAA", "123456", and if not, the fourth recognition result conforms to a preset password setting rule.
Step S130, if the fourth identification result accords with a preset password setting rule, unlocking the credit card with the transaction password locked, and updating the transaction password of the credit card to the fourth identification result.
In this embodiment, if the fourth identification result meets the preset password setting rule, the transaction password of the credit card is unlocked, and the fourth identification result is used as a new transaction password of the credit card.
In this embodiment, a call connection is established with a user terminal corresponding to a credit card with a transaction password locked, and a preset voice is output to the user terminal, then a voice reply from the client terminal is received, and according to a recognition result of the voice reply, a corresponding voice is output to the user terminal, or a corresponding processing step is executed until the processing flow is completed. Through the embodiment, the credit card password unlocking service is provided for the user in a voice self-service mode, so that the labor cost of the bank is reduced, and the service quality is provided.
Further, in an embodiment of the credit card unlocking method of the present invention, before step S10, the method further includes:
when the fact that the credit card transaction password is locked is detected, contact information of a user side corresponding to the credit card with the locked transaction password is obtained;
Currently, when a user uses a credit card, if the wrong password is continuously input three times, the credit card transaction password is automatically locked. In this embodiment, when the event is detected (i.e. the credit card transaction password is detected to be locked), the contact information of the user side corresponding to the credit card is obtained (when the credit card is transacted, the contact telephone of the transacting person is reserved in the banking system).
And sending a call request to a user side corresponding to the credit card with the locked transaction password based on the contact information so as to establish call connection with the user side.
In this embodiment, according to the acquired contact information, automatic dialing is performed (i.e., a call request is sent to the user end corresponding to the credit card with the transaction password locked). The first time that the credit card transaction password is locked is communicated with the person to whom the credit card belongs, so that the experience of the person using the card is improved, and the card using safety is also improved.
Further, referring to fig. 3, fig. 3 is a schematic diagram of a refinement flow of step S40 in fig. 2.
In one embodiment of the credit card unlocking method of the present invention, step S40 includes:
step S401, if the first recognition result is of affirmative type, acquiring voiceprint feature information of the first voice reply and preset voiceprint feature information corresponding to the credit card with the transaction password locked;
In this embodiment, when the credit card is transacted, the voice spoken by the transactor (the voice of the specified content or the voice of the unspecified content) is acquired, and then voiceprint feature information of the voice is extracted and stored as preset voiceprint feature information in the banking system. If the first recognition result is of affirmative type, voiceprint feature information of the first voice reply and preset voiceprint feature information reserved in the bank system are obtained. Wherein the voiceprint feature information may be: acoustic features (cepstrum), prosodic features (pitch and energy "pose" described by n-gram), etc.
Step S402, detecting whether the voiceprint feature information is matched with the preset voiceprint feature information;
in this embodiment, the similarity between the voiceprint feature information and the preset voiceprint feature information is calculated, and if the similarity is higher than a preset value, the voiceprint feature information is considered to be matched with the preset voiceprint feature information.
Step S403, if the voiceprint feature information matches the preset voiceprint feature information, outputting a second voice question to the user terminal.
In this embodiment, if the first recognition result is of affirmative type and the voiceprint feature information is matched with the preset voiceprint feature information, the speaker at the user end is determined to be the person to whom the credit card belongs, and a second voice question is output to the user end. If the transaction codes are not matched, the speaker at the user end is not the owner of the credit card, and in order to improve the card use safety, the credit card with the transaction codes locked is frozen, and the call connection is disconnected.
Further, in an embodiment of the credit card unlocking method of the present invention, step S401 includes:
if the first recognition result is of a positive type, acquiring a preset feature matrix corresponding to the credit card with the transaction password locked from a preset memory, and extracting the feature matrix to be recognized based on the first voice reply by an extraction method of a Mel cepstrum coefficient.
In this embodiment, when a credit card is transacted, a voice uttered by a transactor (a voice of specified content or a voice of unspecified content) is acquired, and a feature matrix for the voice is extracted as a preset feature matrix of the credit card by using an extraction method of mel-frequency cepstrum coefficient (MFCC), and stored in a banking system. Therefore, when the first recognition result is of affirmative type, the preset feature matrix corresponding to the credit card with the transaction password locked can be directly obtained from the preset memory. And extracting a feature matrix for the first voice response by using an extraction method of mel-frequency cepstrum coefficient (MFCC). Mel frequency is proposed based on the auditory characteristics of the human ear, which has a non-linear correspondence with Hz frequency. The mel-frequency cepstral coefficient (MFCC) is a calculated Hz spectral feature using this relationship between them.
Step S402 includes:
calculating the similarity between the preset feature matrix and the feature matrix to be identified through MATLAB analysis;
and if the similarity is larger than or equal to a preset threshold, judging that the voiceprint feature information is matched with the preset voiceprint feature information, and if the similarity is smaller than the preset threshold, judging that the voiceprint feature information is not matched with the preset voiceprint feature information.
In this embodiment, the similarity between the preset feature matrix and the feature matrix to be identified can be obtained by MATLAB analysis, and if the similarity is greater than or equal to a preset threshold (for example, set to 90%, in order to improve card use security, the threshold may be set higher), the voiceprint feature information is considered to be matched with the preset voiceprint feature information, otherwise, the voiceprint feature information is not matched with the preset voiceprint feature information. Wherein MATLAB is a mathematical software, which can perform matrix operation.
Further, in an embodiment of the credit card unlocking method of the present invention, after step S60, the method further includes:
if the second recognition result is of a negative type, outputting a third voice question to the user side;
in this embodiment, if the second recognition result includes one of "not yes" and "not me in use", the second recognition result is of a negative type, i.e. the current card locking is caused by the operation of other people. In order to improve the card use safety, a third voice question is output to the user side. The third voice question is a voice asking the user if the current cardholder is a direct relatives. For example, the third voice question may be a voice like "do you currently get stuck on your direct relatives hand".
Receiving a fifth voice response fed back by the user side based on the third voice question, and performing voice recognition on the fifth voice response to obtain a fifth recognition result;
in this embodiment, after outputting the third voice question, the voice signal from the user terminal is received, and the obtained voice signal is used as the fifth voice reply fed back by the user terminal based on the third voice question. Specifically, after the third voice question is output, the voice signal received from the user side within 5 seconds (the duration is set according to the actual needs) may be used as the fifth voice reply. And carrying out voice recognition on the fifth voice reply in a voice recognition mode to obtain a fifth recognition result. For example, the third voice reply is subjected to voice recognition by the existing voice recognition system, so as to obtain a fifth recognition result.
Detecting whether the fifth recognition result belongs to a negative type;
in this embodiment, for the third voice question, the possible replies include: "yes, is I XX is in use", "is o", "is not", "I don't know who is in use", etc. "yes," is that i am XX is in use, "is," etc. are generalized to positive types, and "not," "i am unaware of who is in use," etc. are generalized to negative types. If one of "not yes", "i don't know who is in use" exists in the fifth recognition result, the fifth recognition result is of a negative type.
And if the fifth identification result is of a negative type, freezing the credit card with the transaction password locked, and disconnecting the call connection.
In this embodiment, if the fifth recognition result is of a negative type, it indicates that the person who is not the credit card is currently using the card, and the person who is using the card is not the direct relative of the person who is using the card, and in order to improve the card use security, the credit card with the transaction password locked is frozen, and the call connection is disconnected.
Further, in an embodiment of the credit card unlocking method of the present invention, after step S90, the method further includes:
and if the third identification result is illegal verification information, freezing the credit card with the transaction password locked, and disconnecting the call connection.
In this embodiment, if the third recognition result is illegal verification information, that is, the speaker at the current user end cannot provide correct verification information, and the first recognition result belongs to a positive type, a contradiction occurs, and it is likely that the speaker lies, and in order to ensure card security, the credit card is frozen and the call connection is disconnected.
Further, in an embodiment of the credit card unlocking method of the present invention, after step S30, the method further includes:
And if the first recognition result is of a negative type, outputting a transfer voice prompt and disconnecting the call connection.
In this embodiment, if the first recognition result is of a negative type, that is, it is determined that the speaker at the current user side is not the person to whom the credit card belongs, in order to ensure the card security, a notification voice prompt is output, for example, "please notify xxx that the credit card transaction password is locked under the name" and the call connection is disconnected, so that the subsequent flow is not performed.
Referring to fig. 4, fig. 4 is a schematic functional block diagram of a first embodiment of a credit card unlocking apparatus according to the present invention.
In a first embodiment of the credit card unlocking apparatus of the present invention, the credit card unlocking apparatus includes:
the first questioning module 10 is configured to establish a call connection with a user terminal corresponding to a credit card with a transaction password locked, and output a first voice questioning to the user terminal;
the first recognition module 20 is configured to receive a first voice response fed back by the user side based on the first voice question, and perform voice recognition on the first voice response to obtain a first recognition result;
a first detection module 30, configured to detect whether the first recognition result is of a positive type;
A second question module 40, configured to output a second voice question to the user terminal if the first recognition result is of affirmative type;
the second recognition module 50 is configured to receive a second voice response fed back by the user side based on the second voice question, and perform voice recognition on the second voice response to obtain a second recognition result;
a second detection module 60, configured to detect whether the second recognition result is of affirmative type;
the first prompt module 70 is configured to output verification information to obtain a voice prompt to the user side if the second recognition result is of a positive type;
the third recognition module 80 is configured to receive a third voice response fed back by the user side by using the voice prompt based on the verification information, and perform voice recognition on the third voice response to obtain a third recognition result;
a third detection module 90, configured to detect whether the third identification result is legal verification information;
the second prompting module 100 is configured to output a password modification voice prompt to the user side if the third recognition result is legal verification information;
a fourth recognition module 110, configured to receive a fourth voice response fed back by the user side based on the password modification voice prompt, and perform voice recognition on the fourth voice response to obtain a fourth recognition result;
A fourth detecting module 120, configured to detect whether the fourth identification result meets a preset password setting rule;
and the unlocking module 130 is configured to unlock the credit card with the transaction password locked if the fourth identification result meets a preset password setting rule, and update the transaction password of the credit card to the fourth identification result.
In this embodiment, a call connection is established with a user terminal corresponding to a credit card with a transaction password locked, and a preset voice is output to the user terminal, then a voice reply from the client terminal is received, and according to a recognition result of the voice reply, a corresponding voice is output to the user terminal, or a corresponding processing step is executed until the processing flow is completed. Through the embodiment, the credit card password unlocking service is provided for the user in a voice self-service mode, so that the labor cost of the bank is reduced, and the service quality is provided.
In addition, the embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a credit card unlocking program, and the credit card unlocking program realizes the steps of the embodiments of the credit card unlocking method when being executed by a processor.
The specific embodiments of the computer readable storage medium of the present invention are substantially the same as the embodiments of the credit card unlocking method described above, and will not be described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. A credit card unlocking method, characterized in that the credit card unlocking method comprises the following steps:
establishing call connection with a user terminal corresponding to the credit card with the transaction password locked, and outputting a first voice question to the user terminal;
receiving a first voice response fed back by the user side based on the first voice question, and performing voice recognition on the first voice response to obtain a first recognition result;
detecting whether the first recognition result is of affirmative type;
if the first recognition result is of affirmative type, outputting a second voice question to the user side;
receiving a second voice response fed back by the user side based on the second voice question, and performing voice recognition on the second voice response to obtain a second recognition result;
detecting whether the second recognition result is of affirmative type;
If the second identification result is of a positive type, outputting verification information to acquire a voice prompt to the user side;
receiving a third voice response fed back by the user side based on the verification information, and performing voice recognition on the third voice response to obtain a third recognition result;
detecting whether the third identification result is legal verification information or not;
if the third identification result is legal verification information, outputting a password modification voice prompt to the user side;
receiving a fourth voice response fed back by the user side based on the password modification voice prompt, and performing voice recognition on the fourth voice response to obtain a fourth recognition result;
detecting whether the fourth identification result accords with a preset password setting rule;
and if the fourth identification result accords with a preset password setting rule, unlocking the credit card with the locked transaction password, and updating the transaction password of the credit card into the fourth identification result.
2. The credit card unlocking method according to claim 1, wherein before the step of establishing a call connection with the user terminal corresponding to the credit card whose transaction password is locked and outputting a first voice question to the user terminal, further comprising:
When the fact that the credit card transaction password is locked is detected, contact information of a user side corresponding to the credit card with the locked transaction password is obtained;
and sending a call request to a user side corresponding to the credit card with the locked transaction password based on the contact information so as to establish call connection with the user side.
3. The credit card unlocking method according to claim 1, wherein the step of outputting a second voice question to the user terminal if the first recognition result is of affirmative type includes:
if the first identification result is of a positive type, acquiring voiceprint feature information of the first voice reply and preset voiceprint feature information corresponding to the credit card with the transaction password locked;
detecting whether the voiceprint feature information is matched with the preset voiceprint feature information;
and if the voiceprint feature information is matched with the preset voiceprint feature information, outputting a second voice question to the user side.
4. The method for unlocking a credit card according to claim 3, wherein the step of acquiring voiceprint feature information of the first voice response and preset voiceprint feature information corresponding to the credit card in which the transaction password is locked if the first recognition result is of affirmative type comprises:
If the first recognition result is of a positive type, acquiring a preset feature matrix corresponding to the credit card with the transaction password locked from a preset memory, and extracting to obtain a feature matrix to be recognized based on the first voice reply by an extraction method of a Mel cepstrum coefficient;
the step of detecting whether the voiceprint feature information is matched with the preset voiceprint feature information comprises the following steps:
calculating the similarity between the preset feature matrix and the feature matrix to be identified through MATLAB analysis;
and if the similarity is larger than or equal to a preset threshold, judging that the voiceprint feature information is matched with the preset voiceprint feature information, and if the similarity is smaller than the preset threshold, judging that the voiceprint feature information is not matched with the preset voiceprint feature information.
5. The credit card unlocking method according to claim 1, further comprising, after said step of detecting whether said second recognition result is of affirmative type:
if the second recognition result is of a negative type, outputting a third voice question to the user side;
receiving a fifth voice response fed back by the user side based on the third voice question, and performing voice recognition on the fifth voice response to obtain a fifth recognition result;
Detecting whether the fifth recognition result belongs to a negative type;
and if the fifth identification result is of a negative type, freezing the credit card with the transaction password locked, and disconnecting the call connection.
6. The credit card unlocking method of claim 1, further comprising, after the step of detecting whether the third recognition result is legal authentication information:
and if the third identification result is illegal verification information, freezing the credit card with the transaction password locked, and disconnecting the call connection.
7. The credit card unlocking method according to any one of claims 1 to 6, characterized by further comprising, after the step of detecting whether the first recognition result is of affirmative type:
and if the first recognition result is of a negative type, outputting a transfer voice prompt and disconnecting the call connection.
8. A credit card unlocking device, characterized in that the credit card unlocking device comprises:
the first questioning module is used for establishing call connection with a user side corresponding to the credit card with the transaction password locked, and outputting a first voice questioning to the user side;
The first recognition module is used for receiving a first voice response fed back by the user side based on the first voice question, and carrying out voice recognition on the first voice response to obtain a first recognition result;
the first detection module is used for detecting whether the first identification result belongs to an affirmative type;
the second questioning module is used for outputting a second voice questioning to the user side if the first recognition result is of a positive type;
the second recognition module is used for receiving a second voice response fed back by the user side based on the second voice question, and carrying out voice recognition on the second voice response to obtain a second recognition result;
the second detection module is used for detecting whether the second identification result belongs to an affirmative type;
the first prompt module is used for outputting verification information to acquire a voice prompt to the user side if the second identification result belongs to a positive type;
the third recognition module is used for receiving a third voice response fed back by the voice prompt acquired by the user terminal based on the verification information, and carrying out voice recognition on the third voice response to acquire a third recognition result;
the third detection module is used for detecting whether the third identification result is legal verification information or not;
The second prompting module is used for outputting a password modification voice prompt to the user side if the third identification result is legal verification information;
the fourth recognition module is used for receiving a fourth voice response fed back by the user side based on the password modification voice prompt, and carrying out voice recognition on the fourth voice response to obtain a fourth recognition result;
the fourth detection module is used for detecting whether the fourth identification result accords with a preset password setting rule;
and the unlocking module is used for unlocking the credit card with the transaction password locked if the fourth identification result accords with a preset password setting rule, and updating the transaction password of the credit card into the fourth identification result.
9. A credit card unlocking apparatus, characterized in that the credit card unlocking apparatus comprises: memory, a processor and a credit card unlocking program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the credit card unlocking method according to any one of claims 1 to 7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a credit card unlocking program, which when executed by a processor, implements the steps of the credit card unlocking method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910424278.4A CN110322888B (en) | 2019-05-21 | 2019-05-21 | Credit card unlocking method, apparatus, device and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910424278.4A CN110322888B (en) | 2019-05-21 | 2019-05-21 | Credit card unlocking method, apparatus, device and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110322888A CN110322888A (en) | 2019-10-11 |
CN110322888B true CN110322888B (en) | 2023-05-30 |
Family
ID=68113194
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910424278.4A Active CN110322888B (en) | 2019-05-21 | 2019-05-21 | Credit card unlocking method, apparatus, device and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110322888B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111696535B (en) * | 2020-05-22 | 2021-10-26 | 百度在线网络技术(北京)有限公司 | Information verification method, device, equipment and computer storage medium based on voice interaction |
CN112527980A (en) * | 2020-11-10 | 2021-03-19 | 联想(北京)有限公司 | Information response processing method, intelligent device and storage medium |
CN113538712B (en) * | 2021-09-17 | 2021-12-21 | 深圳市深圳通有限公司 | Traffic card identification method, device, equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203930982U (en) * | 2014-06-17 | 2014-11-05 | 吴志毅 | Based on the intelligent electronic lock system of mobile phone, voice, note control |
CN107517207A (en) * | 2017-03-13 | 2017-12-26 | 平安科技(深圳)有限公司 | Server, auth method and computer-readable recording medium |
CN108989349A (en) * | 2018-08-31 | 2018-12-11 | 平安科技(深圳)有限公司 | User account number unlocking method, device, computer equipment and storage medium |
CN108985776A (en) * | 2018-09-13 | 2018-12-11 | 南京硅基智能科技有限公司 | Credit card security monitoring method based on multiple Information Authentication |
CN109286554A (en) * | 2018-09-14 | 2019-01-29 | 腾讯科技(深圳)有限公司 | Social functions unlocking method and device in social application |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9262612B2 (en) * | 2011-03-21 | 2016-02-16 | Apple Inc. | Device access using voice authentication |
CN104468522B (en) * | 2014-11-07 | 2017-10-03 | 百度在线网络技术(北京)有限公司 | A kind of voice print verification method and apparatus |
-
2019
- 2019-05-21 CN CN201910424278.4A patent/CN110322888B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203930982U (en) * | 2014-06-17 | 2014-11-05 | 吴志毅 | Based on the intelligent electronic lock system of mobile phone, voice, note control |
CN107517207A (en) * | 2017-03-13 | 2017-12-26 | 平安科技(深圳)有限公司 | Server, auth method and computer-readable recording medium |
CN108989349A (en) * | 2018-08-31 | 2018-12-11 | 平安科技(深圳)有限公司 | User account number unlocking method, device, computer equipment and storage medium |
CN108985776A (en) * | 2018-09-13 | 2018-12-11 | 南京硅基智能科技有限公司 | Credit card security monitoring method based on multiple Information Authentication |
CN109286554A (en) * | 2018-09-14 | 2019-01-29 | 腾讯科技(深圳)有限公司 | Social functions unlocking method and device in social application |
Also Published As
Publication number | Publication date |
---|---|
CN110322888A (en) | 2019-10-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107977776B (en) | Information processing method, device, server and computer readable storage medium | |
CN110322888B (en) | Credit card unlocking method, apparatus, device and computer readable storage medium | |
US10645081B2 (en) | Method and apparatus for authenticating user | |
WO2019090834A1 (en) | Express cabinet pickup method and apparatus based on voiceprint | |
US20030074201A1 (en) | Continuous authentication of the identity of a speaker | |
US20070174868A1 (en) | Apparatus for personal authentication | |
US20170061968A1 (en) | Speaker verification methods and apparatus | |
US9047454B2 (en) | Authentication device and authentication system | |
CN108510290B (en) | Customer information amending method, device, computer equipment and storage medium in call | |
CN104183238B (en) | A kind of the elderly's method for recognizing sound-groove based on enquirement response | |
CN105072249A (en) | Method and device of preventing mobile device from being stolen, and corresponding mobile device | |
US20210320997A1 (en) | Information processing device, information processing method, and information processing program | |
US20180165433A1 (en) | User authentication system and user authentication application program | |
JP2007266944A (en) | Telephone terminal and caller verification method | |
US20070033041A1 (en) | Method of identifying a person based upon voice analysis | |
JP2021047557A (en) | User authentication device and program | |
US10049362B2 (en) | Systems and methods of voice authentication in transactions | |
KR20200006204A (en) | Method for user authentication using data extracting | |
CN108766442B (en) | Identity authentication method and device based on voiceprint graphic identification | |
CN111711523A (en) | Item handling authority authorization method and device, computer equipment and storage medium | |
JP2014072701A (en) | Communication terminal | |
EP3073721A1 (en) | Telephone reservation system | |
JP6772832B2 (en) | Crime judgment device, relay system, telephone system, crime judgment method and program | |
JP2012050034A (en) | Information server device and information service method | |
CN112085506A (en) | Transaction method and device, terminal and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |