CN107690036A - Electronic installation, inlet wire personal identification method and computer-readable recording medium - Google Patents
Electronic installation, inlet wire personal identification method and computer-readable recording medium Download PDFInfo
- Publication number
- CN107690036A CN107690036A CN201710489752.2A CN201710489752A CN107690036A CN 107690036 A CN107690036 A CN 107690036A CN 201710489752 A CN201710489752 A CN 201710489752A CN 107690036 A CN107690036 A CN 107690036A
- Authority
- CN
- China
- Prior art keywords
- client
- vocal print
- print feature
- inlet wire
- identity information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2281—Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/229—Wire identification arrangements; Number assignment determination
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2203/00—Aspects of automatic or semi-automatic exchanges
- H04M2203/60—Aspects of automatic or semi-automatic exchanges related to security aspects in telephonic communication systems
- H04M2203/6045—Identity confirmation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2203/00—Aspects of automatic or semi-automatic exchanges
- H04M2203/60—Aspects of automatic or semi-automatic exchanges related to security aspects in telephonic communication systems
- H04M2203/6054—Biometric subscriber identification
Abstract
The present invention discloses a kind of electronic installation, inlet wire personal identification method and computer-readable recording medium, wherein, this method includes:After caller client is received, according to predetermined telephone number and the mapping relations of client identity information, client identity information corresponding to current inlet wire number is obtained;After successfully client identity information is obtained, according to predetermined client identity information and the mapping relations of vocal print feature data, it is determined that client's vocal print feature data corresponding to the client identity information got;The speech data of inlet wire client is gathered, extracts the vocal print feature in the speech data collected;The vocal print feature extracted is matched with the client's vocal print feature data determined;If the vocal print feature extracted and the client's vocal print feature Data Matching success determined, it is client itself corresponding to the inlet wire number to confirm current inlet wire client.Technical solution of the present invention make it that the authentication to inlet wire client is more convenient, accurate and efficient.
Description
Technical field
The present invention relates to communication technical field, more particularly to a kind of electronic installation, inlet wire personal identification method and computer
Readable storage medium storing program for executing.
Background technology
At present, after customer phone inlet wire, there is provided the company of service is generally all to carry out identification by incoming call, this
Problems be present in the case where needing the scene of strict checking client identity:1st, telephone receiving attendant is needed to pass through in the phone
Voice mode carries out relevant information checking to confirm client identity with client, can provide related clothes for client after identity validation
Business;This mode process is cumbersome and inconvenient, and the experience to client is bad;2nd, need to preserve all client's recording with caution to entangle
Standby when confused, the preservation cost largely recorded is high;3rd, client identity can not be just effectively recognized when fraudulent use of telephone.
Therefore, it is badly in need of proposing a kind of scheme to solve the above problems.
The content of the invention
The main object of the present invention is to provide a kind of inlet wire personal identification method, it is intended to makes the authentication to inlet wire client
It is enhanced convenience, accurate, efficiently, and reduce recording and preserve, reduce cost.
To achieve the above object, electronic installation proposed by the present invention, including memory, processor and it is stored in the storage
On device and the inlet wire identification system that can run on the processor, the inlet wire identification system is by the processor
Following steps are realized during execution:
A, after caller client is received, according to predetermined telephone number and the mapping relations of client identity information,
Obtain client identity information corresponding to current inlet wire number;
B, after successfully client identity information is obtained, according to predetermined client identity information and vocal print feature data
Mapping relations, it is determined that client's vocal print feature data corresponding to the client identity information got;
C, the speech data of inlet wire client is gathered, extracts the vocal print feature in the speech data collected;
D, the vocal print feature extracted is matched with the client's vocal print feature data determined;
If vocal print feature E, extracted and the client's vocal print feature Data Matching success determined, confirm current inlet wire visitor
Family is client itself corresponding to the inlet wire number.
Preferably, the inlet wire identification system by the computing device when also realize following steps:
After client identity information failure is obtained, the speech data of inlet wire client is gathered, extracts the speech data collected
In vocal print feature;
The vocal print feature extracted is matched one by one with client's vocal print feature data in voice print database;
If client's vocal print feature Data Matching success in the vocal print feature and voice print database that extract, according in advance
The client identity information of determination and the mapping relations of client's vocal print feature data, confirm the visitor that the vocal print feature extracted matches
Client identity information corresponding to the vocal print feature data of family.
Preferably, the speech data of the collection inlet wire client, extracts vocal print feature in the speech data collected
Step, including:
F, the character string of predetermined number character is generated at random, reports the character string and prompting user repeats carrying for the character string
Show language;
G, reception client repeats the speech data corresponding to the character string, extracts the content in the speech data received,
And the content for the character string for reporting the content extracted with system is compared;
H, after comparing successfully, the vocal print feature in the speech data received is extracted.
Preferably, the speech data of the collection inlet wire client, extracts vocal print feature in the speech data collected
Step, in addition to:
After the content for the character string that the content extracted and system are reported compares unsuccessfully, step F is performed.
Preferably, the speech data of the collection inlet wire client, extracts vocal print feature in the speech data collected
Step, in addition to:
If the vocal print feature extracted fails with the client's vocal print feature Data Matching determined, error count is set to add one;
If the error count is less than or equal to default error count threshold value, step F is performed;
If the error count exceedes default error count threshold value, emergency safety processing is carried out.
The present invention also proposes a kind of inlet wire personal identification method, and methods described includes:
A, after caller client is received, according to predetermined telephone number and the mapping relations of client identity information,
Obtain client identity information corresponding to current inlet wire number;
B, after successfully client identity information is obtained, according to predetermined client identity information and vocal print feature data
Mapping relations, it is determined that client's vocal print feature data corresponding to the client identity information got;
C, the speech data of inlet wire client is gathered, extracts the vocal print feature in the speech data collected;
D, the vocal print feature extracted is matched with the client's vocal print feature data determined;
If vocal print feature E, extracted and the client's vocal print feature Data Matching success determined, confirm current inlet wire visitor
Family is client itself corresponding to the inlet wire number.
Preferably, the inlet wire personal identification method also includes:
After client identity information failure is obtained, the speech data of inlet wire client is gathered, extracts the speech data collected
In vocal print feature;
The vocal print feature extracted is matched one by one with client's vocal print feature data in voice print database;
If client's vocal print feature Data Matching success in the vocal print feature and voice print database that extract, according in advance
The client identity information of determination and the mapping relations of client's vocal print feature data, confirm the visitor that the vocal print feature extracted matches
Client identity information corresponding to the vocal print feature data of family.
Preferably, the speech data of the collection inlet wire client, extracts vocal print feature in the speech data collected
Step, including:
F, the character string of predetermined number character is generated at random, reports the character string and prompting user repeats carrying for the character string
Show language;
G, reception client repeats the speech data corresponding to the character string, extracts the content in the speech data received,
And the content for the character string for reporting the content extracted with system is compared;
H, after comparing successfully, the vocal print feature in the speech data received is extracted.
Preferably, the speech data of the collection inlet wire client, extracts vocal print feature in the speech data collected
Step, in addition to:
If the vocal print feature extracted fails with the client's vocal print feature Data Matching determined, error count is set to add one;
If the error count is less than or equal to default error count threshold value, step F is performed;
If the error count exceedes default error count threshold value, emergency safety processing is carried out.
The present invention also proposes a kind of computer-readable recording medium, and the computer-readable recording medium storage has inlet wire body
Part identifying system, the inlet wire identification system can be by least one computing device, so that at least one processor
Perform the inlet wire personal identification method described in any of the above-described.
Technical solution of the present invention first pass through inlet wire number obtain corresponding to client identity information, according to client identity information from
The vocal print feature data to be prestored corresponding to it are determined in vocal print feature database, will be carried from the speech data of current inlet wire client
The vocal print feature of taking-up and the vocal print feature Data Matching of the determination, verified according to matching result current inlet wire client whether be
The client itself of the inlet wire number, the client itself of the match is successful the current inlet wire client of explanation the is inlet wire number, it is on the contrary then not
It is.Compared with prior art, technical solution of the present invention is by the way of vocal print verifies client identity automatically, it is not necessary to passes through phone
Attendant is answered to verify client identity, it is enhanced convenience, accurate and efficiently, other people can also be avoided to usurp client's electricity
The situation that words number is dialed;It is accurate and safe and reliable in addition, by way of voice print verification, can without to converse into
Row recording, reduces the preservation of recording data, reduces carrying cost.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Structure according to these accompanying drawings obtains other accompanying drawings.
Fig. 1 is the flow chart of the embodiment of inlet wire personal identification method one of the present invention;
Fig. 2 is the flow chart of the embodiment of inlet wire personal identification method two of the present invention;
Fig. 3 is the flow chart of the embodiment of inlet wire personal identification method three of the present invention;
Fig. 4 is the running environment schematic diagram of inlet wire identification system preferred embodiment of the present invention;
Fig. 5 is the functional block diagram of the embodiment of inlet wire identification system one of the present invention;
Fig. 6 is the functional block diagram of the embodiment of inlet wire identification system two of the present invention;
Fig. 7 is the functional block diagram for the embodiment that extraction module is gathered in inlet wire identification system of the present invention;
Fig. 8 is the functional block diagram for the another embodiment that extraction module is gathered in inlet wire identification system of the present invention.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
The principle and feature of the present invention are described below in conjunction with accompanying drawing, the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
The present invention proposes a kind of inlet wire personal identification method.
As shown in figure 1, Fig. 1 is the flow chart of the embodiment of inlet wire personal identification method one of the present invention.
The inlet wire personal identification method of the present embodiment includes:
Step S10, after caller client is received, according to the mapping of predetermined telephone number and client identity information
Relation, obtain client identity information corresponding to current inlet wire number;
Have in the database of system telephone number and client identity information (such as, it may include user name, certificate number etc.)
Mapping table, the mapping table include all telephone numbers preserved in systems and it is corresponding with these telephone numbers visitor
Family identity information;After client's inlet wire incoming call is connected to, according to the number of inlet wire client from the telephone number and client identity information
Mapping table in, go to search to obtain client identity information corresponding to current inlet wire number;
Step S20, after successfully client identity information is obtained, according to predetermined client identity information and vocal print feature
The mapping relations of data, it is determined that client's vocal print feature data corresponding to the client identity information got;
Establish vocal print feature database in system for storage client, in the vocal print feature database advance typing save
The vocal print feature data of each storage client, and the mapping of vocal print feature data and client identity information is previously provided with system
Relation table, after the client identity information of current inlet wire number is successfully got, found out according to the client identity information got
Corresponding client's vocal print feature data.
Step S30, the speech data of inlet wire client is gathered, extracts the vocal print feature in the speech data collected;
Speech data of the inlet wire client in call is gathered, is analyzed according to the speech data of collection current to extract
The vocal print feature of inlet wire client.
Step S40, the vocal print feature extracted is matched with the client's vocal print feature data determined;
By the vocal print feature extracted according to the speech data of collection and client's vocal print according to client identity information determination
Characteristic is matched, and confirms whether both belong to the vocal print of same people;
Step S50, if the vocal print feature extracted and the client's vocal print feature Data Matching success determined, confirm current
Inlet wire client is client itself corresponding to the inlet wire number.
When the vocal print feature extracted according to the speech data of collection and the vocal print feature according to client identity information determination
Data Matching success, then the client itself that current inlet wire client is the inlet wire number is assured that, now can be according to client
Demand provides related service;If it fails to match, it is not the client itself of the inlet wire number to illustrate current inlet wire client, and having can
Can be stolen or other situations;In the case where it fails to match, system will not provide related service and give inlet wire client.
The scheme of the present embodiment first pass through inlet wire number obtain corresponding to client identity information, according to client identity information from
The vocal print feature data to be prestored corresponding to it are determined in vocal print feature database, will be carried from the speech data of current inlet wire client
The vocal print feature of taking-up and the vocal print feature Data Matching of the determination, verified according to matching result current inlet wire client whether be
The client itself of the inlet wire number, the client itself of the match is successful the current inlet wire client of explanation the is inlet wire number, it is on the contrary then not
It is.Compared with prior art, the technical scheme of the present embodiment is by the way of vocal print verifies client identity automatically, it is not necessary to passes through
Telephone receiving attendant verifies to client identity, enhanced convenience, accurate and efficiently, other people can also be avoided to usurp visitor
The situation that family telephone number is dialed;In addition, by way of voice print verification, it is accurate and safe and reliable, can be without to logical
Words are recorded, and reduce the preservation of recording data, reduce carrying cost.
As shown in Fig. 2 Fig. 2 is the flow chart of the embodiment of inlet wire personal identification method two of the present invention.
This embodiment scheme is based on an embodiment, and in the present embodiment, the inlet wire personal identification method also includes:
Step S60, after client identity information failure is obtained, the speech data of inlet wire client is gathered, extracts what is collected
Vocal print feature in speech data;
When being not enrolled for the situation of telephone number of record during current inlet wire number is system, according to telephone number and visitor
The mapping table of family identity information just can not find client identity information corresponding to current inlet wire number, that is, obtain client identity letter
Breath failure, in such cases, not can determine that current inlet wire client is not the storage client of company yet, it is likely to company's storage
Client is called in by the phone being not enrolled for;Therefore, system gathers to the speech data inlet wire of inlet wire client, and from adopting
Analysis extracts vocal print feature in the speech data of the inlet wire client of collection, to carry out follow-up verification operation according to vocal print feature.
Step S70, client's vocal print feature data in the vocal print feature and voice print database that extract are carried out one by one
Match somebody with somebody;
By the vocal print feature that will be extracted in the speech data of the inlet wire client from collection with vocal print feature database
All client's vocal print feature data matched one by one, to confirm to whether there is client's vocal print feature in vocal print feature database
Data match with the vocal print feature of current inlet wire client, so that it is determined that current inlet wire client whether be company storage client.
Step S80, if client's vocal print feature Data Matching success in the vocal print feature and voice print database that extract,
According to predetermined client identity information and the mapping relations of client's vocal print feature data, the vocal print feature extracted is confirmed
The client identity information corresponding to client's vocal print feature data being fitted on.
Matched when there are client's vocal print feature data in vocal print feature database with the vocal print feature of current inlet wire client
When, the client that illustrates current inlet wire is the telephone number inlet wire that the storage client of company was not enrolled for by company, now
It is special directly to find out the client's vocal print being matched according to client identity information and the mapping relations of client's vocal print feature data for system
Levy the client identity information corresponding to data, the identity information of as current inlet wire client.Certainly, if all it fails to match,
It is not storage client to illustrate inlet wire client, can now be handled by turning the artificial service of answering, or by default other manner
Carry out operation processing.
This embodiment scheme so that be not used in that telephone number preserved of the company of the service of offer in client and dialled
In the case of beating, the identity of client can also be gone out automatically by Application on Voiceprint Recognition, avoiding client must use what company preserved
Number carries out the limitation that incoming call could be identified the situation of identity, makes the more preferable service effectiveness of customer acquisition.
As shown in figure 3, Fig. 3 is the flow chart of the embodiment of inlet wire personal identification method three of the present invention.
The scheme of the present embodiment is based on an above-mentioned embodiment or two embodiments.In the present embodiment, the inlet wire identification
In method, gather inlet wire client speech data and the speech data that collects of extraction in vocal print feature the step of, including:
Step S101, the random character string for generating predetermined number character, reports the character string and prompting user repeats the word
Accord with the signal language of string;
System by random manner generate predetermined number character character string (for example, at random generation 8 words, letter,
The character string of any a variety of formation of numeral or more), and report the character string and report prompting user and repeat carrying for the character string
Show language (for example, " woulding you please repeat following sentence:********”).
Step S102, reception client repeat the speech data corresponding to the character string, extracted in the speech data received
Content, and the content for the character string that the content extracted is reported with system is compared;
System receives speech data when client repeats the character string that system generates at random, and content is carried out to the speech data
To extract the content in the speech data, the content for the character string that the content that this is extracted is reported with system is compared for analysis
It is right, to be confirmed whether that content is identical.
Step S103, after comparing successfully, extract the vocal print feature in the speech data received.
If comparing successfully, i.e., character that content that system is repeated according to client speech data is extracted is reported with system
The content of string is identical, then the vocal print feature in the speech data that client repeats then is extracted, to carry out the voice print verification of next step.
If comparison is unsuccessful, i.e., character string that content that system is repeated according to client speech data is extracted is reported with system
Content differs, and such case is probably because of situations such as client's slip of the tongue, client's accent weight cause, and now, then can be prompted
Client's recitations therein is wrong, and jumps to and perform step S101, provides character string again and is repeated for client to be compared again
Checking;In addition, if when comparing unsuccessful number more than default error thresholds, system can prompt customer authentication errors number mistake
It is more, client is gone into progress manual service at telephone receiving attendant, or the processing modes such as dropped calls can also be taken.
This embodiment scheme is generated character string system in a manner of stochastic and dynamic and repeated for client, and client is repeated
Speech data is as the data for vocal print feature extraction, and the comparison of progress client's recitations therein is tested before vocal print feature is extracted
Card, prevents other people using the recording data to voice of customers by the voice print verification of system, effectively ensure that voice print verification
Security.
Further, in the present embodiment, in the inlet wire personal identification method, the speech data of inlet wire client is gathered simultaneously
The step of extracting the vocal print feature in the speech data collected, in addition to:
If the vocal print feature extracted fails with the client's vocal print feature Data Matching determined, error count is set to add one;
In a practical situation, because environmental noise, client catch a cold what some objective factors such as sick may all extract
The matching of vocal print feature and client's vocal print feature of the determination impacts, therefore system can set multiple voice print verification machine
Meeting, when the vocal print feature extracted fails with the client's vocal print feature Data Matching determined, an error count is carried out, according to
The size of the value of error count determines whether that providing random generation character string again repeats for client to carry out voice print verification;
If the error count such as is less than at the default error count threshold value, step S101 is performed;
If the error count is less than or equal to default error count threshold value, that is, determine that voice print matching errors number does not have also
Having more than mistake allows number, now then jumps to and performs step S101, provides character string again and is repeated for client to enter again
Row checking;
If the error count exceedes default error count threshold value, emergency safety processing is carried out.
After the error count exceedes default error count threshold value, system no longer provides offer character string, and system is entered
The processing of row emergency safety.For example, emergency safety processing can be:1st, the contact mailbox or urgent reserved to current inlet wire number
Telephone number sends abnormity prompt message;2nd, current talking is interrupted, current inlet wire number is locked as abnormality, is made when advance
Wire size code can not carry out related service operation, etc..
This embodiment scheme makes client have the chance of multiple voice print verification, more meets demand during actual use, and
After exceeding certain number to voice print verification errors number, emergency safety processing is carried out, ensures the rights and interests of client.
In this case, the judgment mode of the matching result of vocal print feature can be by the matching degree of vocal print feature with it is default
Matching threshold is compared, and confirms as that the match is successful when more than default matching threshold, true during less than or equal to default matching threshold
Think that it fails to match.
The present invention also proposes a kind of inlet wire identification system.
Referring to Fig. 4, it is the running environment schematic diagram of the preferred embodiment of inlet wire identification system 10 of the present invention.
In the present embodiment, inlet wire identification system 10 is installed and run in electronic installation 1.Electronic installation 1 can be with
It is the computing devices such as desktop PC, notebook, palm PC and server.The electronic installation 1 may include, but not only limit
In memory 11, processor 12 and display 13.Fig. 3 illustrate only the electronic installation 1 with component 11-13, it should be understood that
Be, it is not required that implement all components shown, the more or less component of the implementation that can be substituted.
Memory 11 can be the internal storage unit of electronic installation 1 in certain embodiments, such as the electronic installation 1
Hard disk or internal memory.Memory 11 can also be the External memory equipment of electronic installation 1 in further embodiments, such as electronics dress
Put the plug-in type hard disk being equipped with 1, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card) etc..Further, memory 11 can also be both interior including electronic installation 1
Portion's memory cell also includes External memory equipment.Memory 11, which is used to store, is installed on the application software of electronic installation 1 and all kinds of
Data, such as program code of inlet wire identification system 10 etc..Memory 11 can be also used for temporarily storing and export
Or the data that will be exported.
Processor 12 can be in certain embodiments a central processing unit (Central Processing Unit,
CPU), microprocessor or other data processing chips, for the program code or processing data stored in run memory 11, example
Such as perform inlet wire identification system 10.
Display 13 can be in certain embodiments light-emitting diode display, liquid crystal display, touch-control liquid crystal display and
OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) touches device etc..Display 13 is used to be shown in
The information that is handled in electronic installation 1 and for showing visual user interface, such as business customizing interface etc..Electronic installation
1 part 11-13 is in communication with each other by system bus.
Referring to Fig. 5, it is the functional block diagram of the embodiment of inlet wire identification system 10 1 of the present invention.In the present embodiment
In, inlet wire identification system 10 can be divided into one or more modules, and one or more module is stored in storage
In device 11, and it is performed by one or more processors (the present embodiment is processor 12), to complete the present invention.For example, in Fig. 5
In, inlet wire identification system 10 can be divided into acquisition module 101, determining module 102, collection extraction module 103, first
The identity validation module 105 of matching module 104 and first.Module alleged by the present invention is to refer to complete a series of of specific function
Computer program instructions section, than program more suitable for describing the implementation procedure of inlet wire identification system 10 in the electronic apparatus 1,
Wherein:
Acquisition module 101, for after caller client is received, being believed according to predetermined telephone number and client identity
The mapping relations of breath, obtain client identity information corresponding to current inlet wire number;
Have in the database of system telephone number and client identity information (such as, it may include user name, certificate number etc.)
Mapping table, the mapping table include all telephone numbers preserved in systems and it is corresponding with these telephone numbers visitor
Family identity information;After client's inlet wire incoming call is connected to, acquisition module 101 is according to the number of inlet wire client from the telephone number and visitor
In the mapping table of family identity information, go to search to obtain client identity information corresponding to current inlet wire number;
Determining module 102, for successfully obtain client identity information after, according to predetermined client identity information with
The mapping relations of vocal print feature data, it is determined that client's vocal print feature data corresponding to the client identity information got;
Establish vocal print feature database in system for storage client, in the vocal print feature database advance typing save
The vocal print feature data of each storage client, and the mapping of vocal print feature data and client identity information is previously provided with system
Relation table, after the client identity information that acquisition module 101 successfully gets current inlet wire number, determining module 102 is according to obtaining
The client identity information got finds out corresponding client's vocal print feature data.
Extraction module 103 is gathered, for gathering the speech data of inlet wire client, extracts the sound in the speech data collected
Line feature;
Speech data of the inlet wire client in call is gathered, is analyzed according to the speech data of collection current to extract
The vocal print feature of inlet wire client.
First matching module 104, for by the vocal print feature extracted with determine client's vocal print feature data carry out
Match somebody with somebody;
The vocal print feature that first matching module 104 extracts collection extraction module 103 according to determining module 102 with determining
Client's vocal print feature data matched, to confirm whether both belong to the vocal print of same people;
First identity validation module 105, in the vocal print feature extracted and client's vocal print feature data of determination
After success, it is client itself corresponding to the inlet wire number to confirm current inlet wire client.
When the vocal print feature Data Matching that the vocal print feature that collection extraction module 103 extracts determines with determining module 102
Success, then the first identity validation module 105 determines that the client itself that current inlet wire client is the inlet wire number, now can root
Related service is provided according to customer demand;If it fails to match, the first identity validation module 105 then confirms that current inlet wire client is not
The client itself of the inlet wire number, it may be possible to stolen or other situations;In the case where it fails to match, system will not provide
Inlet wire client is given in related service.
The scheme of the present embodiment first pass through inlet wire number obtain corresponding to client identity information, according to client identity information from
The vocal print feature data to be prestored corresponding to it are determined in vocal print feature database, will be carried from the speech data of current inlet wire client
The vocal print feature of taking-up and the vocal print feature Data Matching of the determination, verified according to matching result current inlet wire client whether be
The client itself of the inlet wire number, the client itself of the match is successful the current inlet wire client of explanation the is inlet wire number, it is on the contrary then not
It is.Compared with prior art, the technical scheme of the present embodiment is by the way of vocal print verifies client identity automatically, it is not necessary to passes through
Telephone receiving attendant verifies to client identity, enhanced convenience, accurate and efficiently, other people can also be avoided to usurp visitor
The situation that family telephone number is dialed;In addition, by way of voice print verification, it is accurate and safe and reliable, can be without to logical
Words are recorded, and reduce the preservation of recording data, reduce carrying cost.
Referring to Fig. 6, it is the functional block diagram of the embodiment of inlet wire identification system 10 2 of the present invention.
This embodiment scheme is based on an embodiment, and in the present embodiment, the inlet wire identification system also includes second
The identity validation module 107 of matching module 106 and second, wherein:
Collection extraction module 103 is additionally operable to after client identity information failure is obtained, and gathers the speech data of inlet wire client,
Extract the vocal print feature in the speech data collected;The telephone number of record is not enrolled in current inlet wire number is system
Situation when, the corresponding client of current inlet wire number just can not find according to telephone number and the mapping table of client identity information
Identity information, that is, client identity information failure is obtained, in such cases, not can determine that current inlet wire client is not company yet
Storage client, it is likely to which company storage client is called in by the phone being not enrolled for;Therefore, now collection extraction mould
Block 103 gathers to the speech data inlet wire of inlet wire client, and analyzes extraction from the speech data of the inlet wire client of collection and speak
Line feature, to carry out follow-up verification operation according to vocal print feature.
Second matching module 106, for by client's vocal print feature number in the vocal print feature and voice print database that extract
According to being matched one by one;
Second matching module 106 passes through the vocal print feature and sound that will be extracted in the speech data of the inlet wire client from collection
All client's vocal print feature data in line property data base are matched one by one, to confirm whether deposited in vocal print feature database
Matched in client's vocal print feature data with the vocal print feature of current inlet wire client, so that it is determined that whether current inlet wire client is company
Storage client.
Second identity validation module 107, it is special for client's vocal print in the vocal print feature and voice print database extracted
After levying Data Matching success, according to predetermined client identity information and the mapping relations of client's vocal print feature data, confirm
The client identity information corresponding to client's vocal print feature data that the vocal print feature extracted matches.
Matched when there are client's vocal print feature data in vocal print feature database with the vocal print feature of current inlet wire client
When, the client that illustrates current inlet wire is the telephone number inlet wire that the storage client of company was not enrolled for by company, now
Second identity validation module 107 according to the mapping relations of client identity information and client's vocal print feature data, directly find out by
The client identity information corresponding to client's vocal print feature data being fitted on, the identity information of as current inlet wire client.Certainly, such as
All it fails to match for fruit, and it is not storage client to illustrate inlet wire client, can now be handled by turning the artificial service of answering, or press
Default other manner carries out operation processing.
This embodiment scheme so that be not used in that telephone number preserved of the company of the service of offer in client and dialled
In the case of beating, the identity of client can also be gone out automatically by Application on Voiceprint Recognition, avoiding client must use what company preserved
Number carries out the limitation that incoming call could be identified the situation of identity, makes the more preferable service effectiveness of customer acquisition.
As shown in fig. 7, in the present embodiment, the collection extraction module 103 of the inlet wire identification system 10 includes:
Submodule 1031 is generated, for generating the character string of predetermined number character at random, the character string is reported and prompting is used
Repeat the signal language of the character string in family;
System by random manner generate predetermined number character character string (for example, at random generation 8 words, letter,
The character string of any a variety of formation of numeral or more), and report the character string and report prompting user and repeat carrying for the character string
Show language (for example, " woulding you please repeat following sentence:********”).
Submodule 1032 is compared, speech data corresponding to the character string is repeated for receiving client, extracts what is received
Content in speech data, and the content for the character string that the content extracted is reported with system is compared;
Speech data when submodule 1032 receives the character string that client's repetition system generates at random is compared, to the voice number
According to content analysis is carried out to extract the content in the speech data, by the content that this is extracted and the character string of system report
Content is compared, to be confirmed whether that content is identical.
Extracting sub-module 1033, after comparing successfully, extract the vocal print feature in the speech data received.
If compare submodule 1032 to confirm to compare successfully, then extracting sub-module 1033 then extracts the voice number of client's repetition
Vocal print feature in, to carry out the voice print verification of next step.If comparing submodule 1032 confirms that comparison is unsuccessful, due to this
Kind now, then can prompt client's recitations therein to have it may be the case that because of situations such as client's slip of the tongue, client's accent weight cause
By mistake, and execution generation submodule 1031 is jumped to, character string is provided again and repeated for client so that checking to be compared again;Separately
Outside, if compare unsuccessful number more than default error thresholds, system can prompt customer authentication errors number excessive, by visitor
Family goes to progress manual service at telephone receiving attendant, or can also take the processing modes such as dropped calls.
This embodiment scheme is generated character string system in a manner of stochastic and dynamic and repeated for client, and client is repeated
Speech data is as the data for vocal print feature extraction, and the comparison of progress client's recitations therein is tested before vocal print feature is extracted
Card, prevents other people using the recording data to voice of customers by the voice print verification of system, effectively ensure that voice print verification
Security.
As shown in figure 8, in the present embodiment, the collection extraction module 103 of the inlet wire identification system 10 also includes:
Counting submodule 1034, for failing in the vocal print feature extracted with the client's vocal print feature Data Matching determined
Afterwards, error count is made to add one;
In a practical situation, because environmental noise, client catch a cold what some objective factors such as sick may all extract
The matching of vocal print feature and client's vocal print feature of the determination impacts, therefore system can set multiple voice print verification machine
Meeting, when the vocal print feature extracted fails with the client's vocal print feature Data Matching determined, an error count is carried out, according to
The size of the value of error count determines whether that providing random generation character string again repeats for client to carry out voice print verification;
Submodule 1035 is redirected, during for the default error count threshold value such as being less than in the error count, random generation
The character string of predetermined number character, the signal language reported the character string and prompt user to repeat the character string;
If the error count is less than or equal to default error count threshold value, that is, determine that voice print matching errors number does not have also
Having more than mistake allows number, now redirects submodule 1035 and handling process then is jumped into execution at generation submodule 1031,
Character string is provided again to repeat for client to be verified again;
Early warning submodule 1036, for after the error count exceedes default error count threshold value, promptly being pacified
Full processing.
After the error count exceedes default error count threshold value, early warning submodule 1036 is carried out at emergency safety
Reason.For example, emergency safety processing can be:1st, the contact mailbox or emergency call connection reserved to current inlet wire number are sent
Abnormity prompt message;2nd, current talking is interrupted, current inlet wire number is locked as abnormality, prevents current inlet wire number from entering
Row related service operation, etc..
This embodiment scheme makes client have the chance of multiple voice print verification, more meets demand during actual use, and
After exceeding certain number to voice print verification errors number, emergency safety processing is carried out, ensures the rights and interests of client.
In this case, the judgment mode of the matching result of vocal print feature can be by the matching degree of vocal print feature with it is default
Matching threshold is compared, and confirms as that the match is successful when more than default matching threshold, true during less than or equal to default matching threshold
Think that it fails to match.
The present invention also proposes a kind of computer-readable recording medium, and the computer-readable recording medium storage has inlet wire body
Part identifying system, the inlet wire identification system can be by least one computing device, so that at least one processor
Perform the inlet wire personal identification method described in any of the above-described embodiment.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the scope of the invention, it is every at this
Under the inventive concept of invention, the equivalent structure transformation made using description of the invention and accompanying drawing content, or directly/use indirectly
It is included in other related technical areas in the scope of patent protection of the present invention.
Claims (10)
1. a kind of electronic installation, it is characterised in that the electronic installation includes memory, processor and is stored in the memory
Inlet wire identification system that is upper and can running on the processor, the inlet wire identification system are held by the processor
Following steps are realized during row:
A, after caller client is received, according to predetermined telephone number and the mapping relations of client identity information, obtain
Client identity information corresponding to current inlet wire number;
B, after successfully client identity information is obtained, according to the mapping of predetermined client identity information and vocal print feature data
Relation, it is determined that client's vocal print feature data corresponding to the client identity information got;
C, the speech data of inlet wire client is gathered, extracts the vocal print feature in the speech data collected;
D, the vocal print feature extracted is matched with the client's vocal print feature data determined;
If vocal print feature E, extracted and the client's vocal print feature Data Matching success determined, confirm that current inlet wire client is
Client itself corresponding to the inlet wire number.
2. electronic installation as claimed in claim 1, it is characterised in that the inlet wire identification system is held by the processor
Following steps are also realized during row:
After client identity information failure is obtained, the speech data of inlet wire client is gathered, is extracted in the speech data collected
Vocal print feature;
The vocal print feature extracted is matched one by one with client's vocal print feature data in voice print database;
If client's vocal print feature Data Matching success in the vocal print feature and voice print database that extract, according to predetermined
Client identity information and client's vocal print feature data mapping relations, confirm client's sound that the vocal print feature extracted matches
Client identity information corresponding to line characteristic.
3. electronic installation as claimed in claim 1 or 2, it is characterised in that the speech data of the collection inlet wire client, extraction
The step of vocal print feature in the speech data collected, including:
F, the character string of predetermined number character is generated at random, the prompting reported the character string and prompt user to repeat the character string
Language;
G, reception client repeats the speech data corresponding to the character string, extracts the content in the speech data received, and will
The content for the character string that the content extracted is reported with system is compared;
H, after comparing successfully, the vocal print feature in the speech data received is extracted.
4. electronic installation as claimed in claim 3, it is characterised in that the speech data of the collection inlet wire client, extraction are adopted
The step of vocal print feature in the speech data collected, in addition to:
After the content for the character string that the content extracted and system are reported compares unsuccessfully, step F is performed.
5. electronic installation as claimed in claim 3, it is characterised in that the speech data of the collection inlet wire client, extraction are adopted
The step of vocal print feature in the speech data collected, in addition to:
If the vocal print feature extracted fails with the client's vocal print feature Data Matching determined, error count is set to add one;
If the error count is less than or equal to default error count threshold value, step F is performed;
If the error count exceedes default error count threshold value, emergency safety processing is carried out.
6. a kind of inlet wire personal identification method, it is characterised in that methods described includes:
A, after caller client is received, according to predetermined telephone number and the mapping relations of client identity information, obtain
Client identity information corresponding to current inlet wire number;
B, after successfully client identity information is obtained, according to the mapping of predetermined client identity information and vocal print feature data
Relation, it is determined that client's vocal print feature data corresponding to the client identity information got;
C, the speech data of inlet wire client is gathered, extracts the vocal print feature in the speech data collected;
D, the vocal print feature extracted is matched with the client's vocal print feature data determined;
If vocal print feature E, extracted and the client's vocal print feature Data Matching success determined, confirm that current inlet wire client is
Client itself corresponding to the inlet wire number.
7. inlet wire personal identification method as claimed in claim 6, it is characterised in that methods described also includes:
After client identity information failure is obtained, the speech data of inlet wire client is gathered, is extracted in the speech data collected
Vocal print feature;
The vocal print feature extracted is matched one by one with client's vocal print feature data in voice print database;
If client's vocal print feature Data Matching success in the vocal print feature and voice print database that extract, according to predetermined
Client identity information and client's vocal print feature data mapping relations, confirm client's sound that the vocal print feature extracted matches
Client identity information corresponding to line characteristic.
8. inlet wire personal identification method as claimed in claims 6 or 7, it is characterised in that the voice of the collection inlet wire client
Data, the step of extracting the vocal print feature in the speech data collected, including:
F, the character string of predetermined number character is generated at random, the prompting reported the character string and prompt user to repeat the character string
Language;
G, reception client repeats the speech data corresponding to the character string, extracts the content in the speech data received, and will
The content for the character string that the content extracted is reported with system is compared;
H, after comparing successfully, the vocal print feature in the speech data received is extracted.
9. inlet wire personal identification method as claimed in claim 8, it is characterised in that the voice number of the collection inlet wire client
According to, the step of extracting the vocal print feature in the speech data collected, in addition to:
If the vocal print feature extracted fails with the client's vocal print feature Data Matching determined, error count is set to add one;
If the error count is less than or equal to default error count threshold value, step F is performed;
If the error count exceedes default error count threshold value, emergency safety processing is carried out.
10. a kind of computer-readable recording medium, it is characterised in that the computer-readable recording medium storage has inlet wire identity
Identifying system, the inlet wire identification system can be by least one computing devices, so that at least one processor is held
Inlet wire personal identification method of the row as described in any one of claim 6-9.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710489752.2A CN107690036A (en) | 2017-06-24 | 2017-06-24 | Electronic installation, inlet wire personal identification method and computer-readable recording medium |
PCT/CN2017/104933 WO2018233137A1 (en) | 2017-06-24 | 2017-09-30 | Electronic device, calling identity recognition method and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710489752.2A CN107690036A (en) | 2017-06-24 | 2017-06-24 | Electronic installation, inlet wire personal identification method and computer-readable recording medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107690036A true CN107690036A (en) | 2018-02-13 |
Family
ID=61152635
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710489752.2A Pending CN107690036A (en) | 2017-06-24 | 2017-06-24 | Electronic installation, inlet wire personal identification method and computer-readable recording medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107690036A (en) |
WO (1) | WO2018233137A1 (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108766444A (en) * | 2018-04-09 | 2018-11-06 | 平安科技(深圳)有限公司 | User ID authentication method, server and storage medium |
CN108810295A (en) * | 2018-03-28 | 2018-11-13 | 平安科技(深圳)有限公司 | Service providing method, electronic equipment and storage medium |
CN108900326A (en) * | 2018-06-15 | 2018-11-27 | 中国联合网络通信集团有限公司 | Communication management information method and device |
CN109302541A (en) * | 2018-11-12 | 2019-02-01 | 平安科技(深圳)有限公司 | Electronic device, distribution method of attending a banquet and computer readable storage medium |
CN110619880A (en) * | 2019-10-14 | 2019-12-27 | 百可录(北京)科技有限公司 | Voiceprint processing system and user identification method |
CN111131635A (en) * | 2019-12-20 | 2020-05-08 | 中国银行股份有限公司 | Voice confirmation method and device for data request |
CN111563099A (en) * | 2020-07-02 | 2020-08-21 | 浙江百应科技有限公司 | CRM (customer relationship management) client duplicate checking method based on voiceprint recognition and electronic equipment thereof |
CN111813454A (en) * | 2020-07-07 | 2020-10-23 | 深圳微步信息股份有限公司 | Electronic device, startup picture display method and computer readable storage medium |
CN111833068A (en) * | 2020-07-31 | 2020-10-27 | 重庆富民银行股份有限公司 | Identity verification system and method based on voiceprint recognition |
CN113707157A (en) * | 2021-08-30 | 2021-11-26 | 平安科技(深圳)有限公司 | Identity verification method and device based on voiceprint recognition, electronic equipment and medium |
CN115021937A (en) * | 2022-06-21 | 2022-09-06 | 中国银行股份有限公司 | User identity authentication method, system, electronic equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1905445A (en) * | 2005-07-27 | 2007-01-31 | 国际商业机器公司 | System and method of speech identification using mobile speech identification card |
CN103501296A (en) * | 2013-09-27 | 2014-01-08 | 厦门天聪智能软件有限公司 | Social insurance survival authentication system based on voiceprint recognition technique and authentication method thereof |
CN103700371A (en) * | 2013-12-13 | 2014-04-02 | 江苏大学 | Voiceprint identification-based incoming call identity identification system and identification method |
US9247059B1 (en) * | 2014-11-03 | 2016-01-26 | Verizon Patent And Licensing Inc. | Priority token-based interactive voice response server |
CN105306657A (en) * | 2014-06-20 | 2016-02-03 | 中兴通讯股份有限公司 | Identity identification method, identity identification device and communication terminal |
CN105933493A (en) * | 2016-04-20 | 2016-09-07 | 乐视控股(北京)有限公司 | Strange incoming call processing method, device and mobile terminal |
-
2017
- 2017-06-24 CN CN201710489752.2A patent/CN107690036A/en active Pending
- 2017-09-30 WO PCT/CN2017/104933 patent/WO2018233137A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1905445A (en) * | 2005-07-27 | 2007-01-31 | 国际商业机器公司 | System and method of speech identification using mobile speech identification card |
CN103501296A (en) * | 2013-09-27 | 2014-01-08 | 厦门天聪智能软件有限公司 | Social insurance survival authentication system based on voiceprint recognition technique and authentication method thereof |
CN103700371A (en) * | 2013-12-13 | 2014-04-02 | 江苏大学 | Voiceprint identification-based incoming call identity identification system and identification method |
CN105306657A (en) * | 2014-06-20 | 2016-02-03 | 中兴通讯股份有限公司 | Identity identification method, identity identification device and communication terminal |
US9247059B1 (en) * | 2014-11-03 | 2016-01-26 | Verizon Patent And Licensing Inc. | Priority token-based interactive voice response server |
CN105933493A (en) * | 2016-04-20 | 2016-09-07 | 乐视控股(北京)有限公司 | Strange incoming call processing method, device and mobile terminal |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108810295A (en) * | 2018-03-28 | 2018-11-13 | 平安科技(深圳)有限公司 | Service providing method, electronic equipment and storage medium |
CN108766444A (en) * | 2018-04-09 | 2018-11-06 | 平安科技(深圳)有限公司 | User ID authentication method, server and storage medium |
CN108766444B (en) * | 2018-04-09 | 2020-11-03 | 平安科技(深圳)有限公司 | User identity authentication method, server and storage medium |
CN108900326A (en) * | 2018-06-15 | 2018-11-27 | 中国联合网络通信集团有限公司 | Communication management information method and device |
CN109302541A (en) * | 2018-11-12 | 2019-02-01 | 平安科技(深圳)有限公司 | Electronic device, distribution method of attending a banquet and computer readable storage medium |
CN110619880A (en) * | 2019-10-14 | 2019-12-27 | 百可录(北京)科技有限公司 | Voiceprint processing system and user identification method |
CN111131635A (en) * | 2019-12-20 | 2020-05-08 | 中国银行股份有限公司 | Voice confirmation method and device for data request |
CN111131635B (en) * | 2019-12-20 | 2020-11-10 | 中国银行股份有限公司 | Voice confirmation method and device for data request |
CN111563099A (en) * | 2020-07-02 | 2020-08-21 | 浙江百应科技有限公司 | CRM (customer relationship management) client duplicate checking method based on voiceprint recognition and electronic equipment thereof |
CN111813454B (en) * | 2020-07-07 | 2024-04-23 | 深圳微步信息股份有限公司 | Electronic device, startup picture display method and computer readable storage medium |
CN111813454A (en) * | 2020-07-07 | 2020-10-23 | 深圳微步信息股份有限公司 | Electronic device, startup picture display method and computer readable storage medium |
CN111833068A (en) * | 2020-07-31 | 2020-10-27 | 重庆富民银行股份有限公司 | Identity verification system and method based on voiceprint recognition |
CN113707157B (en) * | 2021-08-30 | 2023-08-01 | 平安科技(深圳)有限公司 | Voiceprint recognition-based identity verification method and device, electronic equipment and medium |
CN113707157A (en) * | 2021-08-30 | 2021-11-26 | 平安科技(深圳)有限公司 | Identity verification method and device based on voiceprint recognition, electronic equipment and medium |
CN115021937A (en) * | 2022-06-21 | 2022-09-06 | 中国银行股份有限公司 | User identity authentication method, system, electronic equipment and storage medium |
CN115021937B (en) * | 2022-06-21 | 2024-02-09 | 中国银行股份有限公司 | User identity authentication method, system, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2018233137A1 (en) | 2018-12-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107690036A (en) | Electronic installation, inlet wire personal identification method and computer-readable recording medium | |
AU2022201831B2 (en) | Call classification through analysis of DTMF events | |
US10778839B1 (en) | Detecting and preventing phishing phone calls through verified attribute analysis | |
US9607621B2 (en) | Customer identification through voice biometrics | |
CN105279416A (en) | Identity recognition method and system based on multi-biometric feature in combination with device fingerprint | |
US20050138391A1 (en) | Biometric multimodal centralized authentication service | |
CN103177238A (en) | Terminal and user identifying method | |
CN103078828A (en) | Cloud-model voice authentication system | |
CN107633169A (en) | A kind of terminal unlock method, terminal and computer-readable recording medium | |
CN109688273B (en) | Reminding method, reminding device, terminal and storage medium | |
US20100328035A1 (en) | Security with speaker verification | |
CN111125708B (en) | Vulnerability detection method and device | |
CN108428134A (en) | Electronic device, IVR voice payments method and computer readable storage medium | |
CN110322888A (en) | Credit card unlocking method, device, equipment and computer readable storage medium | |
CN108234785B (en) | Telephone sales prompting method, electronic device and readable storage medium | |
US20060281469A1 (en) | Employee tracking system with verification | |
CN109428804A (en) | A kind of account management method and device | |
WO2018222304A1 (en) | Improvements in biometric authentication | |
TWI548256B (en) | Contact identification system and method | |
JP2014072701A (en) | Communication terminal | |
US20140325689A1 (en) | Shutdown verification method and device | |
US20230188564A1 (en) | Detecting and Protecting Against Employee Targeted Phishing Attacks | |
WO2015032876A1 (en) | Method and system for authenticating a user/caller | |
CN205427857U (en) | Identity identification system based on many biological characteristics combine equipment fingerprint | |
CN112995128A (en) | Interface information automatic verification assembly and method based on artificial intelligence |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180213 |