Summary of the invention
For solving the problems of the technologies described above, the embodiment of the present application provides a kind of wireless traffic identity identifying method, equipment and system, to ensure the reliability of authentication.
The embodiment of the present application provides following technical scheme:
A kind of wireless traffic identity identifying method, comprising:
Server receives the ID authentication request that wireless traffic terminal sends;
Generate dynamic text and described dynamic text is handed down to described wireless traffic terminal;
Receive according to user the speech recognition text reading aloud generation of described dynamic text and vocal print feature from described wireless traffic terminal;
Described speech recognition text and vocal print feature is utilized to carry out authentication to described user, if described speech recognition text and described dynamic text match, and the vocal print feature that described vocal print feature and described user register matches, then determine one's identity authentication success; Otherwise determine one's identity authentification failure.
A kind of wireless traffic identity identifying method, comprising:
After wireless traffic terminal receives Client-initiated business operating instructions, send ID authentication request to server;
After described server receives the ID authentication request of wireless traffic terminal transmission, generate dynamic text, and described dynamic text is handed down to described wireless traffic terminal;
After described wireless traffic terminal receives described dynamic text, show described dynamic text and point out user to read aloud described dynamic text;
Described wireless traffic terminal gathers voice and the vocal print feature that user reads aloud described dynamic text, is speech recognition text, described speech recognition text and vocal print feature are sent to server by the speech conversion of collection;
After described server receives described speech recognition text and vocal print feature, described speech recognition text and vocal print feature is utilized to carry out authentication to described user, if described speech recognition text and described dynamic text match, and the vocal print feature that described vocal print feature and described user register matches, then authentication success; Otherwise authentication failure.
A kind of server, comprising:
Request reception unit, for receiving the ID authentication request that wireless traffic terminal sends;
Text issues unit, for after described request receiving element receives described ID authentication request, generates dynamic text, and described dynamic text is handed down to described wireless traffic terminal;
Information receiving unit, for receiving according to user the speech recognition text reading aloud generation of described dynamic text and vocal print feature from described wireless traffic terminal;
Identification authenticating unit, for utilizing described speech recognition text and vocal print feature, authentication is carried out to described user, if described speech recognition text and described dynamic text match, and the vocal print feature that described vocal print feature and described user register matches, then determine one's identity authentication success; Otherwise determine one's identity authentification failure.
A kind of Radio Service system, comprising: server and wireless traffic terminal;
Described service terminal comprises:
Authentication request unit, for after receiving Client-initiated business operating instructions, sends ID authentication request to server;
Receiving element, for receiving the dynamic text that described server issues;
Display unit, for showing described dynamic text and pointing out described user to read aloud described dynamic text;
Information acquisition unit, reads aloud voice and the vocal print feature of described dynamic text for gathering described user;
Converting unit, the speech conversion for described information acquisition unit being gathered is speech recognition text;
Transmitting element, for sending to described server by described speech recognition text and vocal print feature;
Described server comprises:
Request reception unit, for the ID authentication request that described reception wireless traffic terminal sends;
Text issues unit, for after described request receiving element receives described ID authentication request, generates dynamic text, and described dynamic text is handed down to described wireless traffic terminal;
Information receiving unit, for receiving described speech recognition text and vocal print feature from described wireless traffic terminal;
Identification authenticating unit, for utilizing described speech recognition text and vocal print feature, authentication is carried out to described user, if described speech recognition text and described dynamic text match, and the vocal print feature that described vocal print feature and described user register matches, then determine one's identity authentication success; Otherwise determine one's identity authentification failure.
The technical scheme that the embodiment of the present application provides, adopt the mode that dynamic voice identification combines with Application on Voiceprint Recognition, when user carries out business or account operation by wireless authentication, issue to user and show the word of one section of stochastic generation, i.e. dynamic text, then obtain according to user the speech recognition text reading aloud generation of described dynamic text and vocal print feature, whether the text that user reads aloud matches with this dynamic text to utilize speech recognition technology to determine, and determine whether the vocal print feature of vocal print feature and the user's registered in advance obtained matches further, if both all match, then determine one's identity authentication success otherwise the authentification failure that determines one's identity, thus ensure that the reliability of authentication.
Further, if authentication failure, then server forbids that user performs business operation corresponding to this authentication, and then ensure that the fail safe of wireless traffic.
Embodiment
Technical scheme in the application is understood better in order to make those skilled in the art person, below in conjunction with the accompanying drawing in the embodiment of the present application, technical scheme in the embodiment of the present application is clearly and completely described, obviously, described embodiment is only some embodiments of the present application, instead of whole embodiments.Based on the embodiment in the application, the every other embodiment that those of ordinary skill in the art obtain, all should belong to the scope of the application's protection.
At present, speech recognition technology is widely used in the multiple fields such as signal transacting, pattern recognition, artificial intelligence, and its target is computer-readable input by the vocabulary Content Transformation in the voice of the mankind, such as button, binary coding or character string.
The generation of human speech is a complicated physiology physical process between Body Languages maincenter and vocal organs, the phonatory organ such as tongue, tooth, larynx, lung, nasal cavity that people uses when talking everyone widely different in size and form, so the vocal print collection of illustrative plates of any two people is all variant.Everyone existing relative stability of Speech acoustics feature, has variability again, is not absolute, unalterable.This variation can from physiology, pathology, psychology, simulation, camouflage, also relevant with environmental interference.However, because everyone vocal organs are not quite similar, therefore in the ordinary course of things, still can distinguish the sound of different people or judge whether it is the sound of same people.
For this reason, the embodiment of the present application wireless traffic identity identifying method, equipment and system, adopt the identification authentication mode that dynamic voice identification combines with Application on Voiceprint Recognition, when user carries out account operation by wireless traffic, issue to user and show the word of one section of stochastic generation, i.e. dynamic text, then obtain according to user the speech recognition text reading aloud generation of described dynamic text and vocal print feature, utilize speech recognition technology, determine whether the text that user reads aloud matches with this dynamic text, and determine whether the vocal print feature of vocal print feature and the user's registered in advance obtained matches further, if both all match, then authentication success, user is allowed to perform business operation corresponding to this authentication, otherwise authentication failure, forbid this business operation, thus the fail safe of abundant guarantee business.
Described speech recognition refers to, is computer-readable input by the vocabulary Content Transformation in voice, to identify wherein comprised word content.
Described Application on Voiceprint Recognition refers to, automatically extracts the voiceprint of speaker from the voice signal that speaker sends, and to the research field that speaker identifies.Similar with fingerprint, the vocal print of different people is different, the behavior difference that everyone will be formed due to the differences of Physiological of vocal organs and the day after tomorrow, is made the vocal print in their voice all with strong personal colors, is gone out the vocal print feature in voice by prior art identifiable design.
In an embodiment of the application, provide a kind of wireless traffic identity identifying method, as shown in Figure 1, the method comprises following basic step:
Step 101, server receives the ID authentication request that wireless traffic terminal sends.
Described wireless traffic terminal can be to carry with and by WLAN (WirelessLocalAreaNetworks, WLAN), GPRS (GeneralPacketRadioService, general packet radio service), 3G (3rd-generation, G mobile communication) etc. the terminal equipment of wireless mode accessing Internet, such as mobile phone, net book etc.
Wireless traffic terminal can by the data cube computation (by WLAN, GPRS or 3G etc.) set up, based on agreements such as Https, Http, Socket, specifically can automatically select according to the equipment performance of the level of security of wireless traffic, client and network state at that time or pre-set protocol type, submit the ID authentication request of user by sending predefined required parameter, the packet through encryption or the private message transmitted in frame mode through encryption to server to.
Step 102, generates dynamic text and described dynamic text is handed down to described wireless traffic terminal.
After server receives the ID authentication request of described wireless traffic terminal transmission, generate the dynamic text for this ID authentication request, this dynamic text can be the random passage produced, for the ID authentication request of different user or the ID authentication request of same user's different time, the dynamic text produced can be identical, also can be different.
Such as, after service end receives the ID authentication request that user initiated by wireless traffic client, stochastic generation one section of dynamic text is as " fail safe is high ", and the interface channel set up by current wireless client and service end is as Wi-Fi, GPRS (GeneralPacketRadioService, general packet radio service technology) etc. radio channel be handed down to wireless traffic terminal, after wireless traffic terminal successfully receives dynamic text, in the wireless traffic client of correspondence, show " fail safe is high ", and point out user to read aloud text.
In order to ensure the fail safe of described dynamic text in transmitting procedure further, wireless traffic terminal can also be encrypted transmission to described dynamic text, certainly, the mode of encryption can be that server and wireless traffic terminal both sides consult, and also can make an appointment.
Step 103, receives according to user the speech recognition text reading aloud generation of described dynamic text and vocal print feature from described wireless traffic terminal.
Wireless traffic terminal shows described dynamic text and points out described user to read aloud described dynamic text after receiving the dynamic text that server issues, and such as when showing described dynamic text, can show following information: " please read aloud following word " simultaneously.Certainly, also can adopt other prompting mode, to this, the embodiment of the present application does not limit.
When user reads aloud described dynamic text, wireless traffic terminal gathers voice and the vocal print feature that user reads aloud described dynamic text, and is speech recognition text by the speech conversion of collection; Then described speech recognition text and vocal print feature are sent to described server.
Described wireless traffic terminal gathers voice and the vocal print feature that user reads aloud described dynamic text, and specifically can be realized by microphone, sound card, described sound card provides following functions: to signal filtering, amplification, sampling maintenance, A/D and D/A conversion etc.
Described is speech recognition text and speech recognition by the speech conversion of collection, refers to that by the vocabulary Content Transformation in voice be computer-readable input, to identify wherein comprised word content.Particularly, can adopt based on channel model and the method for phonic knowledge, the method for template matches and utilize in the method for artificial neural net one or more.The specific implementation process of speech recognition can be same as the prior art, do not repeat them here.
Step 104, judge whether described speech recognition text and described dynamic text match, and whether the vocal print feature that described vocal print feature and described user register matches, and if so, then performs step 105; Otherwise, perform step 106.
The vocal print feature of described user's registration can be the vocal print feature of reading aloud the extraction of pronunciation custom according to user by server of user preset, such as can be undertaken by following process:
User activate the service or registering account time, after submitting Association Identity documentary evidence to, select to open vocal print identity authentication function.Also can in business use procedure, when the susceptible of proof account holder really of submission Association Identity documentary evidence, vocal print identity authentication function is opened in application.
User is by terminal, and the voice call equipment such as such as PC terminal, mobile phone, landline telephone, carry out vocal print registering characteristics.Particularly, user initiates to open voiceprint registration request by terminal to server, after server receives this registration request, application terminal to user sends passage, and read aloud this section of word by the application terminal notifying user that user is current, such as, mobile terminal when user uses PC to apply for, then the screen display held by PC or speaker sound prompting; During as used the application of voice call equipment, then carry out voice message by current speech verbal system, after terminal collection user reads aloud the voice messaging of this section of word, by this transmission of speech information to server, after server receives this voice messaging, extraction user reads aloud the vocal print feature in the voice messaging of this section of word.Wherein, the vocal print feature in voice messaging also can be extracted by terminal, and then by terminal, by the vocal print feature of acquisition, non-voice information is sent to server, and concrete which kind of mode that adopts is determined by client at that time or environmental condition.Server is characterized as this user according to the vocal print in this voice messaging and sets up vocal print payment cipher, i.e. the vocal print feature of above-mentioned described user's registration.
Step 105, determine one's identity authentication success.
After authentication success, described server can allow described user to perform business operation corresponding to this authentication.
Step 106, determine one's identity authentification failure.
After authentication failure, described server can forbid that described user performs business operation corresponding to this authentication.
Further, after authentication failure, described server can also to described wireless traffic terminal return authentication failed message.Correspondingly, described wireless traffic terminal shows this message after receiving described authentification failure message.
And perform after business operation corresponding to this authentication complete user, described server can also return successful operation message to described wireless traffic terminal.Correspondingly, after described wireless traffic terminal receives described operation information, show this message, confirm this business operation success to make user.
The method of the embodiment of the present application wireless traffic authentication, the mode that the identification of employing dynamic voice combines with Application on Voiceprint Recognition is to realize the authentication in wireless traffic, the text read aloud due to user is by server end stochastic generation, even if therefore the vocal print feature of user is stolen, is also difficult to simulation and forges; And the coupling of vocal print feature completes at server end, completely isolated with wireless traffic terminal, and be that the vocal print feature registered with user matches, prevent machine simulation to read aloud, cannot be cracked in wireless traffic terminal.
In actual applications, fail safe can also be improved further by the mode of restriction single authenticated time and number of times.Such as, service end can require that wireless traffic terminal must return information to be certified in 30 seconds after receiving this authentication information, otherwise cancels this Business Processing by certification time-out.And for example, after continuous three authentification failures of user or time-out, this Business Processing of service end immediate cancel, to ensure the fail safe of customer service.
The embodiment of the present application wireless traffic identity identifying method, to hardware requirement and all lower to environmental requirement, can be widely used in multiple wireless traffic terminal, be specially adapted in the wireless traffic needing to carry out authentication, such as wireless payment business etc., fully ensure the fail safe of user account.
As shown in Figure 2, be a kind of flow chart of the embodiment of the present application wireless traffic identity identifying method, comprise the following steps:
Step 201, after wireless traffic terminal receives Client-initiated business operating instructions, sends ID authentication request to server;
Step 202, after described server receives the ID authentication request of wireless traffic terminal transmission, generates dynamic text;
Step 203, described dynamic text is handed down to described wireless traffic terminal by described server;
Step 204, after described wireless traffic terminal receives described dynamic text, shows described dynamic text and points out user to read aloud described dynamic text;
Step 205, described wireless traffic terminal gathers voice and the vocal print feature that user reads aloud described dynamic text, is speech recognition text by the speech conversion of collection;
Step 206, described speech recognition text and vocal print feature are sent to server by described wireless traffic terminal;
Step 207, after described server receives described speech recognition text and vocal print feature, described speech recognition text and vocal print feature is utilized to carry out authentication to described user, if described speech recognition text and described dynamic text match, and the vocal print feature that described vocal print feature and described user register matches, then authentication success; Otherwise authentication failure.
In embodiments of the present invention, after authentication success, described server can allow described user to perform business operation corresponding to this authentication.After authentication failure, described server can forbid that described user performs business operation corresponding to this authentication.
And after authentication failure, described server can also to described wireless traffic terminal return authentication failed message, step 208 as shown in Figure 2.Correspondingly, described wireless traffic terminal can show this message after receiving described authentification failure message.
In addition, perform after business operation corresponding to this authentication complete user, described server can also return successful operation message to described wireless traffic terminal.Correspondingly, after described wireless traffic terminal receives described operation information, show this message, confirm this business operation success to make user.
Correspondingly, in another embodiment of the application, provide a kind of server, as shown in Figure 3, this server 300 comprises:
Request reception unit 301, for receiving the ID authentication request that wireless traffic terminal sends;
Text issues unit 302, for after described request receiving element 201 receives described ID authentication request, generates dynamic text, and described dynamic text is handed down to described wireless traffic terminal;
Information receiving unit 303, for receiving according to user the speech recognition text reading aloud generation of described dynamic text and vocal print feature from described wireless traffic terminal;
Identification authenticating unit 304, for utilizing described speech recognition text and vocal print feature, authentication is carried out to described user, if described speech recognition text and described dynamic text match, and the vocal print feature that described vocal print feature and described user register matches, then determine one's identity authentication success; Otherwise determine one's identity authentification failure.
In another embodiment of the application, described server 300 also can comprise further:
Control unit (not shown), for after described identification authenticating unit 304 determines one's identity authentication success, allows described user to perform business operation corresponding to this authentication; After described identification authenticating unit 304 determines one's identity authentification failure, forbid that described user performs business operation corresponding to this authentication.
In another embodiment of the application, described server 300 also can comprise further: notification unit (not shown), for confirm authentication failure at described identification authenticating unit 304 after, to described wireless traffic terminal return authentication failed message.
Certainly, conveniently whether successfully user understands this operation, and described notification unit, after being also used in business operation success, returns successful operation message to described wireless traffic terminal, confirms this business operation success to make user.
The server of the embodiment of the present application, the mode adopting dynamic voice identification to combine with Application on Voiceprint Recognition realizes authenticating user identification, when user is by the operation of wireless traffic terminal carrying out service, dynamic text is issued to user, then obtain according to user the speech recognition text reading aloud generation of described dynamic text and vocal print feature, described speech recognition text and vocal print feature is utilized to carry out authentication to described user, if described speech recognition text and described dynamic text match, and the vocal print feature that described vocal print feature and described user register matches, then determine one's identity authentication success, otherwise determine one's identity authentification failure.Thus ensure that the reliability of authentication.Further, if authentication failure, server forbids that user performs business operation corresponding to this authentication, and then ensure that the fail safe of wireless traffic.
Correspondingly, in another embodiment of the application, provide a kind of Radio Service system, this system comprises: server and wireless traffic terminal.Wherein:
Described server, for receiving the ID authentication request that described wireless traffic terminal sends, and generates dynamic text, described dynamic text is handed down to described wireless traffic terminal after receiving described ID authentication request; Receive according to user the speech recognition text reading aloud generation of described dynamic text and vocal print feature from described wireless traffic terminal; Described speech recognition text and vocal print feature is utilized to carry out authentication to described user, if described speech recognition text and described dynamic text match, and the vocal print feature that described vocal print feature and described user register matches, then determine one's identity authentication success; Otherwise determine one's identity authentification failure.The concrete structure of described server with reference to the description of preceding embodiment, may not repeat them here.
Described wireless traffic terminal, for after receiving described Client-initiated business operating instructions, send described ID authentication request to described server, and receive the dynamic text of described server transmission, show described dynamic text and point out described user to read aloud described dynamic text; Gather voice and vocal print feature that described user reads aloud described dynamic text; Be speech recognition text by the speech conversion of collection; Described speech recognition text and vocal print feature are sent to described server.
As shown in Figure 4, a kind of structural representation of the wireless traffic terminal in the embodiment of the present application.
In this embodiment, described wireless traffic terminal 400 comprises:
Authentication request unit 401, for after receiving Client-initiated business operating instructions, sends ID authentication request to server;
Receiving element 402, for receiving the dynamic text that described server issues;
Display unit 403, for showing described dynamic text and pointing out described user to read aloud described dynamic text;
Information acquisition unit 404, reads aloud voice and the vocal print feature of described dynamic text for gathering described user;
Converting unit 405, the speech conversion for described information acquisition unit 404 being gathered is speech recognition text;
Transmitting element 406, for sending to described server by described speech recognition text and vocal print feature.
Conveniently user understands this certification whether success, and in the embodiment of the present application, described receiving element 402, also can be further used for receiving the authentification failure message that described server returns; Correspondingly, described display unit 403, is also further used for showing described authentification failure message.
Certainly, described receiving element 402 also can be further used for receiving the successful operation message that described server returns; Correspondingly, described display unit 403 also can be further used for showing described successful operation message.
The wireless traffic terminal of the embodiment of the present application can be to carry with and by the terminal equipment of the wireless mode accessing Internets such as WLAN, GPRS, 3G, such as mobile phone, net book etc.
The Radio Service system of the embodiment of the present application, the mode that the identification of employing dynamic voice combines with Application on Voiceprint Recognition, to realize the authentication in wireless traffic, fully ensures the reliability of authentication, and then ensure that the fail safe of customer service.
For convenience of description, various unit is divided into describe respectively with function when describing above equipment.Certainly, the function of each unit can be realized in same or multiple software and/or hardware when implementing the application.
As seen through the above description of the embodiments, those skilled in the art can be well understood to the mode that the application can add required general hardware platform by software and realizes.Based on such understanding, the technical scheme of the application can embody with the form of software product the part that prior art contributes in essence in other words, this computer software product can be stored in storage medium, as ROM/RAM, magnetic disc, CD etc., comprising some instructions in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) perform the method described in some part of each embodiment of the application or embodiment.
Each embodiment in this specification all adopts the mode of going forward one by one to describe, between each embodiment identical similar part mutually see, what each embodiment stressed is the difference with other embodiments.Especially, for system embodiment, because it is substantially similar to embodiment of the method, so describe fairly simple, relevant part illustrates see the part of embodiment of the method.System embodiment described above is only schematic, the wherein said unit illustrated as separating component or can may not be and physically separates, parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of module wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.Those of ordinary skill in the art, when not paying creative work, are namely appreciated that and implement.
The application can be used in numerous general or special purpose computing system environment or configuration.Such as: personal computer, server computer, handheld device or portable set, laptop device, multicomputer system, system, set top box, programmable consumer-elcetronics devices, network PC, minicom, mainframe computer, the distributed computing environment (DCE) comprising above any system or equipment etc. based on microprocessor.
The application can describe in the general context of computer executable instructions, such as program module.Usually, program module comprises the routine, program, object, assembly, data structure etc. that perform particular task or realize particular abstract data type.Also can put into practice the application in a distributed computing environment, in these distributed computing environment (DCE), be executed the task by the remote processing devices be connected by communication network.In a distributed computing environment, program module can be arranged in the local and remote computer-readable storage medium comprising memory device.
The above is only the embodiment of the application; it should be pointed out that for those skilled in the art, under the prerequisite not departing from the application's principle; can also make some improvements and modifications, these improvements and modifications also should be considered as the protection range of the application.