CN107105010B - Automobile user rapid login method and device based on GPS (global positioning system) position information - Google Patents
Automobile user rapid login method and device based on GPS (global positioning system) position information Download PDFInfo
- Publication number
- CN107105010B CN107105010B CN201710178182.5A CN201710178182A CN107105010B CN 107105010 B CN107105010 B CN 107105010B CN 201710178182 A CN201710178182 A CN 201710178182A CN 107105010 B CN107105010 B CN 107105010B
- Authority
- CN
- China
- Prior art keywords
- user
- voiceprint
- information
- storage unit
- feature code
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1021—Server selection for load balancing based on client or server locations
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0815—Network architectures or network communication protocols for network security for authentication of entities providing single-sign-on or federations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
Abstract
The invention relates to a method and a device for quickly logging in an automobile user based on GPS (global positioning system) position information, wherein more than two storage units for storing registration information of the user are preset, each storage unit is respectively provided with different information templates, the storage units are allocated to the storage units according to the geographical position of the user during registration during login verification, the retrieval range of a voiceprint characteristic code is locked in the corresponding storage unit through character information corresponding to voiceprint data input by the user, and a user name and a login password corresponding to the voiceprint characteristic code are extracted from the storage unit for logging in. The login can be carried out through the voiceprint data of the user, the user does not need to manually input a user name and a password, and the convenience and the intelligence of the login operation of the user are greatly improved; and the user information classified storage greatly reduces the time for comparing the voiceprint feature codes, so that the voice recognition can be applied to user login.
Description
Technical Field
The invention relates to the technical field of automobile safety, in particular to a method and a device for quickly logging in an automobile user by using GPS (global positioning system) position information.
Background
With the continuous development of automobile technology, the existing automobiles are developed in the direction of energy conservation and environmental protection and the direction of intelligent interconnection, and the functions in the automobiles are also more and more complex. In order to better manage these functions and facilitate interaction with the driver, a vehicle-mounted terminal such as a driving computer is usually installed in the vehicle. Information interaction between a driver and the vehicle-mounted terminal can be input through a control key or a touch screen; some vehicles may also be controlled by voice input, such as the agilawood system carried by a snowfrank vehicle. In the conventional vehicle-mounted terminal, user authentication is generally required before use, and the vehicle-mounted terminal can be used only by logging in after the authentication is passed.
In the prior art, the authentication of a user is mainly performed through a user name and a login password. In some implementations, there is also input of control instructions implemented through speech recognition. The current scheme of voice recognition and control instruction is mainly as follows: when the system is used, user voice collected from the voice collecting module is digitalized, the characteristic value of the voice is extracted, the voice characteristic value is matched and checked with the characteristic code in the voice command set stored in the system, the command is recognized, and then information communication and action are carried out with other controllers.
In the process of implementing the invention, the inventor finds that the following problems exist in the prior art, the existing vehicle-mounted terminal can only log in by verifying a user name and a password, the logging-in operation of the vehicle-mounted terminal is inconvenient, and the user is not convenient and fast to use and is not humanized. In the existing voice control method of the vehicle-mounted terminal, the voice control command data are stored and called based on one voice database, and the stored data volume is large, so that the system is huge, the updating speed is low, the cost is high, the flexibility of the system is low, and the updating and the expansion are not easy; when each voice instruction is judged to need to be retrieved and called from the whole database, the corresponding command subset is matched for checking, and the response time is relatively long. Because the number of registered automobile users is continuously increased, the stored user data is huge, the existing voice recognition scheme consumes long time, and the user identity cannot be recognized in a short time according to the pronunciation characteristics of the user, so that the existing voice recognition scheme is difficult to be applied to the identity recognition of the user during login.
Disclosure of Invention
Therefore, a method for logging in a vehicle user, which is faster and simpler to use, is needed to be provided, so as to solve the technical problem that it is inconvenient for the user to log in the vehicle-mounted terminal in the prior art and it takes long time to log in by adopting voice recognition.
In order to achieve the above object, the inventor provides a method for quickly logging in a vehicle user based on voiceprint recognition, comprising the following steps:
more than two storage units used for storing registration information of a user are preset, and each storage unit is respectively provided with different information templates;
when a user registers, acquiring GPS position information of the user, and distributing different users to different storage units according to the difference of the GPS position information; storing the acquired user name, login password and voiceprint data of the user into a corresponding storage unit, wherein the voiceprint data comprises voiceprint data which is subjected to pronunciation according to an information template of the allocated storage unit and a voiceprint feature code corresponding to the voiceprint data;
when a user logs in, acquiring voiceprint data input by the user, identifying character information corresponding to the voiceprint data of the user, and extracting a voiceprint feature code of the user from the voiceprint data; and determining a storage unit for storing user information according to the character information, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for login.
Further, the voiceprint data is acquired through a sound pickup of the automobile-mounted terminal; each storage unit is arranged on the cloud server; when a user logs in, recognizing text information corresponding to user voiceprint data through an automobile-mounted terminal, and sending the voiceprint data and the text information to a cloud server; extracting a voiceprint feature code of a user from the voiceprint data through a cloud server, determining a storage unit for storing user information according to the received character information, retrieving whether a voiceprint feature code matched with the user exists from the storage unit, if so, determining that the user is a registered user, and extracting a user name and a login password corresponding to the voiceprint feature code for login; if not, the user is refused to log in.
Further, the voiceprint feature code includes acoustic features and prosodic features.
Further, the allocating different users to different storage units according to the difference of the GPS location information includes the following steps:
determining province or city of the user during registration according to the GPS position information;
the users are assigned to different storage units according to different provinces or cities.
Further, when the user registers, the voiceprint feature code corresponding to the voiceprint data is obtained through the following steps:
acquiring voiceprint data of a user for pronunciation by using the same information template more than twice;
judging whether the similarity of the feature codes in the acquired voiceprint data is greater than a preset value or not, if so, successfully extracting the voiceprint feature codes; if not, the extraction of the voiceprint feature code fails.
In order to solve the technical problem, the inventor provides another technical scheme: a vehicle user rapid login device based on GPS position information comprises a preset unit, a registration unit and a login unit;
the preset unit is used for presetting more than two storage units for storing the registration information of the user, and each storage unit is respectively provided with different information templates;
the registration unit is used for acquiring GPS position information of the user when the user registers, and distributing different users to different storage units according to the difference of the GPS position information; storing the acquired user name, login password and voiceprint data of the user into a corresponding storage unit, wherein the voiceprint data comprises voiceprint data which is subjected to pronunciation according to an information template of the allocated storage unit and a voiceprint feature code corresponding to the voiceprint data;
the login unit is used for acquiring voiceprint data input by a user when the user logs in, identifying character information corresponding to the voiceprint data of the user, and extracting a voiceprint feature code of the user from the voiceprint data; and determining a storage unit for storing user information according to the character information, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for login.
Further, the voiceprint data is acquired through a sound pickup of the automobile-mounted terminal; each storage unit is arranged on the cloud server;
the login unit identifies text information corresponding to user voiceprint data through the automobile-mounted terminal when the user logs in and verifies, and sends the voiceprint data and the text information to the cloud server; extracting a voiceprint feature code of a user from the voiceprint data through a cloud server, determining a storage unit for storing user information according to the received character information, retrieving whether a voiceprint feature code matched with the user exists from the storage unit, if so, determining that the user is a registered user, and extracting a user name and a login password corresponding to the voiceprint feature code for login; if not, the user is refused to log in.
Further, the voiceprint feature code includes acoustic features and prosodic features.
Further, the registering unit allocates different users to different storage units according to the difference of the GPS location information, and specifically includes:
determining province or city of the user during registration according to the GPS position information;
the users are assigned to different storage units according to different provinces or cities.
Further, when the registration unit performs user registration, the obtaining the voiceprint feature code corresponding to the voiceprint data specifically includes:
acquiring voiceprint data of a user for pronunciation by using the same information template more than twice;
judging whether the similarity of the feature codes in the acquired voiceprint data is greater than a preset value or not, if so, successfully extracting the voiceprint feature codes; if not, the extraction of the voiceprint feature code fails.
Different from the prior art, the technical scheme is that more than two storage units for storing the registration information of the user are preset in the technical scheme, each storage unit is provided with a different information template, when the user registers, the storage units are distributed to the user according to the GPS position information of the user, so that the registration information of different users can be uniformly distributed to the storage units, and the stored registration information comprises a user name, a login password, voiceprint data for the user to pronounce by using the information template of the corresponding storage unit and a feature code of the voiceprint data; when the user logs in and verifies, recognizing character information corresponding to voiceprint data input by the user and a feature code of the voiceprint of the user, determining a storage unit for storing the user information according to the character information, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for logging in. According to the technical scheme, the storage units are distributed for the user through the GPS position information during registration of the user, so that the registration information of the user can be uniformly distributed to different storage units, each storage unit is provided with different information templates, when login verification is carried out, the retrieval range of the voiceprint feature code is locked in the corresponding storage unit through the text information (namely the information templates) corresponding to the voiceprint data input by the user, and the user name and the login password corresponding to the voiceprint feature code are extracted from the storage units for login, so that the data volume and the time for comparing the voiceprint feature codes are greatly reduced. According to the technical scheme, the user can log in through the voiceprint data of the user, the user does not need to manually input a user name and a password, and the convenience and the intelligence of the user login operation are greatly improved; and the user information classified storage greatly reduces the time for comparing the voiceprint feature codes, so that the voice recognition can be applied to the login of automobile users.
Drawings
FIG. 1 is a schematic flow chart illustrating a method for a vehicle user to quickly log in based on GPS location information according to an embodiment;
FIG. 2 is a schematic diagram of a memory cell in accordance with an embodiment;
fig. 3 is a block diagram of an embodiment of an apparatus for quickly logging in a vehicle user based on GPS location information.
Description of the drawings the reference numerals indicate:
10. a preset unit;
20. a registration unit;
30. a login unit;
40. and a cloud server.
Detailed Description
To explain technical contents, structural features, and objects and effects of the technical solutions in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
Referring to fig. 1, the present embodiment provides a method for a vehicle user to log in quickly based on GPS location information, which includes the following steps:
step S110: more than two storage units used for storing registration information of a user are preset, and each storage unit is respectively provided with different information templates;
step S120: when a user registers, acquiring GPS position information of the user, and distributing different users to different storage units according to the difference of the GPS position information; storing the acquired user name, login password and voiceprint data of the user into a corresponding storage unit, wherein the voiceprint data comprises voiceprint data which is subjected to pronunciation according to an information template of the allocated storage unit and a voiceprint feature code corresponding to the voiceprint data;
step S130: when a user logs in, acquiring voiceprint data input by the user, identifying character information corresponding to the voiceprint data of the user, and extracting a voiceprint feature code of the user from the voiceprint data; and
step S140: and determining a storage unit for storing user information according to the character information, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for login.
In an embodiment, two or more of said storage units are provided, and each storage unit is provided with a different information template, and each storage unit is arranged for a user to store registration information of users in different regions. The information template can be a string of character information or information simultaneously containing characters, numbers or characters, and is used for the pronunciation of the user when the user registers and collects voiceprint data. For example, when the user registers to collect the voiceprint data, the information template is displayed on a display screen in the automobile, and the user pronounces and reads the information template, so that the voiceprint data of the user is adopted through an in-automobile sound pickup. FIG. 2 is a diagram illustrating a memory cell according to an embodiment. In fig. 2, a total of three storage units, i.e., a first storage unit, a second storage unit, and a third storage unit, are included, each of which is provided with a different information template and is configured such that users store registration information of users in different regions. Therefore, the users stored in the same storage unit adopt the same information template to acquire the voiceprint data during registration; and all users are registered in the same region.
When the user registers, the GPS position information of the user during registration can be acquired through the vehicle-mounted GPS equipment or the GPS module of the mobile terminal, and the user is allocated with the corresponding storage unit according to the GPS position information. When the storage unit is allocated, the area to which the position of the user is located when the user is registered can be determined according to the acquired GPS position information, and the storage unit is allocated according to the determined area, so that the users in the same area are allocated to the same storage unit. The range of the region can be set according to the requirement, and can be a large region (such as northeast, south China, west China and the like), province or city. In allocating storage units, users of the same province or city may be allocated to the same storage unit. After the storage unit is allocated to the user, the user name, login password, voiceprint data and other registration information of the user can be acquired. After the storage unit allocated by the user is obtained, the information template set by the storage unit can be obtained, so that the information template can be displayed through display equipment such as a display screen, and the user is prompted to pronounce according to the information template, and then the voiceprint data of the user is collected. The voiceprint data can be acquired after the storage unit of the registration information is determined, and other registration information except the voiceprint data can be acquired before the storage unit is allocated, and then the registration information is stored in the allocated storage unit.
More than two storage units are preset, and different information templates are set for each storage unit; when a user registers, classifying according to GPS position information when the user registers, and allocating storage units for the user, wherein registered users are uniformly distributed in different regions under normal conditions, so that the registration information of different users can be uniformly allocated to the storage units; when acquiring the user registration information, each user pronounces according to the information template of the allocated storage unit so as to acquire voiceprint data of the user, acquire a user name and a login password of the user, analyze a voiceprint feature code of the user from the voiceprint data, and store the voiceprint feature code in the allocated storage unit in an associated manner; when the user logs in and verifies, recognizing character information corresponding to voiceprint data input by the user and a feature code of the voiceprint of the user, determining a storage unit for storing the user information according to the character information, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for logging in.
According to the technical scheme, more than two storage units are arranged, the corresponding information template is arranged for each storage unit, and the storage units are distributed to the user according to the geographical position of the user during registration when the user registers, so that a large amount of user registration information can be uniformly distributed to a plurality of storage units for storage, and the registration information can be prevented from being intensively stored in individual storage units. And during login verification, locking the retrieval range of the voiceprint feature code in a corresponding storage unit through the text information corresponding to the voiceprint data input by the user, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for login. According to the technical scheme, the user can log in through the voiceprint data of the user, the user does not need to manually input a user name and a password, and the convenience and the intelligence of the user login operation are greatly improved; and the user information classified storage greatly reduces the time for comparing the voiceprint feature codes, so that the voice recognition can be applied to user login.
Referring to fig. 2, a specific user registration process is described below to illustrate an application of the above technical solution. The system respectively sets an information template for each storage unit, for example, the information template of the storage unit I is the information template I 'cloud degree automobile change trivial', the information template of the storage unit II is the information template II 'cloud degree automobile pursuit excellent', and the information template of the storage unit III is the information template III 'one-way safety'. And different storage units are respectively arranged for storing user registration information of different regions, for example, a storage unit I is used for storing registered users in a mansion region, a storage unit II is used for storing registered users in a Putian region, and a storage unit III is used for storing registered users in the Putian region.
When a user registers, GPS position information of the user during registration is obtained, the position of the user is determined according to the position information, for example, the user is distributed to a first storage unit when the user is located in a building door, the system prompts the user to pronounce according to an information template I 'cloud automobile change trivial' corresponding to the first storage unit so as to obtain corresponding user voiceprint data, besides the user voiceprint data, the system also obtains a user name and a login password of the user, and the obtained user name, the login password and the voiceprint feature code of the user are stored in the distributed first storage unit in an associated mode. When a user logs in and verifies, the system requires the user to input voiceprint data, namely, pronounces according to an information template adopted during registration, so that the character information 'cloud automobile change trivial' corresponding to the voiceprint data input by the user and the feature code of the voiceprint of the user are identified, the registration information of the user can be determined to be stored in the storage unit I according to the character information 'cloud automobile change trivial', whether the voiceprint feature code matched with the voiceprint feature code of the user exists in the storage unit I is searched, and after the feature code is matched, the user name and the login password corresponding to the voiceprint feature code are extracted for logging in. By the technical scheme, the number of voiceprint feature code retrieval and comparison during login of a user can be greatly reduced, the retrieval and comparison time is effectively reduced, and the voiceprint verification efficiency is greatly improved.
In the embodiment, in order to conveniently acquire voiceprint data of a user, the voiceprint data is acquired through a sound pickup of an automobile-mounted terminal; the storage unit is arranged on the cloud server; when a user logs in, recognizing text information corresponding to user voiceprint data through an automobile-mounted terminal, and sending the voiceprint data and the text information to a cloud server; extracting a voiceprint feature code of a user from the voiceprint data through a cloud server, determining a storage unit for storing user information according to the received character information, retrieving whether a voiceprint feature code matched with the user exists from the storage unit, if so, determining that the user is a registered user, and extracting a user name and a login password corresponding to the voiceprint feature code for login; if not, the user is refused to log in. Acquiring voiceprint data of a user by using a sound pickup on a vehicle-mounted terminal on a vehicle, establishing a storage unit corresponding to each information module on a cloud server, identifying text information corresponding to the voiceprint data of the user by using the vehicle-mounted terminal on the vehicle, simultaneously sending the voiceprint data and the text information to the cloud server, extracting a voiceprint feature code of the user from the voiceprint data by using the cloud server, determining a target storage unit according to the received text information, retrieving whether the voiceprint feature code matched with the user exists in the target storage unit, and if so, extracting a user name and a login password for login if so, wherein the user is a registered user; if not, the user authentication is not passed, and login is refused. The voice input is facilitated for a user by utilizing a sound pick-up of a vehicle-mounted terminal on a vehicle, so that voiceprint data of the user are acquired, and the user is rapidly helped to verify by utilizing full utilization of network resources and the like of a cloud server.
In this embodiment, in order to increase the accurate verification of the voiceprint feature code, the voiceprint feature code includes an acoustic feature, a lexical feature, and a prosodic feature. By verifying the acoustic features (cepstrum) and the prosodic features (pitch and energy 'posture' described by n-gram), the voiceprint feature code can be verified more accurately.
In this embodiment, in order to effectively identify the voiceprint feature code, the comparing whether the voiceprint feature code of the user matches the voiceprint feature code in the target storage unit specifically includes: by comparing the voiceprint feature code of the user with the voiceprint feature code in the target storage unit, when the similarity value between the voiceprint feature code of the user and the voiceprint feature code in the target storage unit exceeds a set value, it is determined that the voiceprint feature code of the user is matched with the voiceprint feature code in the target storage unit, and if the similarity value is lower than the set value, the voiceprint feature code of the user is not matched with the voiceprint feature code in the target storage unit, in this embodiment. Due to the influence of various environments and the like, the voiceprint feature code of the user cannot be matched with the voiceprint feature code in the target storage unit by 100%, the voiceprint feature code of the user is compared with the voiceprint feature code in the target storage unit, matching is confirmed when the similarity value exceeds a set value, and in the embodiment, the voiceprint feature code is effectively identified and the possibility of errors is reduced by setting the similarity value to be 80%. In other embodiments, the set value may also be set to other values.
In this embodiment, in order to increase the extraction accuracy of the voiceprint feature code, when the registration unit registers the user, the extracting the voiceprint feature code of the user from the voiceprint data specifically includes: acquiring voiceprint data of a user for pronunciation by using the same information template more than twice; judging whether the similarity of the feature codes in the acquired voiceprint data is greater than a preset value or not, if so, successfully extracting the voiceprint feature codes; if not, the extraction of the voiceprint feature code fails. The voiceprint data of a user, which are pronounced by using the same information template, are obtained more than twice, feature code similarity is compared according to the voiceprint data obtained for several times, when the feature code similarity exceeds a preset value, voiceprint feature code extraction is successful, if the feature code similarity does not exceed the preset value, the voiceprint feature code extraction fails, extraction needs to be carried out again, and further the voiceprint feature code extraction accuracy is improved.
Referring to fig. 3, another embodiment of a device for fast logging in a vehicle user based on GPS location information includes a preset unit 10, a registration unit 20, and a login unit 30;
the preset unit 10 is used for presetting more than two storage units for storing the registration information of the user, and each storage unit is respectively provided with different information templates;
the registration unit 20 is configured to acquire GPS location information of a user when the user registers, and allocate different users to different storage units according to differences in the GPS location information; storing the acquired user name, login password and voiceprint data of the user into a corresponding storage unit, wherein the voiceprint data comprises voiceprint data which is subjected to pronunciation according to an information template of the allocated storage unit and a voiceprint feature code corresponding to the voiceprint data;
the login unit 30 is configured to obtain voiceprint data input by a user when the user logs in, identify text information corresponding to the voiceprint data of the user, and extract a voiceprint feature code of the user from the voiceprint data;
and determining a storage unit for storing user information according to the character information, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for login.
In an embodiment, two or more of said storage units are provided, and each storage unit is provided with a different information template, and each storage unit is arranged for a user to store registration information of users in different regions. The information template can be a string of character information or information simultaneously containing characters, numbers or characters, and is used for the pronunciation of the user when the user registers and collects voiceprint data. For example, when the user registers to collect the voiceprint data, the information template is displayed on a display screen in the automobile, and the user pronounces and reads the information template, so that the voiceprint data of the user is adopted through an in-automobile sound pickup. The users stored in the same storage unit adopt the same information template to carry out voiceprint data acquisition during registration; and all users are registered in the same region.
When the user registers, the GPS position information of the user during registration can be acquired through the vehicle-mounted GPS equipment or the GPS module of the mobile terminal, and the user is allocated with the corresponding storage unit according to the GPS position information. When the storage unit is allocated, the area to which the position of the user is located when the user is registered can be determined according to the acquired GPS position information, and the storage unit is allocated according to the determined area, so that the users in the same area are allocated to the same storage unit. The range of the region can be set according to the requirement, and can be a large region (such as northeast, south China, west China and the like), province or city. In allocating storage units, users of the same province or city may be allocated to the same storage unit. After the storage unit is allocated to the user, the user name, login password, voiceprint data and other registration information of the user can be acquired. After the storage unit allocated by the user is obtained, the information template set by the storage unit can be obtained, so that the information template can be displayed through display equipment such as a display screen, and the user is prompted to pronounce according to the information template, and then the voiceprint data of the user is collected. The voiceprint data can be acquired after the storage unit of the registration information is determined, and other registration information except the voiceprint data can be acquired before the storage unit is allocated, and then the registration information is stored in the allocated storage unit.
More than two storage units are preset, and different information templates are set for each storage unit; when a user registers, classifying according to GPS position information when the user registers, and allocating storage units for the user, wherein registered users are uniformly distributed in different regions under normal conditions, so that the registration information of different users can be uniformly allocated to the storage units; when acquiring the user registration information, each user pronounces according to the information template of the allocated storage unit so as to acquire voiceprint data of the user, acquire a user name and a login password of the user, analyze a voiceprint feature code of the user from the voiceprint data, and store the voiceprint feature code in the allocated storage unit in an associated manner; when the user logs in and verifies, recognizing character information corresponding to voiceprint data input by the user and a feature code of the voiceprint of the user, determining a storage unit for storing the user information according to the character information, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for logging in.
In the embodiment, the voiceprint data is acquired through a sound pickup of the vehicle-mounted terminal; each storage unit is arranged on the cloud server 40; the login unit identifies text information corresponding to user voiceprint data through the automobile-mounted terminal when the user logs in and verifies, and sends the voiceprint data and the text information to the cloud server; extracting a voiceprint feature code of a user from the voiceprint data through a cloud server, determining a storage unit for storing user information according to the received character information, retrieving whether a voiceprint feature code matched with the user exists from the storage unit, if so, determining that the user is a registered user, and extracting a user name and a login password corresponding to the voiceprint feature code for login; if not, the user is refused to log in. Acquiring voiceprint data of a user by using a sound pickup on a vehicle-mounted terminal on a vehicle, establishing a storage unit corresponding to each information module on a cloud server, identifying text information corresponding to the voiceprint data of the user by using the vehicle-mounted terminal on the vehicle, simultaneously sending the voiceprint data and the text information to the cloud server, extracting a voiceprint feature code of the user from the voiceprint data by using the cloud server, determining a target storage unit according to the received text information, retrieving whether the voiceprint feature code matched with the user exists in the target storage unit, and if so, extracting a user name and a login password for login if so, wherein the user is a registered user; if not, the user authentication is not passed, and login is refused. The voice input is facilitated for a user by utilizing a sound pick-up of a vehicle-mounted terminal on a vehicle, so that voiceprint data of the user are acquired, and the user is rapidly helped to verify by utilizing full utilization of network resources and the like of a cloud server.
In this embodiment, in order to increase the accurate verification of the voiceprint feature code, the voiceprint feature code includes an acoustic feature, a lexical feature, and a prosodic feature. By verifying the acoustic features (cepstrum) and the prosodic features (pitch and energy 'posture' described by n-gram), the voiceprint feature code can be verified more accurately.
In this embodiment, in order to effectively identify the voiceprint feature code, the comparing whether the voiceprint feature code of the user matches the voiceprint feature code in the target storage unit specifically includes: comparing the voiceprint feature code of the user with the voiceprint feature code in the target storage unit, confirming the matching when the similarity value of the voiceprint feature code of the user and the voiceprint feature code in the target storage unit exceeds a set value, and not matching when the similarity value is lower than the set value. The voiceprint feature code of the user cannot be matched with the voiceprint feature code in the target storage unit by 100% due to the influence of various environments and the like, and the voiceprint feature code of the user is compared with the voiceprint feature code in the target storage unit, and when the similarity value exceeds a set value, the matching is confirmed. In the present embodiment, by setting the similarity value to 80%, the voiceprint feature code is effectively identified, and the possibility of errors is reduced.
In this embodiment, in order to increase the extraction accuracy of the voiceprint feature code, when the registration unit registers the user, the extracting the voiceprint feature code of the user from the voiceprint data specifically includes: acquiring voiceprint data of a user for pronunciation by using the same information template more than twice; judging whether the similarity of the feature codes in the acquired voiceprint data is greater than a preset value or not, if so, successfully extracting the voiceprint feature codes; if not, the extraction of the voiceprint feature code fails. The voiceprint data of a user, which are pronounced by using the same information template, are obtained more than twice, feature code similarity is compared according to the voiceprint data obtained for several times, when the feature code similarity exceeds a preset value, voiceprint feature code extraction is successful, if the feature code similarity does not exceed the preset value, the voiceprint feature code extraction fails, extraction needs to be carried out again, and further the voiceprint feature code extraction accuracy is improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrases "comprising … …" or "comprising … …" does not exclude the presence of additional elements in a process, method, article, or terminal that comprises the element. Further, herein, "greater than," "less than," "more than," and the like are understood to exclude the present numbers; the terms "above", "below", "within" and the like are to be understood as including the number.
As will be appreciated by one skilled in the art, the above-described embodiments may be provided as a method, apparatus, or computer program product. These embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. All or part of the steps in the methods according to the embodiments may be implemented by a program instructing associated hardware, where the program may be stored in a storage medium readable by a computer device and used to execute all or part of the steps in the methods according to the embodiments. The computer devices, including but not limited to: personal computers, servers, general-purpose computers, special-purpose computers, network devices, embedded devices, programmable devices, intelligent mobile terminals, intelligent home devices, wearable intelligent devices, vehicle-mounted intelligent devices, and the like; the storage medium includes but is not limited to: RAM, ROM, magnetic disk, magnetic tape, optical disk, flash memory, U disk, removable hard disk, memory card, memory stick, network server storage, network cloud storage, etc.
The various embodiments described above are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a computer apparatus to produce a machine, such that the instructions, which execute via the processor of the computer apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer apparatus to cause a series of operational steps to be performed on the computer apparatus to produce a computer implemented process such that the instructions which execute on the computer apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the embodiments have been described, once the basic inventive concept is obtained, other variations and modifications of these embodiments can be made by those skilled in the art, so that the above embodiments are only examples of the present invention, and not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes using the contents of the present specification and drawings, or any other related technical fields, which are directly or indirectly applied thereto, are included in the scope of the present invention.
Claims (8)
1. A method for quickly logging in an automobile user based on GPS position information is characterized by comprising the following steps:
more than two storage units used for storing registration information of a user are preset, and each storage unit is respectively provided with different information templates;
when a user registers, acquiring GPS position information of the user, and distributing different users to different storage units according to the difference of the GPS position information; storing the acquired user name, login password and voiceprint data of the user into a corresponding storage unit, wherein the voiceprint data comprises voiceprint data which is subjected to pronunciation according to an information template of the allocated storage unit and a voiceprint feature code corresponding to the voiceprint data, and the voiceprint feature code comprises acoustic features and rhythm features;
when a user logs in, acquiring voiceprint data input by the user, identifying character information corresponding to the voiceprint data of the user, and extracting a voiceprint feature code of the user from the voiceprint data;
and determining a storage unit for storing user information according to the character information, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for login.
2. The method of claim 1, wherein the voiceprint data is obtained through a microphone of an in-vehicle terminal of the vehicle; each storage unit is arranged on the cloud server;
when a user logs in, recognizing text information corresponding to user voiceprint data through an automobile-mounted terminal, and sending the voiceprint data and the text information to a cloud server; and
extracting a voiceprint feature code of a user from the voiceprint data through a cloud server, determining a storage unit for storing user information according to the received character information, retrieving whether a voiceprint feature code matched with the user exists from the storage unit, if so, determining that the user is a registered user, and extracting a user name and a login password corresponding to the voiceprint feature code for login; if not, the user is refused to log in.
3. The fast log-in method for automobile users according to claim 1, wherein the allocating different users to different storage units according to the difference of the GPS location information comprises the following steps:
determining province or city of the user during registration according to the GPS position information;
the users are assigned to different storage units according to different provinces or cities.
4. The fast login method for the automobile user according to claim 1, wherein the voiceprint feature code corresponding to the voiceprint data is obtained by the following steps when the user is logged in:
acquiring voiceprint data of a user for pronunciation by using the same information template more than twice;
judging whether the similarity of the feature codes in the acquired voiceprint data is greater than a preset value or not, if so, successfully extracting the voiceprint feature codes; if not, the extraction of the voiceprint feature code fails.
5. A vehicle user rapid login device based on GPS position information is characterized by comprising a preset unit, a registration unit and a login unit;
the preset unit is used for presetting more than two storage units for storing the registration information of the user, and each storage unit is respectively provided with different information templates;
the registration unit is used for acquiring GPS position information of the user when the user registers, and distributing different users to different storage units according to the difference of the GPS position information; storing the acquired user name, login password and voiceprint data of the user into a corresponding storage unit, wherein the voiceprint data comprises voiceprint data which is subjected to pronunciation according to an information template of the allocated storage unit and a voiceprint feature code corresponding to the voiceprint data, and the voiceprint feature code comprises acoustic features and rhythm features;
the login unit is used for acquiring voiceprint data input by a user when the user logs in, identifying character information corresponding to the voiceprint data of the user, and extracting a voiceprint feature code of the user from the voiceprint data;
and determining a storage unit for storing user information according to the character information, and extracting a user name and a login password corresponding to the voiceprint feature code from the storage unit for login.
6. The quick login device for the automobile user according to claim 5, wherein the voiceprint data is acquired through a microphone of an automobile-mounted terminal; each storage unit is arranged on the cloud server;
the login unit identifies text information corresponding to user voiceprint data through the automobile-mounted terminal when the user logs in and verifies, and sends the voiceprint data and the text information to the cloud server; and
extracting a voiceprint feature code of a user from the voiceprint data through a cloud server, determining a storage unit for storing user information according to the received character information, retrieving whether a voiceprint feature code matched with the user exists from the storage unit, if so, determining that the user is a registered user, and extracting a user name and a login password corresponding to the voiceprint feature code for login; if not, the user is refused to log in.
7. The fast login device for automobile users according to claim 5, wherein the registration unit assigns different users to different storage units according to the difference of GPS location information, specifically comprising:
determining province or city of the user during registration according to the GPS position information;
the users are assigned to different storage units according to different provinces or cities.
8. The device of claim 5, wherein the registering unit, when registering the user, obtains the voiceprint feature code corresponding to the voiceprint data specifically includes:
acquiring voiceprint data of a user for pronunciation by using the same information template more than twice;
judging whether the similarity of the feature codes in the acquired voiceprint data is greater than a preset value or not, if so, successfully extracting the voiceprint feature codes; if not, the extraction of the voiceprint feature code fails.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710178182.5A CN107105010B (en) | 2017-03-23 | 2017-03-23 | Automobile user rapid login method and device based on GPS (global positioning system) position information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710178182.5A CN107105010B (en) | 2017-03-23 | 2017-03-23 | Automobile user rapid login method and device based on GPS (global positioning system) position information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107105010A CN107105010A (en) | 2017-08-29 |
| CN107105010B true CN107105010B (en) | 2020-02-07 |
Family
ID=59675077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710178182.5A Active CN107105010B (en) | 2017-03-23 | 2017-03-23 | Automobile user rapid login method and device based on GPS (global positioning system) position information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107105010B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829739A (en) * | 2018-05-23 | 2018-11-16 | 出门问问信息科技有限公司 | A kind of information-pushing method and device |
| CN113870613B (en) * | 2021-10-14 | 2022-09-30 | 中国第一汽车股份有限公司 | Parking space determination method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101400121A (en) * | 2008-11-18 | 2009-04-01 | 华为技术有限公司 | Method, system and regional location server for centralized register |
| CN101692314A (en) * | 2009-10-15 | 2010-04-07 | 康华武 | Method for identifying vehicle identity by using vehicle position information and application |
| CN102238189A (en) * | 2011-08-01 | 2011-11-09 | 安徽科大讯飞信息科技股份有限公司 | Voiceprint password authentication method and system |
| CN102999546A (en) * | 2011-09-15 | 2013-03-27 | 富士通株式会社 | Information management method and information management apparatus |
| CN106204855A (en) * | 2016-08-09 | 2016-12-07 | 福建省汽车工业集团云度新能源汽车股份有限公司 | A kind of Application on Voiceprint Recognition automobile accessing method |
-
2017
- 2017-03-23 CN CN201710178182.5A patent/CN107105010B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101400121A (en) * | 2008-11-18 | 2009-04-01 | 华为技术有限公司 | Method, system and regional location server for centralized register |
| CN101692314A (en) * | 2009-10-15 | 2010-04-07 | 康华武 | Method for identifying vehicle identity by using vehicle position information and application |
| CN102238189A (en) * | 2011-08-01 | 2011-11-09 | 安徽科大讯飞信息科技股份有限公司 | Voiceprint password authentication method and system |
| CN102999546A (en) * | 2011-09-15 | 2013-03-27 | 富士通株式会社 | Information management method and information management apparatus |
| CN106204855A (en) * | 2016-08-09 | 2016-12-07 | 福建省汽车工业集团云度新能源汽车股份有限公司 | A kind of Application on Voiceprint Recognition automobile accessing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107105010A (en) | 2017-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106683680B (en) | Speaker recognition method and device, computer equipment and computer readable medium | |
| EP3195311B1 (en) | Method and apparatus for performing speaker recognition | |
| CN108766444B (en) | User identity authentication method, server and storage medium | |
| CN115766031A (en) | Identity verification method, device and equipment | |
| WO2017162112A1 (en) | Identity registration method and device | |
| US20180233152A1 (en) | Voice Signature for User Authentication to Electronic Device | |
| CN110570869A (en) | Voiceprint recognition method, device, equipment and storage medium | |
| CN110400563A (en) | Vehicle-mounted voice instruction identification method, device, computer equipment and storage medium | |
| CN106650350A (en) | Identity authentication method and system | |
| CN106098069B (en) | Identity authentication method and terminal equipment | |
| US20200042686A1 (en) | Method and apparatus for user authentication based on feature information | |
| CN109448732B (en) | Digital string voice processing method and device | |
| CN106888204B (en) | Implicit identity authentication method based on natural interaction | |
| CN107105010B (en) | Automobile user rapid login method and device based on GPS (global positioning system) position information | |
| CN113177850A (en) | Method and device for multi-party identity authentication of insurance | |
| CN106470192B (en) | Identity verification method, device and system | |
| CN107894882B (en) | Voice input method of mobile terminal | |
| CN106098070B (en) | identity authentication method and network system | |
| CN113707157A (en) | Identity verification method and device based on voiceprint recognition, electronic equipment and medium | |
| CN112102547A (en) | Threshold language matching method and device, storage medium and intelligent equipment | |
| CN106921668A (en) | User vehicle fast verification method and device based on Application on Voiceprint Recognition | |
| CN106599637A (en) | Method and device for inputting verification code into verification interface | |
| CN107426143A (en) | The quick accessing method of user vehicle and device based on Application on Voiceprint Recognition | |
| CN114417294A (en) | Method, device, equipment and medium for updating feature vector database | |
| CN108922547B (en) | Identity identification method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 351100 west side of LiHan Road, Jiangxi town, Jiangkou Town, Hanjiang District, Putian, Fujian, China Patentee after: Yundu New Energy Vehicle Co.,Ltd. Address before: 351100 west side of LiHan Road, Jiangxi town, Jiangkou Town, Hanjiang District, Putian, Fujian, China Patentee before: Yundu New Energy Automobile Co.,Ltd. Address after: 351100 west side of LiHan Road, Jiangxi town, Jiangkou Town, Hanjiang District, Putian, Fujian, China Patentee after: Yundu New Energy Automobile Co.,Ltd. Address before: 351100 west side of LiHan Road, Jiangxi town, Jiangkou Town, Hanjiang District, Putian, Fujian, China Patentee before: FJ MOTOR GROUP, YUDO NEW-ENERGY AUTOMOBILE Co.,Ltd. |