The method and apparatus of high in the clouds Voice Navigation
Technical field
The present invention relates to field of navigation technology, specially refer to the method and apparatus of a kind of high in the clouds Voice Navigation.
Background technology
Navigating instrument is widely used in the vehicle drive process at present, and navigating instrument is the key word input that receives the car owner usually, searches the destination address of coupling on the backstage according to key word.But there is defective in this mode, and the car owner possibly change by way of the address or destination address in the process of moving at any time, but can make vehicle drive in the hole at driving process to the operation that navigating instrument carries out the literal input.For addressing the above problem, some navigating instrument is provided with speech voice input function, is address information with speech conversion, navigate, but its speech identifying function only limits to carry out at local terminal again, and the accuracy of speech recognition is lower.
Summary of the invention
Fundamental purpose of the present invention is the method and apparatus that the Voice Navigation of a kind of high in the clouds is provided, and improves the precision and the speed of navigator speech recognition.
The present invention proposes the method for a kind of high in the clouds Voice Navigation, comprising:
Navigator receives the speech data of user's input, and is sent to the high in the clouds speech recognition server;
Said high in the clouds speech recognition server converts said speech data into keyword message, and is sent to navigation server;
Said navigation server is inquired about corresponding address information according to said keyword message, and is sent to said navigator;
Navigator is navigated according to said address information.
Preferably, said navigation server comprises according to keyword message inquiry corresponding address information:
Obtain the address information of many couplings according to said keyword message and preset matching degree.
Said address information is sent to navigator through wireless network.
Preferably, said navigator is navigated according to address information and is comprised:
Point out said address information, supply the user to select;
The address information that the user selects is located on map, and begin navigation.
Preferably, after carrying out the prompting address information, also comprise:
When the address information of prompting surpassed a predetermined number, manual guidance was carried out at the place calls center automatically.
Preferably, said address information comprises destination address and/or the corresponding longitude and latitude of destination address.
The present invention also proposes the system of a kind of high in the clouds Voice Navigation, comprises navigator, high in the clouds speech recognition server, navigation server, wherein,
Said navigator is used to receive the speech data of user's input, and is sent to the high in the clouds speech recognition server;
Said high in the clouds speech recognition server is used for converting said speech data into keyword message, and is sent to navigation server;
Said navigation server is used for according to said keyword message inquiry corresponding address information, and is sent to said navigator;
Said navigator also is used for navigating according to said address information.
Preferably, said navigation server comprises:
Acquisition module is used for obtaining according to said keyword message and preset matching degree the address information of many couplings.
Sending module is used for said address information is sent to navigator through wireless network.
Preferably, said navigator comprises:
Reminding module is used to point out said address information, supplies the user to select;
Locating module is used for the address information that the user selects is located on map, and begins navigation.
Preferably, said navigator also comprises:
Calling module is used for when the address information of prompting surpasses a predetermined number, and manual guidance is carried out at the place calls center automatically.
Preferably, said address information comprises destination address and/or the corresponding longitude and latitude of destination address.
The method and system of a kind of high in the clouds Voice Navigation that the present invention proposes through the navigate speech recognition of address of high in the clouds speech recognition server, when improving car owner's drive safety, has improved the speed and the precision of speech recognition greatly.
Description of drawings
Fig. 1 is the schematic flow sheet of method one embodiment of high in the clouds of the present invention Voice Navigation;
Fig. 2 is the structural representation of one embodiment of system of high in the clouds of the present invention Voice Navigation;
Fig. 3 is the structural representation of navigation server among one embodiment of system of high in the clouds of the present invention Voice Navigation;
Fig. 4 is the structural representation of navigator among one embodiment of system of high in the clouds of the present invention Voice Navigation.
The realization of the object of the invention, functional characteristics and advantage will combine embodiment, further specify with reference to accompanying drawing.
Embodiment
Should be appreciated that specific embodiment described herein only in order to explanation the present invention, and be not used in qualification the present invention.
With reference to Fig. 1, method one embodiment of high in the clouds of the present invention Voice Navigation is proposed, comprising:
Step S101, navigator receive the speech data of user's input, and are sent to the high in the clouds speech recognition server.This speech data is the voice about the key word of start address or destination address, and navigator will comprise that the speech recognition solicited message of this speech data is sent to the high in the clouds speech recognition server through wireless network.
Step S102, high in the clouds speech recognition server convert said speech data into keyword message, and are sent to navigation server.After the high in the clouds speech recognition server receives and requires to identify the speech recognition solicited message of speech data, convert this speech data the keyword message of text formatting into, this keyword message is used to mate corresponding address information.Because the calculating scale and the capacity of high in the clouds speech recognition server far are more than navigator, therefore carry out speech recognition through the high in the clouds speech recognition server, can improve the precision and the speed of speech recognition greatly.
Step S103, said navigation server are inquired about corresponding address information according to said keyword message, and are sent to said navigator.The preset matching degree of navigation server is as 90%, according to this matching degree and above-mentioned key word, can find out one or many address informations that are complementary.This address information can comprise start address, destination address and start address or the corresponding longitude and latitude of destination address.
Step S104, navigator are navigated according to said address information.The address information that navigator receives through speech play supplies the user to confirm.As having many address informations that are complementary, navigator broadcast address information successively then, each address information can be play a preset number of times.When the user hears suitable address information, can confirm that then navigator begins navigation with the address information notice map software that the user confirms through voice selecting.All finish like all address informations, the user is still non-selected, and then navigator can be set to automatic place calls center and attends a banquet, and carries out manual guidance.
Present embodiment when improving car owner's drive safety, has improved the speed and the precision of speech recognition through the navigate speech recognition of address of high in the clouds speech recognition server greatly.
With reference to Fig. 2, one embodiment of system of high in the clouds of the present invention Voice Navigation is proposed, comprise navigator 10, high in the clouds speech recognition server 20, navigation server 30; Wherein, Said navigator 10 is used to receive the speech data of user's input, and is sent to high in the clouds speech recognition server 20; Said high in the clouds speech recognition server 20 is used for converting said speech data into keyword message, and is sent to navigation server 30; Said navigation server 30 is used for according to said keyword message inquiry corresponding address information, and is sent to said navigator 10; Said navigator 10 also is used for navigating according to said address information.
With reference to Fig. 3, navigation server 30 comprises:
Acquisition module 31 is used for obtaining according to said keyword message and preset matching degree the address information of many couplings.
Sending module 32 is used for said address information is sent to navigator through wireless network.
With reference to Fig. 4, navigator 10 comprises:
Reminding module 11 is used to point out said address information, supplies the user to select;
Locating module 12 is used for the address information that the user selects is located on map, and begins navigation;
Calling module 13 is used for when the address information of prompting surpasses a predetermined number, and manual guidance is carried out at the place calls center automatically.
Navigator 10 receives the speech data of user's input, and is sent to high in the clouds speech recognition server 20.This speech data is the voice about the key word of start address or destination address, and navigator 10 will comprise that the speech recognition solicited message of this speech data is sent to high in the clouds speech recognition server 20 through wireless network.
High in the clouds speech recognition server 20 converts said speech data into keyword message, and is sent to navigation server 30.After high in the clouds speech recognition server 20 receives and requires to identify the speech recognition solicited message of speech data, convert this speech data the keyword message of text formatting into, this keyword message is used to mate corresponding address information.Because the calculating scale and the capacity of high in the clouds speech recognition server 20 far are more than navigator 10, therefore carry out speech recognition through high in the clouds speech recognition server 20, can improve the precision and the speed of speech recognition greatly.
The acquisition module 31 of navigation server 30 is inquired about corresponding address information according to said keyword message, and is sent to said navigator by sending module 32.The preset matching degrees of navigation server 30 are as 90%, and acquisition module 31 is according to this matching degree and above-mentioned key word, can find out one or many address informations that are complementary.This address information can comprise start address, destination address and start address or the corresponding longitude and latitude of destination address.
Navigator 10 is navigated according to said address information.The address information that reminding module 11 receives through speech play supplies the user to confirm.As having many address informations that are complementary, reminding module 11 broadcast address information successively then, each address information can be play a preset number of times.When the user hears suitable address information, can confirm that then locating module 12 begins navigation with the address information notice map software that the user confirms through voice selecting.All finish like all address informations, the user is still non-selected, and then calling module 13 can be set to automatic place calls center and attends a banquet, and carries out manual guidance.
Present embodiment when improving car owner's drive safety, has improved the speed and the precision of speech recognition through the navigate speech recognition of address of high in the clouds speech recognition server 20 greatly.
The above is merely the preferred embodiments of the present invention; Be not so limit claim of the present invention; Every equivalent structure or equivalent flow process conversion that utilizes instructions of the present invention and accompanying drawing content to be done; Or directly or indirectly be used in other relevant technical fields, all in like manner be included in the scope of patent protection of the present invention.