The method and apparatus of cloud speech navigation
Technical field
The present invention relates to field of navigation technology, be related specifically to a kind of method and apparatus of cloud speech navigation.
Background technology
Navigating instrument is widely used in vehicle operation at present, and usual navigating instrument is the key word input receiving car owner, searches the destination address of coupling according to key word on backstage.But this mode existing defects, car owner in the process of moving, may change by way of address or destination address at any time, but vehicle drive can be made at driving process in the hole to the operation that navigating instrument carries out text event detection.For solving the problem, some navigating instrument is provided with speech voice input function, is address information, then navigates speech conversion, but its speech identifying function is only limitted to carry out at local terminal, and the accuracy of speech recognition is lower.
Summary of the invention
Fundamental purpose of the present invention, for providing a kind of method and apparatus of cloud speech navigation, improves precision and the speed of navigator speech recognition.
The present invention proposes a kind of method of cloud speech navigation, comprising:
Navigator receives the speech data of user's input, and is sent to high in the clouds speech recognition server;
Described speech data is converted to keyword message by described high in the clouds speech recognition server, and is sent to navigation server;
The address information that described navigation server is corresponding according to described keyword message inquiry, and be sent to described navigator;
Navigator is navigated according to described address information.
Preferably, the address information that described navigation server is corresponding according to keyword message inquiry comprises:
The address informations of many couplings are obtained according to described keyword message and default matching degree.
Described address information is sent to navigator by wireless network.
Preferably, described navigator is carried out navigation according to address information and is comprised:
Point out described address information, select for user;
The address information that user selects is located on map, and starts navigation.
Preferably, after execution prompting address information, also comprise:
When the address information pointed out is more than a predetermined number, manual guidance is carried out at automatic place calls center.
Preferably, described address information comprises destination address and/or longitude and latitude corresponding to destination address.
The present invention also proposes a kind of system of cloud speech navigation, comprises navigator, high in the clouds speech recognition server, navigation server, wherein,
Described navigator, for receiving the speech data of user's input, and is sent to high in the clouds speech recognition server;
Described high in the clouds speech recognition server, for described speech data is converted to keyword message, and is sent to navigation server;
Described navigation server, for the address information corresponding according to described keyword message inquiry, and is sent to described navigator;
Described navigator is also for navigating according to described address information.
Preferably, described navigation server comprises:
Acquisition module, for obtaining the address informations of many couplings according to described keyword message and default matching degree.
Sending module, for being sent to navigator by described address information by wireless network.
Preferably, described navigator comprises:
Reminding module, for pointing out described address information, selects for user;
Locating module, locates on map for address information user selected, and starts navigation.
Preferably, described navigator also comprises:
Calling module, for when the address information pointed out is more than a predetermined number, manual guidance is carried out at automatic place calls center.
Preferably, described address information comprises destination address and/or longitude and latitude corresponding to destination address.
The method and system of a kind of cloud speech navigation that the present invention proposes, carries out the speech recognition of navigation address by high in the clouds speech recognition server, while raising car owner drive safety, substantially increase speed and the precision of speech recognition.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of method one embodiment of cloud speech navigation of the present invention;
Fig. 2 is the structural representation of system one embodiment of cloud speech navigation of the present invention;
Fig. 3 is the structural representation of navigation server in system one embodiment of cloud speech navigation of the present invention;
Fig. 4 is the structural representation of navigator in system one embodiment of cloud speech navigation of the present invention.
The realization of the object of the invention, functional characteristics and advantage will in conjunction with the embodiments, are described further with reference to accompanying drawing.
Embodiment
Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
With reference to Fig. 1, propose method one embodiment of cloud speech navigation of the present invention, comprising:
Step S101, navigator receive the speech data of user's input, and are sent to high in the clouds speech recognition server.This speech data is the voice of the key word about start address or destination address, and the speech recognition request information comprising this speech data is sent to high in the clouds speech recognition server by wireless network by navigator.
Described speech data is converted to keyword message, and is sent to navigation server by step S102, high in the clouds speech recognition server.This speech data is converted to the keyword message of text formatting after receiving and requiring to identify the speech recognition request information of speech data by high in the clouds speech recognition server, and this keyword message is for mating corresponding address information.Due to calculating scale and the capacity of high in the clouds speech recognition server, be far more than navigator, therefore carry out speech recognition by high in the clouds speech recognition server, greatly can improve precision and the speed of speech recognition.
The address information that step S103, described navigation server are corresponding according to described keyword message inquiry, and be sent to described navigator.Navigation server presets a matching degree as 90%, according to this matching degree and above-mentioned key word, can find out the address information that one or more matches.This address information can comprise start address, destination address and start address or longitude and latitude corresponding to destination address.
Step S104, navigator are navigated according to described address information.The address information that navigator is received by speech play, confirms for user.As there are many address informations matched, then navigator broadcast address information successively, each address information can play a number of times preset.When user hears suitable address information, confirm by voice selecting, then the address information that user confirms by navigator notifies map software, starts navigation.As all address informations all finish, user is still non-selected, then navigator can be set to automatic place calls center agent, carries out manual guidance.
The present embodiment carries out the speech recognition of navigation address by high in the clouds speech recognition server, while raising car owner drive safety, substantially increases speed and the precision of speech recognition.
With reference to Fig. 2, propose system one embodiment of cloud speech navigation of the present invention, comprise navigator 10, high in the clouds speech recognition server 20, navigation server 30, wherein, described navigator 10, for receiving the speech data of user's input, and is sent to high in the clouds speech recognition server 20; Described high in the clouds speech recognition server 20, for described speech data is converted to keyword message, and is sent to navigation server 30; Described navigation server 30, for the address information corresponding according to described keyword message inquiry, and is sent to described navigator 10; Described navigator 10 is also for navigating according to described address information.
With reference to Fig. 3, navigation server 30 comprises:
Acquisition module 31, for obtaining the address informations of many couplings according to described keyword message and default matching degree.
Sending module 32, for being sent to navigator by described address information by wireless network.
With reference to Fig. 4, navigator 10 comprises:
Reminding module 11, for pointing out described address information, selects for user;
Locating module 12, locates on map for address information user selected, and starts navigation;
Calling module 13, for when the address information pointed out is more than a predetermined number, manual guidance is carried out at automatic place calls center.
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 of the key word about start address or destination address, and the speech recognition request information comprising this speech data is sent to high in the clouds speech recognition server 20 by wireless network by navigator 10.
Described speech data is converted to keyword message by high in the clouds speech recognition server 20, and is sent to navigation server 30.This speech data is converted to the keyword message of text formatting after receiving and requiring to identify the speech recognition request information of speech data by high in the clouds speech recognition server 20, and this keyword message is for mating corresponding address information.Due to calculating scale and the capacity of high in the clouds speech recognition server 20, be far more than navigator 10, therefore carry out speech recognition by high in the clouds speech recognition server 20, greatly can improve precision and the speed of speech recognition.
The acquisition module 31 of navigation server 30 according to the address information of described keyword message inquiry correspondence, and is sent to described navigator by sending module 32.Navigation server 30 presets a matching degree as 90%, and acquisition module 31, according to this matching degree and above-mentioned key word, can find out the address information that one or more matches.This address information can comprise start address, destination address and start address or longitude and latitude corresponding to destination address.
Navigator 10 is navigated according to described address information.The address information that reminding module 11 is received by speech play, confirms for user.As there are many address informations matched, then reminding module 11 broadcast address information successively, each address information can play a number of times preset.When user hears suitable address information, confirm by voice selecting, then the address information that user confirms by locating module 12 notifies map software, starts navigation.As all address informations all finish, user is still non-selected, then calling module 13 can be set to automatic place calls center agent, carries out manual guidance.
The present embodiment carries out the speech recognition of navigation address by high in the clouds speech recognition server 20, while raising car owner drive safety, substantially increases speed and the precision of speech recognition.
The foregoing is only the preferred embodiments of the present invention; not thereby the scope of the claims of the present invention is limited; every utilize instructions of the present invention and accompanying drawing content to do equivalent structure or equivalent flow process conversion; or be directly or indirectly used in other relevant technical fields, be all in like manner included in scope of patent protection of the present invention.