Dynamic voice label information query system and information query method thereof
Technical field
The present invention relates to the technology of information inquiry, particularly relate to the technology of a kind of dynamic voice label information query system and information query method thereof.
Background technology
When steering vehicle, if the user wants just can access internet inquire relevant information (such as weather in car, stock information, real-time traffic, periphery interest point information etc.), from convenient and security consideration, the user more wishes only just can inquire these information by voice command, rather than removes operating handset or other mobile unit when driving.
A kind of method in common is the system that has static key query word sound bank of installing in terminal device, when the user says a key query word, system can become literal to speech conversion according to the sound bank of key query word, then the key word of text is sent to network and inquires about.Because sending to the data of network is the text keyword data, its data volume is less, can be so that the cost of data network transmission course be lower, efficient is higher, the key query word sound bank that but the shortcoming of this method is a terminal device itself can store is limited, because user's query demand can't be expected by system, so the key query word sound bank of terminal device storage itself must be enough big, can cover most user inquiring demand; In addition, if the user expects a updated information (such as coming out), new information key word does not exist in key query word sound bank, and system just can't discern this key word, perhaps identification error, and the user just can't inquire the information of wanting.
Another kind method is that terminal device directly sends to the network agent server to user's acoustic information data, the network agent server is converted to key word to be checked to acoustic information data (such as wav file), and the webserver utilizes this key word decorrelation query site to relevant information then.The benefit of this method is that equipment itself does not need to dispose a very big storer; And it is, therefore also very little to user's query demand restriction because the network agent server can have a very big keyword query sound bank.But shortcoming is all to need to upload bigger voice data (such as wav file) for terminal device during each inquiry, cause the cost of data network transmission course higher, transmission time is longer, also need acting server to convert text data at every turn, whole process efficiency is not high, and the proxy server software design is complicated.
Summary of the invention
At the defective that exists in the above-mentioned prior art, technical matters to be solved by this invention provides a kind of easy to use, query demand restriction to the user is little, and the inquiry cost is low, dynamic voice label information query system and information query method thereof that search efficiency is high.
In order to solve the problems of the technologies described above, a kind of dynamic voice label information query system provided by the present invention, comprise client device and content server, it is characterized in that: be provided with microprocessor, communication module, GPS navigation module, speech recognition engine, data memory module and microphone in the described client device;
Described communication module is through the Internet connection content server, and described GPS navigation module receives GPS navigation information with wireless mode, and described microphone connects the audio input port of microprocessor, and described microprocessor connects and controls each module and move;
Fixedly voice label tabulation and dynamic voice label tabulation have been deposited in the described data memory module, there are download instruction voice label and a plurality of query statement voice label in the described fixedly voice label tabulation, have a plurality of road name voice labels in the described dynamic voice label tabulation;
Described speech recognition engine is built in the microprocessor or deposits in the data memory module, is used to discern the voice that microphone picks up;
Deposit the road name tabulation in each city in the described content server.
The information query method of dynamic voice label information query system provided by the invention is characterized in that, concrete steps are as follows:
1) client device picks up voice by microphone, and by speech recognition engine the voice that pick up and the tabulation of the fixedly voice label in the data memory module and dynamic voice label tabulation is compared, and then repeats this step if comparison gets nowhere;
2) comparison result according to step 1 generates a download request or query requests, or upgrades existing query requests;
If in the step 1, the voice that pick up and fixedly the download instruction voice label in the voice label tabulation compare successfully, be download instruction then with the speech recognition of picking up, and generate a download request that includes this instruction, gather the current location information of client device then by the GPS navigation module, and the current location information of being gathered is added in the download request;
If in the step 1, the voice that pick up and fixedly the query statement voice label in the voice label tabulation compare successfully, then be and the successful corresponding query statement of query statement voice label of comparison with the speech recognition of picking up, and check whether there is query requests, if do not return step 1 after not existing query requests then directly to generate a query requests that includes this query statement, if exist query requests then to cancel this query requests earlier, and then return step 1 after generating a query requests that includes this query statement;
If in the step 1, the road name voice label in voice that pick up and the dynamic voice label tabulation is compared successfully, then checks whether there is query requests, if do not exist query requests then to return step 1; If exist query requests then to be and the successful corresponding road name text of road name voice label of comparison, and the text be added in the query requests with the speech recognition of picking up;
3) client device sends to content server by communication module with download request or query requests;
After content server is received download request, determine city, client device place according to the current location information in this request earlier, the road name tabulation with this city sends to client device then; After client device is received the road name tabulation that content server passes back, empty the dynamic voice label tabulation in the data memory module earlier, convert each road name in the road name tabulation to the road name voice label one by one again, and deposit in the dynamic voice label tabulation after emptying;
After content server is received query requests, be that the query statement in this request carried out in key word with the road name text in this request, and Query Result is sent to client device; After client device is received the Query Result that content server passes back, play Query Result or show Query Result by graphics mode by the audio frequency mode.
Dynamic voice label information query system provided by the invention and information query method thereof have following beneficial effect:
1) client device picks up voice by microphone, and by the speech recognition engine voice command recognition, makes user in car only need open one's mouth and can carry out information inquiry, and is very easy to use;
2) client device can be according to the road name voice label in the tabulation of user's current location renewal dynamic voice label, work as the user like this and arrive the another one place, just be easy to obtain local road name voice label, utilize local road name voice label, the user just can inquire near the point of interest of real-time traffic, navigation information or road of local road, and is little to user's query demand restriction;
3) only deposit the voice label of some fixed instruction and the road name voice label of locality in the local memory module, local road name voice label can dynamically update according to user's needs, its data volume is less, and is therefore not high to the storage capacity requirement of local memory module;
4) because voice label all is stored in the client device, user's voice data can be discerned by speech recognition engine fast, and be converted into the text keyword that to inquire about fast, send query requests by network to content server and have only very little network traffics data, send voice data relatively to network, the inquiry cost of this design is low, the search efficiency height.
Description of drawings
Fig. 1 is the structured flowchart of the dynamic voice label information query system of the embodiment of the invention;
Fig. 2 is the information inquiry process flow diagram of the dynamic voice label information query system of the embodiment of the invention;
Fig. 3 is the process flow diagram that the renewal dynamic voice label of the dynamic voice label information query system of the embodiment of the invention is tabulated;
Fig. 4 is the process flow diagram of real-time traffic situation of Nanjing Road, inquiry Shanghai City of the dynamic voice label information query system of the embodiment of the invention.
Embodiment
Below in conjunction with description of drawings embodiments of the invention are described in further detail, but present embodiment is not limited to the present invention, every employing analog structure of the present invention and similar variation thereof all should be listed protection scope of the present invention in.
As shown in Figure 1, a kind of dynamic voice label information query system that the embodiment of the invention provided, comprise a plurality of client devices 1 and a plurality of content server 2, it is characterized in that: be provided with microprocessor 11, communication module 12, GPS navigation module 13, speech recognition engine 14, data memory module 15 and microphone 16 in each client device 1;
Described communication module 12 is 3 each content server 2 of connection through the internet, and described GPS navigation module 13 receives GPS navigation information with wireless mode, and described microphone 16 connects the audio input port of microprocessors 11, and described microprocessor 11 connects also controls each module operation;
Fixedly voice label tabulation and dynamic voice label tabulation have been deposited in the described data memory module 15, there are download instruction voice label and a plurality of query statement voice label in the described fixedly voice label tabulation, have a plurality of road name voice labels in the described dynamic voice label tabulation;
Described speech recognition engine 14 is built in the microprocessor or deposits in the data memory module, is used to discern the voice that microphone 16 picks up;
Deposit the road name tabulation in each city in the described content server.
In the embodiment of the invention, described GPS navigation module 13 is that model is the GPS navigation chip of SirFIII, described speech recognition engine 14 is ScanSoft VoCon 3200 software engines, described microprocessor 11 is that model is little process chip of PowerPC5200, described communication module 12 is that model is the Bluetooth chip of CSR BlueCore6, interconnect with the external communications equipment that is built-in with the Bluetooth transmission module and can be connected the internet by this Bluetooth chip when client device 1 uses, and then be connected to the internet by external communications equipment;
In the embodiment of the invention, described communication module 12 also can be gsm module, CDMA module or ADSL Modem;
As shown in Figure 2, the information query method of the dynamic voice label information query system that the embodiment of the invention provided, concrete steps are as follows:
1) client device picks up voice by microphone, and by speech recognition engine the voice that pick up and the tabulation of the fixedly voice label in the data memory module and dynamic voice label tabulation is compared, and then repeats this step if comparison gets nowhere;
2) comparison result according to step 1 generates a download request or query requests, or upgrades existing query requests;
If in the step 1, the voice that pick up and fixedly the download instruction voice label in the voice label tabulation compare successfully, be download instruction then with the speech recognition of picking up, and generate a download request that includes this instruction, gather the current location information (such as longitude and latitude) of client device then by the GPS navigation module, and the current location information of being gathered is added in the download request;
If in the step 1, the voice that pick up and fixedly the query statement voice label in the voice label tabulation compare successfully, then be and the successful corresponding query statement of query statement voice label of comparison with the speech recognition of picking up, and check whether there is query requests, if do not return step 1 after not existing query requests then directly to generate a query requests that includes this query statement, if exist query requests then to cancel this query requests earlier, and then return step 1 after generating a query requests that includes this query statement;
If in the step 1, the road name voice label in voice that pick up and the dynamic voice label tabulation is compared successfully, then checks whether there is query requests, if do not exist query requests then to return step 1; If exist query requests then to be and the successful corresponding road name text of road name voice label of comparison, and the text be added in the query requests with the speech recognition of picking up;
3) client device sends to content server by communication module with download request or query requests;
After content server is received download request, determine city, client device place according to the current location information in this request earlier, the road name tabulation with this city sends to client device then; After client device is received the road name tabulation that content server passes back, empty the dynamic voice label tabulation in the data memory module earlier, convert each road name in the road name tabulation to the road name voice label one by one again, and deposit in the dynamic voice label tabulation after emptying;
After content server is received query requests, be that the query statement in this request carried out in key word with the road name text in this request, and Query Result is sent to client device; After client device is received the Query Result that content server passes back, play Query Result or show Query Result by graphics mode by the audio frequency mode.
As shown in Figure 3, when the road name voice label that do not have the user to inquire about in the tabulation of the dynamic voice label of client device, (use Pekinese's road tabulation usually in Beijing such as the user, in case and the user has arrived Shanghai, the user wants to inquire about the condition of road surface in Shanghai, must use the road tabulation in Shanghai), this moment, the user said voice command " download link name ", client device by speech recognition engine compare out this voice command and fixedly the download instruction voice label in the voice label tabulation be complementary, be about to it and be identified as download instruction, generate a download request that includes this instruction then, and the current location information (such as longitude and latitude) that adding GPS navigation module is gathered in download request, the form of this download request is: (such as city, the current place of user is Shanghai to download instruction+current location information, promptly in the scope of Shanghai, this moment, the form of download request was the current location information that the GPS navigation module is gathered: download instruction+Shanghai); And then download request is sent to content server by communication module, content server sends to client device to the road name tabulation with the pairing city of current location information (such as Shanghai) according to the download request of receiving (download instruction+current location information); Client device is received after the road name tabulation, converts each road name in the road name tabulation to the road name voice label one by one, and deposits in the dynamic voice label tabulation after emptying;
As shown in Figure 4, want to inquire about the real-time traffic situation of Nanjing Road in Shanghai as the user, and the road name of having downloaded Shanghai is tabulated, this moment, the user said voice command " real-time traffic ", client device by speech recognition engine compare out this voice command and fixedly the real-time traffic query statement voice label in the voice label tabulation be complementary, be about to it and be identified as the real-time traffic query statement, generate a query requests that includes this instruction then, and with voice mode or graphics mode prompting user " please say road title ", the road name voice label " Nanjing Road " that client device is compared out in this voice command and the dynamic voice label tabulation by speech recognition engine is complementary, be about to it and be identified as the text of content for " Nanjing Road ", and the text is added in the query requests, this moment, the form of query requests was: real-time traffic query statement+Nanjing Road; And then query requests being sent to content server by communication module, it be key word execution real-time traffic query statement that content server is carried out with " Nanjing Road ", and Query Result is sent to client device; After client device is received the Query Result that content server passes back, play Query Result or show Query Result by graphics mode by the audio frequency mode.